Compare commits

...

18 Commits

Author SHA1 Message Date
zhu
2d1397c277 1 2026-05-13 16:59:26 +08:00
zhu
cb5a13d352 1 2026-05-13 11:22:10 +08:00
zhu
302311b3af 1 2026-05-12 17:58:27 +08:00
zhu
c7cb977243 11 2026-05-12 15:26:17 +08:00
zhu
cf7ea741a6 优化了popup 2026-05-12 11:10:21 +08:00
zhu
a59178b816 1 2026-05-11 17:57:53 +08:00
zhu
f8972f72ba ui+功能一样 2026-05-11 17:24:53 +08:00
zhu
6677ec5eec 1 2026-05-09 18:51:44 +08:00
zhu
186840ba23 1 2026-05-09 17:48:31 +08:00
zhu
30f9467cc8 1 2026-05-09 17:16:08 +08:00
zhu
6587b0c1d9 1 2026-05-07 09:38:05 +08:00
zhu
d6dc8a0db4 1 2026-05-07 09:29:56 +08:00
zhu
a22f1a42e4 修改配置+优化爬取 2026-05-06 17:42:40 +08:00
zhu
7e2a83efd6 1 2026-05-06 15:34:26 +08:00
zhu
40df507300 1 2026-05-06 14:04:05 +08:00
zhu
d78d70bde0 1 2026-05-06 10:52:45 +08:00
zhu
53e4f0b2f4 注释 2026-05-06 10:22:38 +08:00
zhu
350d4fc2e2 1 2026-05-06 10:16:11 +08:00
43 changed files with 4624 additions and 938 deletions

1
.gitignore vendored
View File

@@ -9,6 +9,7 @@ lerna-debug.log*
node_modules node_modules
dist dist
storeai-extension-v0.1.0
dist-ssr dist-ssr
*.local *.local

View File

@@ -19,5 +19,3 @@
7.在窗口中记得显示一个取消按钮,点击后关闭窗口,取消爬取 7.在窗口中记得显示一个取消按钮,点击后关闭窗口,取消爬取
# 具体代码实现流程
请阅读./step.md文档并严格按照步骤进行执行

View File

@@ -22,9 +22,14 @@ export default defineManifest({
}, },
], ],
host_permissions: ['https://*/*', 'http://*/*'], host_permissions: ['https://*/*', 'http://*/*'],
permissions: ['storage', 'tabs', 'scripting', 'activeTab', 'windows'], permissions: ['storage', 'tabs', 'scripting', 'activeTab', 'windows', 'alarms'],
background: { background: {
service_worker: 'src/background/index.ts', service_worker: 'src/background/index.ts',
type: 'module', type: 'module',
}, },
externally_connectable: {
matches: [
"http://localhost/*",
]
}
}); });

View File

@@ -1,7 +1,7 @@
{ {
"name": "vite-project", "name": "vite-project",
"private": true, "private": true,
"version": "0.0.0", "version": "0.1.4",
"type": "module", "type": "module",
"scripts": { "scripts": {
"dev": "vite", "dev": "vite",
@@ -9,6 +9,7 @@
"preview": "vite preview" "preview": "vite preview"
}, },
"dependencies": { "dependencies": {
"axios": "^1.16.0",
"pinia": "^3.0.4", "pinia": "^3.0.4",
"vue": "^3.5.32", "vue": "^3.5.32",
"vue-router": "^5.0.6" "vue-router": "^5.0.6"

211
pnpm-lock.yaml generated
View File

@@ -8,6 +8,9 @@ importers:
.: .:
dependencies: dependencies:
axios:
specifier: ^1.16.0
version: 1.16.0
pinia: pinia:
specifier: ^3.0.4 specifier: ^3.0.4
version: 3.0.4(typescript@5.9.3)(vue@3.5.33(typescript@5.9.3)) version: 3.0.4(typescript@5.9.3)(vue@3.5.33(typescript@5.9.3))
@@ -152,36 +155,42 @@ packages:
engines: {node: '>= 10.0.0'} engines: {node: '>= 10.0.0'}
cpu: [arm] cpu: [arm]
os: [linux] os: [linux]
libc: [glibc]
'@parcel/watcher-linux-arm-musl@2.5.6': '@parcel/watcher-linux-arm-musl@2.5.6':
resolution: {integrity: sha512-Ve3gUCG57nuUUSyjBq/MAM0CzArtuIOxsBdQ+ftz6ho8n7s1i9E1Nmk/xmP323r2YL0SONs1EuwqBp2u1k5fxg==} resolution: {integrity: sha512-Ve3gUCG57nuUUSyjBq/MAM0CzArtuIOxsBdQ+ftz6ho8n7s1i9E1Nmk/xmP323r2YL0SONs1EuwqBp2u1k5fxg==}
engines: {node: '>= 10.0.0'} engines: {node: '>= 10.0.0'}
cpu: [arm] cpu: [arm]
os: [linux] os: [linux]
libc: [musl]
'@parcel/watcher-linux-arm64-glibc@2.5.6': '@parcel/watcher-linux-arm64-glibc@2.5.6':
resolution: {integrity: sha512-f2g/DT3NhGPdBmMWYoxixqYr3v/UXcmLOYy16Bx0TM20Tchduwr4EaCbmxh1321TABqPGDpS8D/ggOTaljijOA==} resolution: {integrity: sha512-f2g/DT3NhGPdBmMWYoxixqYr3v/UXcmLOYy16Bx0TM20Tchduwr4EaCbmxh1321TABqPGDpS8D/ggOTaljijOA==}
engines: {node: '>= 10.0.0'} engines: {node: '>= 10.0.0'}
cpu: [arm64] cpu: [arm64]
os: [linux] os: [linux]
libc: [glibc]
'@parcel/watcher-linux-arm64-musl@2.5.6': '@parcel/watcher-linux-arm64-musl@2.5.6':
resolution: {integrity: sha512-qb6naMDGlbCwdhLj6hgoVKJl2odL34z2sqkC7Z6kzir8b5W65WYDpLB6R06KabvZdgoHI/zxke4b3zR0wAbDTA==} resolution: {integrity: sha512-qb6naMDGlbCwdhLj6hgoVKJl2odL34z2sqkC7Z6kzir8b5W65WYDpLB6R06KabvZdgoHI/zxke4b3zR0wAbDTA==}
engines: {node: '>= 10.0.0'} engines: {node: '>= 10.0.0'}
cpu: [arm64] cpu: [arm64]
os: [linux] os: [linux]
libc: [musl]
'@parcel/watcher-linux-x64-glibc@2.5.6': '@parcel/watcher-linux-x64-glibc@2.5.6':
resolution: {integrity: sha512-kbT5wvNQlx7NaGjzPFu8nVIW1rWqV780O7ZtkjuWaPUgpv2NMFpjYERVi0UYj1msZNyCzGlaCWEtzc+exjMGbQ==} resolution: {integrity: sha512-kbT5wvNQlx7NaGjzPFu8nVIW1rWqV780O7ZtkjuWaPUgpv2NMFpjYERVi0UYj1msZNyCzGlaCWEtzc+exjMGbQ==}
engines: {node: '>= 10.0.0'} engines: {node: '>= 10.0.0'}
cpu: [x64] cpu: [x64]
os: [linux] os: [linux]
libc: [glibc]
'@parcel/watcher-linux-x64-musl@2.5.6': '@parcel/watcher-linux-x64-musl@2.5.6':
resolution: {integrity: sha512-1JRFeC+h7RdXwldHzTsmdtYR/Ku8SylLgTU/reMuqdVD7CtLwf0VR1FqeprZ0eHQkO0vqsbvFLXUmYm/uNKJBg==} resolution: {integrity: sha512-1JRFeC+h7RdXwldHzTsmdtYR/Ku8SylLgTU/reMuqdVD7CtLwf0VR1FqeprZ0eHQkO0vqsbvFLXUmYm/uNKJBg==}
engines: {node: '>= 10.0.0'} engines: {node: '>= 10.0.0'}
cpu: [x64] cpu: [x64]
os: [linux] os: [linux]
libc: [musl]
'@parcel/watcher-win32-arm64@2.5.6': '@parcel/watcher-win32-arm64@2.5.6':
resolution: {integrity: sha512-3ukyebjc6eGlw9yRt678DxVF7rjXatWiHvTXqphZLvo7aC5NdEgFufVwjFfY51ijYEWpXbqF5jtrK275z52D4Q==} resolution: {integrity: sha512-3ukyebjc6eGlw9yRt678DxVF7rjXatWiHvTXqphZLvo7aC5NdEgFufVwjFfY51ijYEWpXbqF5jtrK275z52D4Q==}
@@ -240,36 +249,42 @@ packages:
engines: {node: ^20.19.0 || >=22.12.0} engines: {node: ^20.19.0 || >=22.12.0}
cpu: [arm64] cpu: [arm64]
os: [linux] os: [linux]
libc: [glibc]
'@rolldown/binding-linux-arm64-musl@1.0.0-rc.17': '@rolldown/binding-linux-arm64-musl@1.0.0-rc.17':
resolution: {integrity: sha512-b/CgbwAJpmrRLp02RPfhbudf5tZnN9nsPWK82znefso832etkem8H7FSZwxrOI9djcdTP7U6YfNhbRnh7djErg==} resolution: {integrity: sha512-b/CgbwAJpmrRLp02RPfhbudf5tZnN9nsPWK82znefso832etkem8H7FSZwxrOI9djcdTP7U6YfNhbRnh7djErg==}
engines: {node: ^20.19.0 || >=22.12.0} engines: {node: ^20.19.0 || >=22.12.0}
cpu: [arm64] cpu: [arm64]
os: [linux] os: [linux]
libc: [musl]
'@rolldown/binding-linux-ppc64-gnu@1.0.0-rc.17': '@rolldown/binding-linux-ppc64-gnu@1.0.0-rc.17':
resolution: {integrity: sha512-4EII1iNGRUN5WwGbF/kOh/EIkoDN9HsupgLQoXfY+D1oyJm7/F4t5PYU5n8SWZgG0FEwakyM8pGgwcBYruGTlA==} resolution: {integrity: sha512-4EII1iNGRUN5WwGbF/kOh/EIkoDN9HsupgLQoXfY+D1oyJm7/F4t5PYU5n8SWZgG0FEwakyM8pGgwcBYruGTlA==}
engines: {node: ^20.19.0 || >=22.12.0} engines: {node: ^20.19.0 || >=22.12.0}
cpu: [ppc64] cpu: [ppc64]
os: [linux] os: [linux]
libc: [glibc]
'@rolldown/binding-linux-s390x-gnu@1.0.0-rc.17': '@rolldown/binding-linux-s390x-gnu@1.0.0-rc.17':
resolution: {integrity: sha512-AH8oq3XqQo4IibpVXvPeLDI5pzkpYn0WiZAfT05kFzoJ6tQNzwRdDYQ45M8I/gslbodRZwW8uxLhbSBbkv96rA==} resolution: {integrity: sha512-AH8oq3XqQo4IibpVXvPeLDI5pzkpYn0WiZAfT05kFzoJ6tQNzwRdDYQ45M8I/gslbodRZwW8uxLhbSBbkv96rA==}
engines: {node: ^20.19.0 || >=22.12.0} engines: {node: ^20.19.0 || >=22.12.0}
cpu: [s390x] cpu: [s390x]
os: [linux] os: [linux]
libc: [glibc]
'@rolldown/binding-linux-x64-gnu@1.0.0-rc.17': '@rolldown/binding-linux-x64-gnu@1.0.0-rc.17':
resolution: {integrity: sha512-cLnjV3xfo7KslbU41Z7z8BH/E1y5mzUYzAqih1d1MDaIGZRCMqTijqLv76/P7fyHuvUcfGsIpqCdddbxLLK9rA==} resolution: {integrity: sha512-cLnjV3xfo7KslbU41Z7z8BH/E1y5mzUYzAqih1d1MDaIGZRCMqTijqLv76/P7fyHuvUcfGsIpqCdddbxLLK9rA==}
engines: {node: ^20.19.0 || >=22.12.0} engines: {node: ^20.19.0 || >=22.12.0}
cpu: [x64] cpu: [x64]
os: [linux] os: [linux]
libc: [glibc]
'@rolldown/binding-linux-x64-musl@1.0.0-rc.17': '@rolldown/binding-linux-x64-musl@1.0.0-rc.17':
resolution: {integrity: sha512-0phclDw1spsL7dUB37sIARuis2tAgomCJXAHZlpt8PXZ4Ba0dRP1e+66lsRqrfhISeN9bEGNjQs+T/Fbd7oYGw==} resolution: {integrity: sha512-0phclDw1spsL7dUB37sIARuis2tAgomCJXAHZlpt8PXZ4Ba0dRP1e+66lsRqrfhISeN9bEGNjQs+T/Fbd7oYGw==}
engines: {node: ^20.19.0 || >=22.12.0} engines: {node: ^20.19.0 || >=22.12.0}
cpu: [x64] cpu: [x64]
os: [linux] os: [linux]
libc: [musl]
'@rolldown/binding-openharmony-arm64@1.0.0-rc.17': '@rolldown/binding-openharmony-arm64@1.0.0-rc.17':
resolution: {integrity: sha512-0ag/hEgXOwgw4t8QyQvUCxvEg+V0KBcA6YuOx9g0r02MprutRF5dyljgm3EmR02O292UX7UeS6HzWHAl6KgyhA==} resolution: {integrity: sha512-0ag/hEgXOwgw4t8QyQvUCxvEg+V0KBcA6YuOx9g0r02MprutRF5dyljgm3EmR02O292UX7UeS6HzWHAl6KgyhA==}
@@ -342,24 +357,28 @@ packages:
engines: {node: '>= 20'} engines: {node: '>= 20'}
cpu: [arm64] cpu: [arm64]
os: [linux] os: [linux]
libc: [glibc]
'@tailwindcss/oxide-linux-arm64-musl@4.2.4': '@tailwindcss/oxide-linux-arm64-musl@4.2.4':
resolution: {integrity: sha512-bBADEGAbo4ASnppIziaQJelekCxdMaxisrk+fB7Thit72IBnALp9K6ffA2G4ruj90G9XRS2VQ6q2bCKbfFV82g==} resolution: {integrity: sha512-bBADEGAbo4ASnppIziaQJelekCxdMaxisrk+fB7Thit72IBnALp9K6ffA2G4ruj90G9XRS2VQ6q2bCKbfFV82g==}
engines: {node: '>= 20'} engines: {node: '>= 20'}
cpu: [arm64] cpu: [arm64]
os: [linux] os: [linux]
libc: [musl]
'@tailwindcss/oxide-linux-x64-gnu@4.2.4': '@tailwindcss/oxide-linux-x64-gnu@4.2.4':
resolution: {integrity: sha512-7Mx25E4WTfnht0TVRTyC00j3i0M+EeFe7wguMDTlX4mRxafznw0CA8WJkFjWYH5BlgELd1kSjuU2JiPnNZbJDA==} resolution: {integrity: sha512-7Mx25E4WTfnht0TVRTyC00j3i0M+EeFe7wguMDTlX4mRxafznw0CA8WJkFjWYH5BlgELd1kSjuU2JiPnNZbJDA==}
engines: {node: '>= 20'} engines: {node: '>= 20'}
cpu: [x64] cpu: [x64]
os: [linux] os: [linux]
libc: [glibc]
'@tailwindcss/oxide-linux-x64-musl@4.2.4': '@tailwindcss/oxide-linux-x64-musl@4.2.4':
resolution: {integrity: sha512-2wwJRF7nyhOR0hhHoChc04xngV3iS+akccHTGtz965FwF0up4b2lOdo6kI1EbDaEXKgvcrFBYcYQQ/rrnWFVfA==} resolution: {integrity: sha512-2wwJRF7nyhOR0hhHoChc04xngV3iS+akccHTGtz965FwF0up4b2lOdo6kI1EbDaEXKgvcrFBYcYQQ/rrnWFVfA==}
engines: {node: '>= 20'} engines: {node: '>= 20'}
cpu: [x64] cpu: [x64]
os: [linux] os: [linux]
libc: [musl]
'@tailwindcss/oxide-wasm32-wasi@4.2.4': '@tailwindcss/oxide-wasm32-wasi@4.2.4':
resolution: {integrity: sha512-FQsqApeor8Fo6gUEklzmaa9994orJZZDBAlQpK2Mq+DslRKFJeD6AjHpBQ0kZFQohVr8o85PPh8eOy86VlSCmw==} resolution: {integrity: sha512-FQsqApeor8Fo6gUEklzmaa9994orJZZDBAlQpK2Mq+DslRKFJeD6AjHpBQ0kZFQohVr8o85PPh8eOy86VlSCmw==}
@@ -510,6 +529,12 @@ packages:
resolution: {integrity: sha512-cbdCP0PGOBq0ASG+sjnKIoYkWMKhhz+F/h9pRexUdX2Hd38+WOlBkRKlqkGOSm0YQpcFMQBJeK4WspUAkwsEdg==} resolution: {integrity: sha512-cbdCP0PGOBq0ASG+sjnKIoYkWMKhhz+F/h9pRexUdX2Hd38+WOlBkRKlqkGOSm0YQpcFMQBJeK4WspUAkwsEdg==}
engines: {node: '>=20.19.0'} engines: {node: '>=20.19.0'}
asynckit@0.4.0:
resolution: {integrity: sha512-Oei9OH4tRh0YqU3GxhX79dM/mwVgvbZJaSNaRk+bshkj0S5cfHcgYakreBjrHwatXKbz+IoIdYLxrKim2MjW0Q==}
axios@1.16.0:
resolution: {integrity: sha512-6hp5CwvTPlN2A31g5dxnwAX0orzM7pmCRDLnZSX772mv8WDqICwFjowHuPs04Mc8deIld1+ejhtaMn5vp6b+1w==}
birpc@2.9.0: birpc@2.9.0:
resolution: {integrity: sha512-KrayHS5pBi69Xi9JmvoqrIgYGDkD6mcSe/i6YKi3w5kekCLzrX4+nawcXqrj2tIp50Kw/mT/s3p+GVK0A0sKxw==} resolution: {integrity: sha512-KrayHS5pBi69Xi9JmvoqrIgYGDkD6mcSe/i6YKi3w5kekCLzrX4+nawcXqrj2tIp50Kw/mT/s3p+GVK0A0sKxw==}
@@ -520,6 +545,10 @@ packages:
resolution: {integrity: sha512-yQbXgO/OSZVD2IsiLlro+7Hf6Q18EJrKSEsdoMzKePKXct3gvD8oLcOQdIzGupr5Fj+EDe8gO/lxc1BzfMpxvA==} resolution: {integrity: sha512-yQbXgO/OSZVD2IsiLlro+7Hf6Q18EJrKSEsdoMzKePKXct3gvD8oLcOQdIzGupr5Fj+EDe8gO/lxc1BzfMpxvA==}
engines: {node: '>=8'} engines: {node: '>=8'}
call-bind-apply-helpers@1.0.2:
resolution: {integrity: sha512-Sp1ablJ0ivDkSzjcaJdxEunN5/XvksFJ2sMBFfq6x0ryhQV/2b/KwFe21cMpmHtPOSij8K99/wSfoEuTObmuMQ==}
engines: {node: '>= 0.4'}
chokidar@4.0.3: chokidar@4.0.3:
resolution: {integrity: sha512-Qgzu8kfBvo+cA4962jnP1KkS6Dop5NS6g7R5LFYJr4b8Ub94PPQXUksCw9PvXoeXPRRddRNC5C1JQUR2SMGtnA==} resolution: {integrity: sha512-Qgzu8kfBvo+cA4962jnP1KkS6Dop5NS6g7R5LFYJr4b8Ub94PPQXUksCw9PvXoeXPRRddRNC5C1JQUR2SMGtnA==}
engines: {node: '>= 14.16.0'} engines: {node: '>= 14.16.0'}
@@ -528,6 +557,10 @@ packages:
resolution: {integrity: sha512-TQMmc3w+5AxjpL8iIiwebF73dRDF4fBIieAqGn9RGCWaEVwQ6Fb2cGe31Yns0RRIzii5goJ1Y7xbMwo1TxMplw==} resolution: {integrity: sha512-TQMmc3w+5AxjpL8iIiwebF73dRDF4fBIieAqGn9RGCWaEVwQ6Fb2cGe31Yns0RRIzii5goJ1Y7xbMwo1TxMplw==}
engines: {node: '>= 20.19.0'} engines: {node: '>= 20.19.0'}
combined-stream@1.0.8:
resolution: {integrity: sha512-FQN4MRfuJeHf7cBbBMJFXhKSDq+2kAArBlmRBvcvFE5BB1HZKXtSFASDhdlz9zOYwxh8lDdnvmMOe/+5cdoEdg==}
engines: {node: '>= 0.8'}
confbox@0.1.8: confbox@0.1.8:
resolution: {integrity: sha512-RMtmw0iFkeR4YV+fUOSucriAQNb9g8zFR52MWCtl+cCZOFRNL6zeB395vPzFhEjjn4fMxXudmELnl/KF/WrK6w==} resolution: {integrity: sha512-RMtmw0iFkeR4YV+fUOSucriAQNb9g8zFR52MWCtl+cCZOFRNL6zeB395vPzFhEjjn4fMxXudmELnl/KF/WrK6w==}
@@ -560,6 +593,10 @@ packages:
supports-color: supports-color:
optional: true optional: true
delayed-stream@1.0.0:
resolution: {integrity: sha512-ZySD7Nf91aLB0RxL4KGrKHBXl7Eds1DAmEdcoVawXnLD7SDhpNgtuII2aAkg7a7QS41jxPSZ17p4VdGnMHk3MQ==}
engines: {node: '>=0.4.0'}
detect-libc@2.1.2: detect-libc@2.1.2:
resolution: {integrity: sha512-Btj2BOOO83o3WyH59e8MgXsxEQVcarkUOpEYrubB0urwnN10yQ364rsiByU11nZlqWYZm05i/of7io4mzihBtQ==} resolution: {integrity: sha512-Btj2BOOO83o3WyH59e8MgXsxEQVcarkUOpEYrubB0urwnN10yQ364rsiByU11nZlqWYZm05i/of7io4mzihBtQ==}
engines: {node: '>=8'} engines: {node: '>=8'}
@@ -577,6 +614,10 @@ packages:
domutils@3.2.2: domutils@3.2.2:
resolution: {integrity: sha512-6kZKyUajlDuqlHKVX1w7gyslj9MPIXzIFiz/rGu35uC1wMi+kMhQwGhl4lt9unC9Vb9INnY9Z3/ZA3+FhASLaw==} resolution: {integrity: sha512-6kZKyUajlDuqlHKVX1w7gyslj9MPIXzIFiz/rGu35uC1wMi+kMhQwGhl4lt9unC9Vb9INnY9Z3/ZA3+FhASLaw==}
dunder-proto@1.0.1:
resolution: {integrity: sha512-KIN/nDJBQRcXw0MLVhZE9iQHmG68qAVIBg9CqmUYjmQIhgij9U5MFvrqkUL5FbtyyzZuOeOt0zdeRe4UY7ct+A==}
engines: {node: '>= 0.4'}
enhanced-resolve@5.21.0: enhanced-resolve@5.21.0:
resolution: {integrity: sha512-otxSQPw4lkOZWkHpB3zaEQs6gWYEsmX4xQF68ElXC/TWvGxGMSGOvoNbaLXm6/cS/fSfHtsEdw90y20PCd+sCA==} resolution: {integrity: sha512-otxSQPw4lkOZWkHpB3zaEQs6gWYEsmX4xQF68ElXC/TWvGxGMSGOvoNbaLXm6/cS/fSfHtsEdw90y20PCd+sCA==}
engines: {node: '>=10.13.0'} engines: {node: '>=10.13.0'}
@@ -589,9 +630,25 @@ packages:
resolution: {integrity: sha512-TWrgLOFUQTH994YUyl1yT4uyavY5nNB5muff+RtWaqNVCAK408b5ZnnbNAUEWLTCpum9w6arT70i1XdQ4UeOPA==} resolution: {integrity: sha512-TWrgLOFUQTH994YUyl1yT4uyavY5nNB5muff+RtWaqNVCAK408b5ZnnbNAUEWLTCpum9w6arT70i1XdQ4UeOPA==}
engines: {node: '>=0.12'} engines: {node: '>=0.12'}
es-define-property@1.0.1:
resolution: {integrity: sha512-e3nRfgfUZ4rNGL232gUgX06QNyyez04KdjFrF+LTRoOXmrOgFKDg4BCdsjW8EnT69eqdYGmRpJwiPVYNrCaW3g==}
engines: {node: '>= 0.4'}
es-errors@1.3.0:
resolution: {integrity: sha512-Zf5H2Kxt2xjTvbJvP2ZWLEICxA6j+hAmMzIlypy4xcBg1vKVnx89Wy0GbS+kf5cwCVFFzdCFh2XSCFNULS6csw==}
engines: {node: '>= 0.4'}
es-module-lexer@0.10.5: es-module-lexer@0.10.5:
resolution: {integrity: sha512-+7IwY/kiGAacQfY+YBhKMvEmyAJnw5grTUgjG85Pe7vcUI/6b7pZjZG8nQ7+48YhzEAEqrEgD2dCz/JIK+AYvw==} resolution: {integrity: sha512-+7IwY/kiGAacQfY+YBhKMvEmyAJnw5grTUgjG85Pe7vcUI/6b7pZjZG8nQ7+48YhzEAEqrEgD2dCz/JIK+AYvw==}
es-object-atoms@1.1.1:
resolution: {integrity: sha512-FGgH2h8zKNim9ljj7dankFPcICIK9Cp5bm+c2gQSYePhpaG5+esrLODihIorn+Pe6FGJzWhXQotPv73jTaldXA==}
engines: {node: '>= 0.4'}
es-set-tostringtag@2.1.0:
resolution: {integrity: sha512-j6vWzfrGVfyXxge+O0x5sh6cvxAog0a/4Rdd2K36zCMV5eJ+/+tOAngRO8cODMNWbVRdVlmGZQL2YS3yR8bIUA==}
engines: {node: '>= 0.4'}
estree-walker@2.0.2: estree-walker@2.0.2:
resolution: {integrity: sha512-Rfkk/Mp/DL7JVje3u18FxFujQlTNR2q6QfMSMB7AvCBx91NGj/ba3kCfza0f6dVDbw7YlRf/nDrn7pQrCCyQ/w==} resolution: {integrity: sha512-Rfkk/Mp/DL7JVje3u18FxFujQlTNR2q6QfMSMB7AvCBx91NGj/ba3kCfza0f6dVDbw7YlRf/nDrn7pQrCCyQ/w==}
@@ -618,6 +675,19 @@ packages:
resolution: {integrity: sha512-YsGpe3WHLK8ZYi4tWDg2Jy3ebRz2rXowDxnld4bkQB00cc/1Zw9AWnC0i9ztDJitivtQvaI9KaLyKrc+hBW0yg==} resolution: {integrity: sha512-YsGpe3WHLK8ZYi4tWDg2Jy3ebRz2rXowDxnld4bkQB00cc/1Zw9AWnC0i9ztDJitivtQvaI9KaLyKrc+hBW0yg==}
engines: {node: '>=8'} engines: {node: '>=8'}
follow-redirects@1.16.0:
resolution: {integrity: sha512-y5rN/uOsadFT/JfYwhxRS5R7Qce+g3zG97+JrtFZlC9klX/W5hD7iiLzScI4nZqUS7DNUdhPgw4xI8W2LuXlUw==}
engines: {node: '>=4.0'}
peerDependencies:
debug: '*'
peerDependenciesMeta:
debug:
optional: true
form-data@4.0.5:
resolution: {integrity: sha512-8RipRLol37bNs2bhoV67fiTEvdTrbMUYcFTiy3+wuuOnUog2QBHCZWXDRijWQfAkhBj2Uf5UnVaiWwA5vdd82w==}
engines: {node: '>= 6'}
fs-extra@10.1.0: fs-extra@10.1.0:
resolution: {integrity: sha512-oRXApq54ETRj4eMiFzGnHWGy+zo5raudjuxN0b8H7s/RU2oW0Wvsx9O0ACRN/kRq9E8Vu/ReskGB5o3ji+FzHQ==} resolution: {integrity: sha512-oRXApq54ETRj4eMiFzGnHWGy+zo5raudjuxN0b8H7s/RU2oW0Wvsx9O0ACRN/kRq9E8Vu/ReskGB5o3ji+FzHQ==}
engines: {node: '>=12'} engines: {node: '>=12'}
@@ -627,13 +697,40 @@ packages:
engines: {node: ^8.16.0 || ^10.6.0 || >=11.0.0} engines: {node: ^8.16.0 || ^10.6.0 || >=11.0.0}
os: [darwin] os: [darwin]
function-bind@1.1.2:
resolution: {integrity: sha512-7XHNxH7qX9xG5mIwxkhumTox/MIRNcOgDrxWsMt2pAr23WHp6MrRlN7FBSFpCpr+oVO0F744iUgR82nJMfG2SA==}
get-intrinsic@1.3.0:
resolution: {integrity: sha512-9fSjSaos/fRIVIp+xSJlE6lfwhES7LNtKaCBIamHsjr2na1BiABJPo0mOjjz8GJDURarmCPGqaiVg5mfjb98CQ==}
engines: {node: '>= 0.4'}
get-proto@1.0.1:
resolution: {integrity: sha512-sTSfBjoXBp89JvIKIefqw7U2CCebsc74kiY6awiGogKtoSGbgjYE/G/+l9sF3MWFPNc9IcoOC4ODfKHfxFmp0g==}
engines: {node: '>= 0.4'}
glob-parent@5.1.2: glob-parent@5.1.2:
resolution: {integrity: sha512-AOIgSQCepiJYwP3ARnGx+5VnTu2HBYdzbGP45eLw1vr3zB3vZLeyed1sC9hnbcOc9/SrMyM5RPQrkGz4aS9Zow==} resolution: {integrity: sha512-AOIgSQCepiJYwP3ARnGx+5VnTu2HBYdzbGP45eLw1vr3zB3vZLeyed1sC9hnbcOc9/SrMyM5RPQrkGz4aS9Zow==}
engines: {node: '>= 6'} engines: {node: '>= 6'}
gopd@1.2.0:
resolution: {integrity: sha512-ZUKRh6/kUFoAiTAtTYPZJ3hw9wNxx+BIBOijnlG9PnrJsCcSjs1wyyD6vJpaYtgnzDrKYRSqf3OO6Rfa93xsRg==}
engines: {node: '>= 0.4'}
graceful-fs@4.2.11: graceful-fs@4.2.11:
resolution: {integrity: sha512-RbJ5/jmFcNNCcDV5o9eTnBLJ/HszWV0P73bc+Ff4nS/rJj+YaS6IGyiOL0VoBYX+l1Wrl3k63h/KrH+nhJ0XvQ==} resolution: {integrity: sha512-RbJ5/jmFcNNCcDV5o9eTnBLJ/HszWV0P73bc+Ff4nS/rJj+YaS6IGyiOL0VoBYX+l1Wrl3k63h/KrH+nhJ0XvQ==}
has-symbols@1.1.0:
resolution: {integrity: sha512-1cDNdwJ2Jaohmb3sg4OmKaMBwuC48sYni5HUw2DvsC8LjGTLK9h+eb1X6RyuOHe4hT0ULCW68iomhjUoKUqlPQ==}
engines: {node: '>= 0.4'}
has-tostringtag@1.0.2:
resolution: {integrity: sha512-NqADB8VjPFLM2V0VvHUewwwsw0ZWBaIdgo+ieHtK3hasLz4qeCRjYcqfB6AQrBggRKppKF8L52/VqdVsO47Dlw==}
engines: {node: '>= 0.4'}
hasown@2.0.3:
resolution: {integrity: sha512-ej4AhfhfL2Q2zpMmLo7U1Uv9+PyhIZpgQLGT1F9miIGmiCJIoCgSmczFdrc97mWT4kVY72KA+WnnhJ5pghSvSg==}
engines: {node: '>= 0.4'}
he@1.2.0: he@1.2.0:
resolution: {integrity: sha512-F/1DnUGPopORZi0ni+CvrCgHQ5FyEAHRLSApuYWMmrbSwoN2Mn/7k+Gl38gJnR7yyDZk6WLXwiGod1JOWNDKGw==} resolution: {integrity: sha512-F/1DnUGPopORZi0ni+CvrCgHQ5FyEAHRLSApuYWMmrbSwoN2Mn/7k+Gl38gJnR7yyDZk6WLXwiGod1JOWNDKGw==}
hasBin: true hasBin: true
@@ -712,24 +809,28 @@ packages:
engines: {node: '>= 12.0.0'} engines: {node: '>= 12.0.0'}
cpu: [arm64] cpu: [arm64]
os: [linux] os: [linux]
libc: [glibc]
lightningcss-linux-arm64-musl@1.32.0: lightningcss-linux-arm64-musl@1.32.0:
resolution: {integrity: sha512-UpQkoenr4UJEzgVIYpI80lDFvRmPVg6oqboNHfoH4CQIfNA+HOrZ7Mo7KZP02dC6LjghPQJeBsvXhJod/wnIBg==} resolution: {integrity: sha512-UpQkoenr4UJEzgVIYpI80lDFvRmPVg6oqboNHfoH4CQIfNA+HOrZ7Mo7KZP02dC6LjghPQJeBsvXhJod/wnIBg==}
engines: {node: '>= 12.0.0'} engines: {node: '>= 12.0.0'}
cpu: [arm64] cpu: [arm64]
os: [linux] os: [linux]
libc: [musl]
lightningcss-linux-x64-gnu@1.32.0: lightningcss-linux-x64-gnu@1.32.0:
resolution: {integrity: sha512-V7Qr52IhZmdKPVr+Vtw8o+WLsQJYCTd8loIfpDaMRWGUZfBOYEJeyJIkqGIDMZPwPx24pUMfwSxxI8phr/MbOA==} resolution: {integrity: sha512-V7Qr52IhZmdKPVr+Vtw8o+WLsQJYCTd8loIfpDaMRWGUZfBOYEJeyJIkqGIDMZPwPx24pUMfwSxxI8phr/MbOA==}
engines: {node: '>= 12.0.0'} engines: {node: '>= 12.0.0'}
cpu: [x64] cpu: [x64]
os: [linux] os: [linux]
libc: [glibc]
lightningcss-linux-x64-musl@1.32.0: lightningcss-linux-x64-musl@1.32.0:
resolution: {integrity: sha512-bYcLp+Vb0awsiXg/80uCRezCYHNg1/l3mt0gzHnWV9XP1W5sKa5/TCdGWaR/zBM2PeF/HbsQv/j2URNOiVuxWg==} resolution: {integrity: sha512-bYcLp+Vb0awsiXg/80uCRezCYHNg1/l3mt0gzHnWV9XP1W5sKa5/TCdGWaR/zBM2PeF/HbsQv/j2URNOiVuxWg==}
engines: {node: '>= 12.0.0'} engines: {node: '>= 12.0.0'}
cpu: [x64] cpu: [x64]
os: [linux] os: [linux]
libc: [musl]
lightningcss-win32-arm64-msvc@1.32.0: lightningcss-win32-arm64-msvc@1.32.0:
resolution: {integrity: sha512-8SbC8BR40pS6baCM8sbtYDSwEVQd4JlFTOlaD3gWGHfThTcABnNDBda6eTZeqbofalIJhFx0qKzgHJmcPTnGdw==} resolution: {integrity: sha512-8SbC8BR40pS6baCM8sbtYDSwEVQd4JlFTOlaD3gWGHfThTcABnNDBda6eTZeqbofalIJhFx0qKzgHJmcPTnGdw==}
@@ -758,6 +859,10 @@ packages:
magic-string@0.30.21: magic-string@0.30.21:
resolution: {integrity: sha512-vd2F4YUyEXKGcLHoq+TEyCjxueSeHnFxyyjNp80yg0XV4vUhnDer/lvvlqM/arB5bXQN5K2/3oinyCRyx8T2CQ==} resolution: {integrity: sha512-vd2F4YUyEXKGcLHoq+TEyCjxueSeHnFxyyjNp80yg0XV4vUhnDer/lvvlqM/arB5bXQN5K2/3oinyCRyx8T2CQ==}
math-intrinsics@1.1.0:
resolution: {integrity: sha512-/IXtbwEk5HTPyEwyKX6hGkYXxM9nbj64B+ilVJnC/R6B0pH5G4V3b0pVbL7DBj4tkhBAppbQUlf6F6Xl9LHu1g==}
engines: {node: '>= 0.4'}
merge2@1.4.1: merge2@1.4.1:
resolution: {integrity: sha512-8q7VEgMJW4J8tcfVPy8g09NcQwZdbwFEqhe/WZkoIzjn/3TGDwtOCYtXGxA3O8tPzpczCCDgv+P2P5y00ZJOOg==} resolution: {integrity: sha512-8q7VEgMJW4J8tcfVPy8g09NcQwZdbwFEqhe/WZkoIzjn/3TGDwtOCYtXGxA3O8tPzpczCCDgv+P2P5y00ZJOOg==}
engines: {node: '>= 8'} engines: {node: '>= 8'}
@@ -766,6 +871,14 @@ packages:
resolution: {integrity: sha512-PXwfBhYu0hBCPw8Dn0E+WDYb7af3dSLVWKi3HGv84IdF4TyFoC0ysxFd0Goxw7nSv4T/PzEJQxsYsEiFCKo2BA==} resolution: {integrity: sha512-PXwfBhYu0hBCPw8Dn0E+WDYb7af3dSLVWKi3HGv84IdF4TyFoC0ysxFd0Goxw7nSv4T/PzEJQxsYsEiFCKo2BA==}
engines: {node: '>=8.6'} engines: {node: '>=8.6'}
mime-db@1.52.0:
resolution: {integrity: sha512-sPU4uV7dYlvtWJxwwxHD0PuihVNiE7TyAbQ5SWxDCB9mUYvOgroQOwYQQOKPJ8CIbE+1ETVlOoK1UC2nU3gYvg==}
engines: {node: '>= 0.6'}
mime-types@2.1.35:
resolution: {integrity: sha512-ZDY+bPm5zTTF+YpCrAU9nK0UgICYPT0QtT1NZWFv4s++TNkcgVaT0g6+4R2uI4MjQjzysHB1zxuWL50hzaeXiw==}
engines: {node: '>= 0.6'}
mitt@3.0.1: mitt@3.0.1:
resolution: {integrity: sha512-vKivATfr97l2/QBCYAkXYDbrIWPM2IIKEl7YPhjCvKlG3kE2gm+uBo6nEXK3M5/Ffh/FLpKExzOQ3JJoJGFKBw==} resolution: {integrity: sha512-vKivATfr97l2/QBCYAkXYDbrIWPM2IIKEl7YPhjCvKlG3kE2gm+uBo6nEXK3M5/Ffh/FLpKExzOQ3JJoJGFKBw==}
@@ -834,6 +947,10 @@ packages:
resolution: {integrity: sha512-W62t/Se6rA0Az3DfCL0AqJwXuKwBeYg6nOaIgzP+xZ7N5BFCI7DYi1qs6ygUYT6rvfi6t9k65UMLJC+PHZpDAA==} resolution: {integrity: sha512-W62t/Se6rA0Az3DfCL0AqJwXuKwBeYg6nOaIgzP+xZ7N5BFCI7DYi1qs6ygUYT6rvfi6t9k65UMLJC+PHZpDAA==}
engines: {node: ^10 || ^12 || >=14} engines: {node: ^10 || ^12 || >=14}
proxy-from-env@2.1.0:
resolution: {integrity: sha512-cJ+oHTW1VAEa8cJslgmUZrc+sjRKgAKl3Zyse6+PV38hZe/V6Z14TbCuXcan9F9ghlz4QrFr2c92TNF82UkYHA==}
engines: {node: '>=10'}
quansync@0.2.11: quansync@0.2.11:
resolution: {integrity: sha512-AifT7QEbW9Nri4tAwR5M/uzpBuqfZf+zwaEM/QkzEjj7NBuFD2rBuy0K3dE+8wltbezDV7JMA0WfnCPYRSYbXA==} resolution: {integrity: sha512-AifT7QEbW9Nri4tAwR5M/uzpBuqfZf+zwaEM/QkzEjj7NBuFD2rBuy0K3dE+8wltbezDV7JMA0WfnCPYRSYbXA==}
@@ -1472,6 +1589,16 @@ snapshots:
'@babel/parser': 7.29.2 '@babel/parser': 7.29.2
ast-kit: 2.2.0 ast-kit: 2.2.0
asynckit@0.4.0: {}
axios@1.16.0:
dependencies:
follow-redirects: 1.16.0
form-data: 4.0.5
proxy-from-env: 2.1.0
transitivePeerDependencies:
- debug
birpc@2.9.0: {} birpc@2.9.0: {}
boolbase@1.0.0: {} boolbase@1.0.0: {}
@@ -1480,6 +1607,11 @@ snapshots:
dependencies: dependencies:
fill-range: 7.1.1 fill-range: 7.1.1
call-bind-apply-helpers@1.0.2:
dependencies:
es-errors: 1.3.0
function-bind: 1.1.2
chokidar@4.0.3: chokidar@4.0.3:
dependencies: dependencies:
readdirp: 4.1.2 readdirp: 4.1.2
@@ -1488,6 +1620,10 @@ snapshots:
dependencies: dependencies:
readdirp: 5.0.0 readdirp: 5.0.0
combined-stream@1.0.8:
dependencies:
delayed-stream: 1.0.0
confbox@0.1.8: {} confbox@0.1.8: {}
confbox@0.2.4: {} confbox@0.2.4: {}
@@ -1514,6 +1650,8 @@ snapshots:
dependencies: dependencies:
ms: 2.1.3 ms: 2.1.3
delayed-stream@1.0.0: {}
detect-libc@2.1.2: {} detect-libc@2.1.2: {}
dom-serializer@2.0.0: dom-serializer@2.0.0:
@@ -1534,6 +1672,12 @@ snapshots:
domelementtype: 2.3.0 domelementtype: 2.3.0
domhandler: 5.0.3 domhandler: 5.0.3
dunder-proto@1.0.1:
dependencies:
call-bind-apply-helpers: 1.0.2
es-errors: 1.3.0
gopd: 1.2.0
enhanced-resolve@5.21.0: enhanced-resolve@5.21.0:
dependencies: dependencies:
graceful-fs: 4.2.11 graceful-fs: 4.2.11
@@ -1543,8 +1687,23 @@ snapshots:
entities@7.0.1: {} entities@7.0.1: {}
es-define-property@1.0.1: {}
es-errors@1.3.0: {}
es-module-lexer@0.10.5: {} es-module-lexer@0.10.5: {}
es-object-atoms@1.1.1:
dependencies:
es-errors: 1.3.0
es-set-tostringtag@2.1.0:
dependencies:
es-errors: 1.3.0
get-intrinsic: 1.3.0
has-tostringtag: 1.0.2
hasown: 2.0.3
estree-walker@2.0.2: {} estree-walker@2.0.2: {}
exsolve@1.0.8: {} exsolve@1.0.8: {}
@@ -1569,6 +1728,16 @@ snapshots:
dependencies: dependencies:
to-regex-range: 5.0.1 to-regex-range: 5.0.1
follow-redirects@1.16.0: {}
form-data@4.0.5:
dependencies:
asynckit: 0.4.0
combined-stream: 1.0.8
es-set-tostringtag: 2.1.0
hasown: 2.0.3
mime-types: 2.1.35
fs-extra@10.1.0: fs-extra@10.1.0:
dependencies: dependencies:
graceful-fs: 4.2.11 graceful-fs: 4.2.11
@@ -1578,12 +1747,44 @@ snapshots:
fsevents@2.3.3: fsevents@2.3.3:
optional: true optional: true
function-bind@1.1.2: {}
get-intrinsic@1.3.0:
dependencies:
call-bind-apply-helpers: 1.0.2
es-define-property: 1.0.1
es-errors: 1.3.0
es-object-atoms: 1.1.1
function-bind: 1.1.2
get-proto: 1.0.1
gopd: 1.2.0
has-symbols: 1.1.0
hasown: 2.0.3
math-intrinsics: 1.1.0
get-proto@1.0.1:
dependencies:
dunder-proto: 1.0.1
es-object-atoms: 1.1.1
glob-parent@5.1.2: glob-parent@5.1.2:
dependencies: dependencies:
is-glob: 4.0.3 is-glob: 4.0.3
gopd@1.2.0: {}
graceful-fs@4.2.11: {} graceful-fs@4.2.11: {}
has-symbols@1.1.0: {}
has-tostringtag@1.0.2:
dependencies:
has-symbols: 1.1.0
hasown@2.0.3:
dependencies:
function-bind: 1.1.2
he@1.2.0: {} he@1.2.0: {}
hookable@5.5.3: {} hookable@5.5.3: {}
@@ -1675,6 +1876,8 @@ snapshots:
dependencies: dependencies:
'@jridgewell/sourcemap-codec': 1.5.5 '@jridgewell/sourcemap-codec': 1.5.5
math-intrinsics@1.1.0: {}
merge2@1.4.1: {} merge2@1.4.1: {}
micromatch@4.0.8: micromatch@4.0.8:
@@ -1682,6 +1885,12 @@ snapshots:
braces: 3.0.3 braces: 3.0.3
picomatch: 2.3.2 picomatch: 2.3.2
mime-db@1.52.0: {}
mime-types@2.1.35:
dependencies:
mime-db: 1.52.0
mitt@3.0.1: {} mitt@3.0.1: {}
mlly@1.8.2: mlly@1.8.2:
@@ -1748,6 +1957,8 @@ snapshots:
picocolors: 1.1.1 picocolors: 1.1.1
source-map-js: 1.2.1 source-map-js: 1.2.1
proxy-from-env@2.1.0: {}
quansync@0.2.11: {} quansync@0.2.11: {}
queue-microtask@1.2.3: {} queue-microtask@1.2.3: {}

389
s.md Normal file
View File

@@ -0,0 +1,389 @@
# dianshan 插件爬取任务开发文档(逻辑/通信/状态)
> 目的:把“点击爬取后发生了什么、会触发哪些方法、给谁通信、改变哪些状态”说清楚,方便后续二开与排查。
>
> 范围:`dianshan/` 目录内的扩展popup + background + content/overlay + 外部网页桥接)。
>
> 注意:当前项目代码里没有 `startDianshanCrawl()` / `getDianshanCrawlState()` 这类方法名;
> 正确入口分别是 `startCrawl()``dianshan/src/background/task/crawlTask.ts:14`)与 `getCrawlTaskState()``dianshan/src/background/task/taskState.ts:10`),以及对应的消息 action`START_CRAWL` / `GET_CRAWL_STATE`)。
---
## 1. 关键文件索引(按职责)
### 1.1 Popup扩展弹窗 UI
- `dianshan/src/popup/App.vue`
- UI 展示:平台选择、开始/取消/继续按钮、步骤列表、底部语言切换/版本号
- `dianshan/src/popup/hook/use-scan.ts`
- 与 background 通信(开始/取消/继续/读取状态)
- 监听 `chrome.storage.onChanged` 同步任务状态
- 计时器:根据 `startedAt` 计算已用时
- `dianshan/src/popup/hook/use-i18n.ts`
- Popup 文案 i18n中文/英文),持久化到 `chrome.storage.local`
### 1.2 Background后台调度 + 任务状态机)
- `dianshan/src/background/index.ts`
- 统一接收 popup/content/external 的 message`chrome.runtime.onMessage`
- 监听窗口/Tab 关闭(自动暂停任务)
- 监听 storage 变化并对外广播external bridge
- `dianshan/src/background/task/crawlTask.ts`
- 任务生命周期start/cancel/pause/resume/dismiss
- 步骤执行器:按 steps 顺序打开页面、等待、抓取、处理中断/重试
- 完成后收尾:发送结果 -> 清空记录 -> 关闭窗口
- `dianshan/src/background/task/taskState.ts`
- 读写 `chrome.storage.local``crawlTaskState`
- 写入时同时 `sendTabMessage(tabId,'CRAWL_STATE_UPDATE',state)` 推送给爬取窗口overlay 用)
- `dianshan/src/background/task/helper.ts`
- `openSingleTabWindow()` 创建 popup 类型新窗口并返回 `{windowId, tabId}`
- `waitForTabLoaded()` 等待 tab load complete
- `scrapeStepInContent()` 与 content script 通信执行抓取(`tabs.sendMessage`
- `dianshan/src/background/service/externalBridge.ts`
- 与外部网页(官网/业务系统)进行 external message / long-connect 通信
- 监听 storage 变化,广播 `DIANSHAN_CRAWL_STATE / DONE / ...` 等事件
### 1.3 Content Script爬取窗口页内逻辑
- `dianshan/src/content/pageRunner.ts`
- 接收 background 指令:
- `CHECK_INTERRUPT`:判断登录/验证码/404/未就绪等“需要人工处理”的中断
- `SCRAPE_STEP`:等待关键 selector 稳定后执行 DOM 抓取
- `dianshan/src/content/crawlOverlay.ts`
- 爬取窗口左下角悬浮 UI圆形计时菜单
- 点击圆形菜单展开后展示“与 popup 类似”的步骤进度/暂停提示/继续/取消
- 接收 background 推送的 `CRAWL_STATE_UPDATE` 状态
- 初始化时会拉取一次 `GET_CRAWL_STATE_FOR_TAB` 快照(只在爬取 tab 返回状态)
### 1.4 Shared跨模块协议
- `dianshan/src/shared/message.ts`
- popup/content -> background 的消息 action 类型(例如 `START_CRAWL`
- `dianshan/src/shared/tab.ts`
- background -> content爬取窗口 tab消息 action 类型(例如 `CRAWL_STATE_UPDATE`
- `dianshan/src/types/crawl.ts`
- `CrawlTaskState` / `CrawlProgressStep` / `CrawlPauseInfo` 等任务数据结构
### 1.5 关键方法定位(按真实代码)
> 下面列的都是当前项目里“确实存在”的方法/入口,后面章节会反复引用;每条都附带文件地址+行号,方便你 Ctrl+P 直达。
- popup 启动爬取:`handleScan()``dianshan/src/popup/hook/use-scan.ts:46`
- popup 取消爬取:`handleCancelCrawl()``dianshan/src/popup/hook/use-scan.ts:70`
- popup 继续爬取:`handleResumeCrawl()``dianshan/src/popup/hook/use-scan.ts:83`
- popup 同步状态:`handleStorageChanged()``dianshan/src/popup/hook/use-scan.ts:146`
- background 消息总入口:`chrome.runtime.onMessage.addListener(...)``dianshan/src/background/index.ts:22`
- background 路由:`case "START_CRAWL"` 等:`dianshan/src/background/index.ts:34`
- background 窗口/Tab 关闭监听:`windows.onRemoved`/`tabs.onRemoved``dianshan/src/background/index.ts:92`
- 任务启动:`startCrawl()``dianshan/src/background/task/crawlTask.ts:14`
- 任务执行器:`runCrawlSteps()``dianshan/src/background/task/crawlTask.ts:63`
- 完成收尾:`finalizeCompletedTask()``dianshan/src/background/task/crawlTask.ts:312`
- 取消任务:`cancelCrawl()``dianshan/src/background/task/crawlTask.ts:131`
- 窗口关闭自动暂停:`pauseCrawlOnWindowRemoved()``dianshan/src/background/task/crawlTask.ts:158`
- Tab 关闭自动暂停:`pauseCrawlOnTabRemoved()``dianshan/src/background/task/crawlTask.ts:188`
- 继续/恢复:`resumeCrawl()``dianshan/src/background/task/crawlTask.ts:219`
- 状态读写:`getCrawlTaskState()`/`setCrawlTaskState()``dianshan/src/background/task/taskState.ts:10` / `dianshan/src/background/task/taskState.ts:20`
- 新开爬取窗口:`openSingleTabWindow()``dianshan/src/background/task/helper.ts:8`
- 等待页面加载:`waitForTabLoaded()``dianshan/src/background/task/helper.ts:45`
- 让 content 抓取:`scrapeStepInContent()``dianshan/src/background/task/helper.ts:90`
- content 执行器入口:`setupPageRunner()``dianshan/src/content/pageRunner.ts:28`
- content 抓取处理:`handlePageRunnerMessage()``dianshan/src/content/pageRunner.ts:38`
- 爬取窗口悬浮 UI`mountCrawlOverlay()``dianshan/src/content/crawlOverlay.ts:36`
- 悬浮 UI 初始化拉取快照:`GET_CRAWL_STATE_FOR_TAB``dianshan/src/content/crawlOverlay.ts:67`
- 悬浮 UI 实时状态推送:`CRAWL_STATE_UPDATE``dianshan/src/content/crawlOverlay.ts:54`
---
## 2. 核心数据结构CrawlTaskState状态机
存储位置:`chrome.storage.local['crawlTaskState']`
关键字段(简化说明):
- `id`:任务唯一 ID`platformId-startedAt`
- `platformId/platformName`:平台信息
- `windowId/tabId`:当前爬取窗口与承载爬取的 taboverlay 只在这个 tab 渲染)
- `startedAt`:任务开始时间戳(用于 popup/overlay 计时)
- `status``running | paused | completed | failed | canceled`
- `pause`:当 `status='paused'` 时存在,包含
- `reason``reauth | shield | not_found | page_not_ready | window_closed`
- `message`:给用户看的暂停提示
- `currentStepIndex`:当前执行到的步骤索引
- `steps[]`:每个步骤的进度条记录
- `uniqueKey/name`
- `status``pending | running | success | failed`
- `result/message`:抓取结果或失败原因
状态同步策略:
- background 每次 `setCrawlTaskState()` / `updateCrawlTaskState()` 都会写入 storage
- popup监听 `chrome.storage.onChanged`,永远以 storage 为准渲染 UI
- overlay通过 `sendTabMessage(tabId,'CRAWL_STATE_UPDATE',state)` 实时更新(并可在初始化时请求快照)
- 外部网页:`chrome.storage.onChanged` -> `externalBridge.broadcastCrawlStorageChange()` 广播结果/状态
---
## 3. “点击爬取”后的完整时序(从 UI 到抓取)
以下用“触发方法 / 通信对象 / 状态变化”描述每一步。
### 3.1 Popup 点击 “Scan now”
1) 触发方法
- popup`use-scan.ts -> handleScan()``dianshan/src/popup/hook/use-scan.ts:46`
2) 通信
- popup -> background`sendBackgroundMessage({ action:'START_CRAWL', payload:{ platformId } })`
3) background 入口
- `background/index.ts``chrome.runtime.onMessage` 收到 `START_CRAWL``dianshan/src/background/index.ts:22` / `dianshan/src/background/index.ts:34`
- 调用:`crawlTask.startCrawl(platformId)``dianshan/src/background/task/crawlTask.ts:14`
4) 状态变化startCrawl
- `openSingleTabWindow(steps[0].url)`创建爬取窗口popup 类型)得到 `{windowId, tabId}``dianshan/src/background/task/helper.ts:8`
- 构建初始 `CrawlTaskState`
- `status='running'`
- `currentStepIndex=0`
- `steps[0].status='running'`,其余 `pending`
- `setCrawlTaskState(nextState)` 写入 storage`dianshan/src/background/task/taskState.ts:20`
- 这一步会触发:
- popup 的 storage 监听更新 UI
- background 同时 `sendTabMessage(tabId,'CRAWL_STATE_UPDATE',state)` 推送给 overlay`dianshan/src/background/task/taskState.ts:20`
- externalBridge 通过 storage.onChanged 对外广播(如果网页有连 port
5) 启动执行器
- background创建 `AbortController`,并异步执行:
- `runCrawlSteps(taskId, tabId, platform.steps, signal, startIndex=0)``dianshan/src/background/task/crawlTask.ts:63`
---
## 4. “执行一个步骤”会发生什么runCrawlSteps 的循环体)
每个 step 的处理流程如下(对每个 i 从 startIndex 到 steps.length-1
### 4.1 进入新 step先更新状态机
1) 触发方法
- background`updateCrawlTaskState(taskId, updater)`
2) 状态变化
- `currentStepIndex = i`
- `steps[i].status = 'running'`(其它步骤保持原样)
3) 通信影响
- 因为 `updateCrawlTaskState()` 内部会 `setCrawlTaskState()`
- storage 写入 -> popup UI 更新
- 同时 `sendTabMessage(tabId,'CRAWL_STATE_UPDATE',state)` -> overlay 更新
- storage.onChanged -> external bridge 广播(如果外部网页连着)
### 4.2 跳转页面并等待加载完成
1) 触发方法
- background`chrome.tabs.update(tabId, { url: step.url, active: true })`
- background`waitForTabLoaded(tabId, signal)`
2) 通信对象
- background -> Chrome tabs API无 content 参与)
3) 状态变化
- 不改变任务状态,只是准备让 content script 进入目标页面上下文
### 4.3 让 content script 执行抓取(核心通信)
1) 触发方法
- background`scrapeStepInContent(tabId, step, signal)`
2) 通信
- background -> content爬取窗口 tab`chrome.tabs.sendMessage(tabId, { action:'SCRAPE_STEP', payload:{ fields, checkSelector } })`
3) content 入口
- `content/pageRunner.ts``chrome.runtime.onMessage` 收到 `SCRAPE_STEP`
- `detectPageInterrupt()`:先判断是否需要人工处理(登录/验证码/404/未就绪)
- `waitForStableSelector(checkSelector, timeout)`:等待关键 DOM 稳定出现
- `processFields(fields, document.body)`:按配置抓取 DOM 数据
4) 返回值约定PageRunnerResponse
- `ok: true, data: DomScrapeResult`:本步骤抓取成功
- `interrupt: CrawlPauseInfo`:需要人工处理(会进入 paused
- `ok: false, error`:未就绪/异常background 会重试
### 4.4 抓取成功:写入结果并标记 step success
1) 触发方法
- background`updateCrawlTaskState(taskId, updater)`
2) 状态变化
- `steps[i].status = 'success'`
- `steps[i].result = res.data`
3) 通信影响
- 同 4.1storage + overlay 推送 + external bridge 广播
### 4.5 抓取中断:进入 paused需要用户处理
中断来源:
- content 检测到 `shield/reauth/not_found/page_not_ready`
- 或者:爬取窗口被用户关掉(见第 6 章)
1) 触发方法(以 content 中断为例)
- background`updateCrawlTaskState(taskId, s => ({ ...s, status:'paused', pause: interrupt }))``dianshan/src/background/task/crawlTask.ts:93`
2) 状态变化
- `status='paused'`
- `pause={reason,message}`
3) 执行器行为
- background 在 `runCrawlSteps` 内部“死等恢复”:
- 循环检查 `getCrawlTaskState()?.status === 'paused'`
- 直到用户点击“继续”把状态改回 `running` 才继续
4) UI 行为
- popup / overlay 都会显示暂停提示 + “Continue”
---
## 5. “点击继续”会发生什么RESUME_CRAWL
触发来源:
- popup 的 Continue
- overlay 的 Continue
### 5.1 popup/overlay 发消息
- popup`use-scan.ts -> handleResumeCrawl() -> sendBackgroundMessage({action:'RESUME_CRAWL'})``dianshan/src/popup/hook/use-scan.ts:83`
- overlay`crawlOverlay.ts -> chrome.runtime.sendMessage({action:'RESUME_CRAWL'})``dianshan/src/content/crawlOverlay.ts:392`
### 5.2 background 处理 resume
入口:
- `background/index.ts` switch case `RESUME_CRAWL``dianshan/src/background/index.ts:66`
- 调用 `crawlTask.resumeCrawl()``dianshan/src/background/task/crawlTask.ts:219`
resumeCrawl 分两类:
#### A) 登录/验证码等中断(窗口仍存在)
条件:
- `state.status === 'paused'`
- `state.pause.reason !== 'window_closed'`
- `state.windowId && state.tabId` 还在
行为:
- 仅把状态改回 `running`(清掉 pause
- 原来的 `runCrawlSteps()` 仍在“死等恢复”,会自动继续跑下一轮
#### B) 窗口被关闭导致中断(需要重开窗口)
条件:
- `state.pause.reason === 'window_closed'``windowId/tabId` 不存在
行为:
- 根据 `currentStepIndex` 找到“第一个未 success 的步骤”作为 `startIndex`
- `openSingleTabWindow(url)` 重新打开爬取窗口(`dianshan/src/background/task/helper.ts:8`
- `setCrawlTaskState()` 写入新的 `windowId/tabId/status='running'/currentStepIndex=startIndex``dianshan/src/background/task/taskState.ts:20`
- 新建 `AbortController`,重新启动执行器:
- `runCrawlSteps(taskId, newTabId, platform.steps, signal, startIndex)``dianshan/src/background/task/crawlTask.ts:63`
---
## 6. “爬取过程中窗口被关掉”会发生什么(自动暂停)
触发点:
- `background/index.ts` 监听:
- `chrome.windows.onRemoved``dianshan/src/background/index.ts:92`
- `chrome.tabs.onRemoved`(兜底)(`dianshan/src/background/index.ts:97`
处理逻辑:
- 调用 `crawlTask.pauseCrawlOnWindowRemoved(windowId)``dianshan/src/background/task/crawlTask.ts:158`)或 `pauseCrawlOnTabRemoved(tabId)``dianshan/src/background/task/crawlTask.ts:188`
行为:
1) 中止执行器
- 找到当前任务对应的 `AbortController``abort()`
- 目的:避免后台继续对不存在的 tab 进行 `tabs.update/sendMessage` 导致刷屏错误
2) 状态改为 paused
- `status='paused'`
- `pause.reason='window_closed'`
- `pause.message` 提示用户点击继续可恢复
- 清空 `windowId/tabId`(避免 UI 侧再尝试 focus 老窗口)
用户点击继续后:
- 走第 5.2 的 B 分支:重开窗口 + 从未完成步骤继续
---
## 7. “全部步骤完成”会发生什么(发送结果 + 清理 + 关窗)
触发点:
- `runCrawlSteps()` 完成 for 循环后:
1) `updateCrawlTaskState(...status='completed')`
2) 调用 `finalizeCompletedTask(taskId)`
finalizeCompletedTask 做三件事(顺序很重要):
1) 发送结果给页面
- background -> content爬取 tab`sendTabMessage(tabId,'CRAWL_COMPLETED',{ result: ... })`
- 同时 storage 完成态会触发 `externalBridge` 对外广播 `DIANSHAN_CRAWL_DONE`
2) 清空本次任务记录
- `clearCrawlTaskState()`:移除 `chrome.storage.local['crawlTaskState']`
- popup 会收到 storage 改变并自动把 UI 恢复到“未开始”状态
3) 关闭爬取窗口
- `chrome.windows.remove(windowId)`
---
## 8. Popup/Overlay 如何拿到状态(同步机制总结)
### 8.1 Popup只看 storage强一致
- 初次加载:发 `GET_CRAWL_STATE`
- 后续更新:监听 `chrome.storage.onChanged`,只要 `crawlTaskState` 变化就刷新 UI
### 8.2 Overlay推送为主拉取为辅
- 推送background 写入 state 时会 `sendTabMessage(tabId,'CRAWL_STATE_UPDATE',state)`
- overlay 监听 `chrome.runtime.onMessage`,收到 `action==='CRAWL_STATE_UPDATE'` 立刻渲染
- 拉取overlay 初始化时发 `GET_CRAWL_STATE_FOR_TAB`
- background 只在 `sender.tab.id === state.tabId` 时返回 state否则返回 null
---
## 9. 外部网页(官网/业务系统如何接收结果externalBridge
两种方式:
### 9.1 onMessageExternal短消息
- 网页发 `DIANSHAN_START_CRAWL / DIANSHAN_GET_CRAWL_STATE / ...`
- background `externalBridge.handleExternalMessage()` 返回当前状态/平台列表等
### 9.2 onConnectExternal长连接 Port
- 网页建立 Portname=`DIANSHAN_CRAWL`
- background 把当前 state 发一次 `DIANSHAN_CRAWL_STATE`
- 后续只要 storage 变化,就广播:
- `DIANSHAN_CRAWL_STATE`(进行中)
- `DIANSHAN_CRAWL_DONE`(完成且带 result
- `DIANSHAN_CRAWL_CLEARED / FAILED / CANCELED`(清理/失败/取消)
结果结构:
- `externalBridge.buildCrawlWebPayload(state)` 会给出:
- `state`:完整状态机
- `result`:仅当 `state.status==='completed'` 时非空,为按 step.uniqueKey 聚合的结果对象
---
## 10. 常见问题排查(建议)
1) overlay 不显示 / 不更新
- 先确认该 tab 是否为 `crawlTaskState.tabId`
- overlay 初始化会请求 `GET_CRAWL_STATE_FOR_TAB`,只有爬取 tab 才返回 state
- 确认 background 写入 state 时是否调用了 `setCrawlTaskState()`(它会推送 `CRAWL_STATE_UPDATE`
2) 点击取消 popup “闪一下”
- 通常是计时器回调解引用了空状态popup 侧必须在 state 清空时 stop timer
3) 窗口被关后任务还在后台跑
- 应当由 `windows.onRemoved/tabs.onRemoved` 触发 `pauseCrawlOnWindowRemoved/TabRemoved`
- 检查 background/index.ts 是否注册了监听
---
## 11. 约定:消息 action 一览(当前)
popup/content -> background`dianshan/src/shared/message.ts`
- `START_CRAWL`
- `GET_CRAWL_STATE`
- `GET_CRAWL_STATE_FOR_TAB`(仅爬取 tab 返回 state
- `CANCEL_CRAWL`
- `RESUME_CRAWL`
- `DISMISS_CRAWL`
- `CANCEL_AUTOCLOSE`(兼容旧 overlay 按钮,不建议新逻辑依赖)
background -> content`dianshan/src/shared/tab.ts`
- `CRAWL_STATE_UPDATE`overlay/pagerunner 可用)
- `CRAWL_COMPLETED`(完成时额外发送结果)

24
src/api/me.ts Normal file
View File

@@ -0,0 +1,24 @@
import request from "@/shared/request";
/**
* 获取扩展侧可用的配额/配置(扩展 token 鉴权)
*
* 中文备注:
* - API 文档GET `/api/me/scan-quota`
* - 按你的要求:返回值/参数全部用 any不定义复杂类型
*/
export async function getScanQuotaApi(): Promise<any> {
return await request.get("/me/scan-quota");
}
/**
* 扩展心跳(用于后端记录扩展活跃/跳过原因)
*
* 中文备注:
* - API 文档POST `/api/extension/heartbeat`
* - 这里不强依赖心跳成功,失败不应影响爬取主流程
*/
export async function extensionHeartbeatApi(body: any): Promise<any> {
return await request.post("/extension/heartbeat", body);
}

12
src/api/scan.ts Normal file
View File

@@ -0,0 +1,12 @@
import request from "@/shared/request";
/**
* 上传扫描数据(扩展侧直传后端)。
* 中文备注:接口定义来自 `StoreAI-New/BACKEND_API_DOCUMENTATION.md` 的 POST `/api/ingest/scan`。
*
* 注意:按你的要求:返回值、参数都用 any不定义复杂类型。
*/
export async function ingestScanApi(body: any): Promise<any> {
return await request.post("/ingest/scan", body);
}

View File

@@ -1,35 +1,37 @@
import type { PlatformFieldConfig } from '@/types'; import type {PlatformFieldConfig} from '@/types';
/** DOM 抓取后的通用结果结构。 */
export type DomScrapeResult = Record<string, unknown>; export type DomScrapeResult = Record<string, unknown>;
/** /**
* 在目标网页上下文中执行 DOM 抓取。 * 等待重试机制
*
* 注意:该方法会通过 chrome.scripting.executeScript 注入到页面中执行,
* 所以依赖的辅助方法都写在函数内部,避免注入后丢失模块作用域。
*/ */
export async function scrapeDomFields(fields: PlatformFieldConfig[]): Promise<DomScrapeResult | null> { async function waitForElement(rootDom: ParentNode, selector: string) {
if (!document.body) { let retryCount = 5;
return null; for (let i = 0; i < retryCount; i++) {
const element = rootDom.querySelector(selector);
if (element) {
return element;
}
if (i < retryCount) {
await sleep(500);
}
} }
return null;
return processFields(fields, document.body);
} }
/** 睡眠工具,给点击、翻页、异步渲染留出等待时间。 */ // 睡眠工具,给点击、翻页、异步渲染留出等待时间。
const sleep = (ms?: number) => new Promise((resolve) => window.setTimeout(resolve, ms ?? 1500)); const sleep = (ms?: number) => new Promise((resolve) => window.setTimeout(resolve, ms ?? 1500));
/** 从元素中提取实际值,默认取文本,也支持 attr、图片 src、链接 href。 */ /**
* 从元素中提取实际值,默认取文本,也支持 attr、图片 src、链接 href。
*/
function extractValue(el: Element | null, config: PlatformFieldConfig): string | null { function extractValue(el: Element | null, config: PlatformFieldConfig): string | null {
if (!el) { if (el == null) {
return null; return "未找到"
} }
if (config.attr) { if (config.attr) {
return (el.getAttribute(config.attr) || '').trim(); return (el.getAttribute(config.attr) || "").trim();
} }
const tagName = el.tagName.toUpperCase(); const tagName = el.tagName.toUpperCase();
@@ -46,30 +48,33 @@ function extractValue(el: Element | null, config: PlatformFieldConfig): string |
return (el.textContent || '').replace(/\n/g, '').trim(); return (el.textContent || '').replace(/\n/g, '').trim();
} }
/** 根据字段 condition 配置在指定 DOM 范围内自动点击目标元素。 */ /**
async function autoClick(config: PlatformFieldConfig, rootDom: ParentNode): Promise<void> { * 自动点击
* 根据字段 condition 配置在指定 DOM 范围内自动点击目标元素。
*/
async function autoClick(config: PlatformFieldConfig, rootDom: Element): Promise<void> {
if (!config.condition) { if (!config.condition) {
return; return;
} }
for (const condition of config.condition.list) {
for (const selector of config.condition.list) { let targets: HTMLElement[] = Array.from(rootDom.querySelectorAll(condition))
const targets = Array.from(rootDom.querySelectorAll<HTMLElement>(selector));
for (const target of targets) { for (const target of targets) {
target.click(); target.click();
await sleep(config.condition.time); await sleep(config?.condition.time);
} }
} }
} }
/** 递归处理字段配置,支持普通字段、嵌套 row、列表和表格。 */ /**
async function processFields(columns: PlatformFieldConfig[], rootDom: ParentNode): Promise<DomScrapeResult> { * 递归处理字段配置,支持普通字段、嵌套 row、列表和表格。
const result: DomScrapeResult = {}; */
export async function processFields(columns: PlatformFieldConfig[], rootDom: Element) {
const result = {} as any;
for (const item of columns) { for (const item of columns) {
await autoClick(item, rootDom); await autoClick(item, rootDom);
const element = rootDom.querySelector(item.className); const element = await waitForElement(rootDom, item.className)
if (!element) { if (!element) {
result[item.label] = '没找到该元素'; result[item.label] = '没找到该元素';
@@ -100,9 +105,13 @@ async function processFields(columns: PlatformFieldConfig[], rootDom: ParentNode
return result; return result;
} }
/** 按列表配置抓取所有列表项,并按分页配置继续翻页。 */ /**
async function processList(config: PlatformFieldConfig, rootDom: ParentNode): Promise<DomScrapeResult[]> { * 提取列表的数据
const allList: DomScrapeResult[] = []; * @param config 配置
* @param rootDom 父节点
*/
async function processList(config: PlatformFieldConfig, rootDom: ParentNode) {
const allList = [];
let pageCount = 0; let pageCount = 0;
while (true) { while (true) {
@@ -148,55 +157,52 @@ async function processList(config: PlatformFieldConfig, rootDom: ParentNode): Pr
return allList; return allList;
} }
/** 按表格配置抓取表格行数据,并按分页配置继续翻页。 */ /**
async function processTable(config: PlatformFieldConfig, rootDom: ParentNode): Promise<DomScrapeResult[]> { * 按表格配置抓取表格行数据,并按分页配置继续翻页。
const allTableData: DomScrapeResult[] = []; */
async function processTable(config: PlatformFieldConfig, rootDom: ParentNode) {
const allTableData: any[] = [];
let pageCount = 0; let pageCount = 0;
while (true) { while (true) {
pageCount += 1; pageCount += 1;
const partsNodes: Record<string, Element[]> = {}; const partsNodes: any = {};
for (const part of config.tableParts ?? []) { config.tableParts!.forEach(part => {
const partKey = part.name ?? part.label; partsNodes[part.name as any] = rootDom.querySelectorAll(`${part.select} tr`);
const partSelector = part.select ?? part.className; });
const rowSelector = part.rowSelector ?? `${partSelector} tr`;
partsNodes[partKey] = Array.from(rootDom.querySelectorAll(rowSelector));
}
const firstPart = config.tableParts?.[0]; // //以第一个part的行数为准进行横向扫描
const firstPartKey = firstPart ? firstPart.name ?? firstPart.label : ''; const rowCount = partsNodes[config.tableParts![0].name!]?.length || 0
const rowCount = partsNodes[firstPartKey]?.length || 0;
for (let index = 0; index < rowCount; index += 1) {
const rowData: DomScrapeResult = {};
for (const keyItem of config.keys ?? []) { for (let i = 0; i < rowCount; i++) {
const partKey = keyItem.part ?? firstPartKey; const rowData: any = {};
const targetRowNode = partsNodes[partKey]?.[index];
if (!targetRowNode) { //遍历keys根据part映射取对应的里面找
continue; for (const keyItem of config.keys!) {
} const targetRowNode = partsNodes[keyItem.part!][i];
if (keyItem.keys) { if (targetRowNode) {
rowData[keyItem.label] = await processFields(keyItem.keys, targetRowNode); //提取值
} else { if (keyItem.keys) {
rowData[keyItem.label] = extractValue(targetRowNode.querySelector(keyItem.className), keyItem); rowData[keyItem.label] = await processFields(keyItem.keys, targetRowNode)
} else {
rowData[keyItem.label] = extractValue(targetRowNode.querySelector(keyItem.className), keyItem);
}
} }
} }
allTableData.push(rowData); allTableData.push(rowData);
} }
if (!config.pagination) { if (!config.pagination) {
console.log('未配置分页信息,抓取单页后结束。'); console.log("未配置分页信息,抓取单页后结束。");
break; break;
} }
if (config.pagination.maxPage && pageCount >= config.pagination.maxPage) { if (config.pagination.maxPage && pageCount >= config.pagination.maxPage) {
console.log('已达到配置的最大页数,停止。'); console.log("已达到配置的最大页数,停止。");
break; break;
} }
@@ -221,4 +227,4 @@ async function processTable(config: PlatformFieldConfig, rootDom: ParentNode): P
} }
return allTableData; return allTableData;
} }

View File

@@ -1,33 +1,138 @@
import { handleBackgroundCommand, handleInstalled, handleStartup, handleWindowRemoved } from './service'; import {broadcastCrawlStorageChange, handleExternalConnect, handleExternalMessage} from "./service/externalBridge";
import type { BackgroundCommand } from './types'; import type {MessageAction} from "@/shared/message";
import {
cancelCrawl,
dismissCrawl,
pauseCrawlOnTabRemoved,
pauseCrawlOnWindowRemoved,
resumeCrawl,
startCrawl,
} from "./task/crawlTask";
import {getCrawlTaskState, updateCrawlTaskState} from "./task/taskState";
import {initAuthState} from "@/shared/store";
import {initAutoScanScheduler, rescheduleAutoScanAlarms} from "@/background/service/autoScanScheduler";
// 中文备注MV3 service worker 可能随时被系统回收;启动时先从 storage 恢复 authState 到内存,供 axios 同步读取。
void initAuthState();
// 中文备注:初始化定时爬取调度器(注册 alarms 监听 + 启动时重建 alarms
initAutoScanScheduler();
chrome.runtime.onInstalled.addListener(() => { chrome.runtime.onInstalled.addListener(() => {
void handleInstalled(); // 中文备注:安装/更新后尝试重建一次定时任务(如果已配对过,会从 storage 取到配置)。
void rescheduleAutoScanAlarms("onInstalled");
}); });
chrome.runtime.onStartup.addListener(() => { chrome.runtime.onStartup.addListener(() => {
void handleStartup(); // 中文备注:浏览器启动时重建定时任务,避免 service worker 回收导致 alarms 丢失。
void rescheduleAutoScanAlarms("onStartup");
}); });
chrome.runtime.onMessage.addListener((message: BackgroundCommand, _sender, sendResponse) => { /**
void handleBackgroundMessage(message, sendResponse); * 接收 popup/content 的消息
return true; */
chrome.runtime.onMessage.addListener((message, sender, sendResponse) => {
const action = message.action as MessageAction;
const payload = message.payload;
(async () => {
try {
let resultData: any = null;
switch (action) {
case "START_CRAWL":
// 中文备注:手动触发
resultData = await startCrawl(payload.platformId, "manual");
// 中文备注startCrawl 可能返回 `{ error: ... }`,这里转成 ok:false 给 popup 处理
if (resultData && typeof resultData === "object" && "error" in resultData && !("id" in resultData)) {
throw new Error(String((resultData as any).error || "start_failed"));
}
break;
case "GET_CRAWL_STATE":
resultData = await getCrawlTaskState();
break;
case "GET_CRAWL_STATE_FOR_TAB": {
// 中文备注:只允许“爬取窗口 tab”拿到状态避免其它页面误显示 overlay。
const state = await getCrawlTaskState();
const senderTabId = sender.tab?.id;
resultData = state && senderTabId && state.tabId === senderTabId ? state : null;
break;
}
case "CANCEL_CRAWL":
await cancelCrawl();
break;
case "CANCEL_AUTOCLOSE": {
// 中文备注:兼容旧悬浮面板按钮;当前版本默认完成后会清理并关闭窗口。
const state = await getCrawlTaskState();
if (state) {
await updateCrawlTaskState(state.id, (s) => ({...s, autocloseAt: null}));
resultData = await getCrawlTaskState();
} else {
resultData = null;
}
break;
}
case "RESUME_CRAWL":
resultData = await resumeCrawl();
break;
case "DISMISS_CRAWL":
await dismissCrawl();
break;
default:
throw new Error(`未知的后台指令 ${action}`);
}
sendResponse({ok: true, data: resultData});
} catch (error: any) {
console.error(`[Background] Action ${action} failed:`, error);
sendResponse({ok: false, error: error?.message || "Unknown error"});
}
})();
return true;
}); });
/**
* 监听窗口/Tab 关闭:
* - 用户手动关掉爬取窗口时,不直接取消任务,而是自动暂停,等待用户点击继续。
*/
chrome.windows.onRemoved.addListener((windowId) => { chrome.windows.onRemoved.addListener((windowId) => {
void handleWindowRemoved(windowId); void pauseCrawlOnWindowRemoved(windowId);
}); });
/** 统一包装后台消息处理,确保异步错误能回给调用方。 */ chrome.tabs.onRemoved.addListener((tabId) => {
async function handleBackgroundMessage( void pauseCrawlOnTabRemoved(tabId);
message: BackgroundCommand, });
sendResponse: (response?: unknown) => void,
) { /**
try { * 接收外部网页消息onMessageExternal
const result = await handleBackgroundCommand(message); */
sendResponse(result); chrome.runtime.onMessageExternal.addListener((message, _sender, sendResponse) => {
} catch (error: unknown) { void handleExternalMessage(message)
const messageText = error instanceof Error ? error.message : 'Unknown error'; .then(sendResponse)
sendResponse({ ok: false, error: messageText }); .catch((error: unknown) => {
} sendResponse({
} ok: false,
error: error instanceof Error ? error.message : String(error),
});
});
return true; // 中文备注:保持异步响应通道开启
});
/**
* 外部网页长连接onConnectExternal
*/
chrome.runtime.onConnectExternal.addListener(handleExternalConnect);
/**
* 监听 storage 变化并广播给 popup/overlay/外部网页
*/
chrome.storage.onChanged.addListener((changes, areaName) => {
broadcastCrawlStorageChange(changes, areaName);
// 中文备注:配对成功/退出登录会写入 auth_state这里同步重建定时爬取 alarms
if (areaName === "local" && changes["auth_state"]) {
void rescheduleAutoScanAlarms("auth_state_changed");
}
});

View File

@@ -1,410 +0,0 @@
import { getPlatformById } from '@/config/platforms';
import type { CrawlProgressStep, CrawlTaskState, PlatformConfig, PlatformStepConfig } from '@/types';
import { scrapeDomFields, type DomScrapeResult } from './domScraper';
import type { BackgroundCommand, BackgroundResponse, CrawlStateResponse } from './types';
/** chrome.storage.local 中保存当前爬取任务状态的键名。 */
const CRAWL_TASK_STORAGE_KEY = 'crawlTaskState';
/** 扩展安装完成时的初始化入口,当前仅保留日志方便调试生命周期。 */
export async function handleInstalled(): Promise<void> {
console.log('[background] installed');
}
/** 浏览器启动并加载扩展时的初始化入口,当前仅保留日志方便调试生命周期。 */
export async function handleStartup(): Promise<void> {
console.log('[background] startup');
}
/** 监听窗口关闭事件;如果关闭的是爬取窗口,就把当前任务标记为取消。 */
export async function handleWindowRemoved(windowId: number): Promise<void> {
console.log('[background] window removed', windowId);
/** 当前保存的爬取任务状态。 */
const state = await getCrawlTaskState();
if (state?.windowId === windowId && state.status === 'running') {
await setCrawlTaskState({
...state,
status: 'canceled',
steps: state.steps.map((step, index) =>
index === state.currentStepIndex ? { ...step, status: 'failed', message: '爬取窗口已关闭' } : step,
),
});
}
}
/** 根据 popup/content 发来的 action 分发到对应的后台处理函数。 */
export async function handleBackgroundCommand(
message: BackgroundCommand,
): Promise<BackgroundResponse | CrawlStateResponse> {
switch (message.action) {
case 'START_CRAWL':
return startCrawl(message.payload.platformId);
case 'GET_CRAWL_STATE':
return { ok: true, data: await getCrawlTaskState() };
case 'CANCEL_CRAWL':
return cancelCrawl();
default:
return { ok: false, error: '未知的后台指令' };
}
}
/** 创建新的爬取任务,打开目标平台窗口,并把初始时间轴状态写入 storage。 */
async function startCrawl(platformId: string): Promise<CrawlStateResponse> {
/** 根据平台 ID 找到对应的平台爬取配置。 */
const platform = getPlatformById(platformId);
if (!platform) {
return { ok: false, error: '平台配置不存在' };
}
/** 当前任务的开始时间戳,用于计算正计时。 */
const startedAt = Date.now();
/** 窗口创建前的初始任务状态,先写入 storage 让所有页面能立即感知爬取开始。 */
const nextState: CrawlTaskState = {
id: `${platform.id}-${startedAt}`,
platformId: platform.id,
platformName: platform.name,
startedAt,
status: 'running',
currentStepIndex: 0,
steps: platform.steps.map<CrawlProgressStep>((step, index) => ({
name: step.name,
uniqueKey: step.uniqueKey,
status: index === 0 ? 'running' : 'pending',
})),
};
await setCrawlTaskState(nextState);
try {
/** background 创建出来的目标平台窗口信息。 */
const windowInfo = await createCrawlWindow(platform.baseUrl);
/** 补充 windowId 后的任务状态,后续可用于取消或监听窗口关闭。 */
const stateWithWindow = { ...nextState, windowId: windowInfo.id };
await setCrawlTaskState(stateWithWindow);
void runCrawlSteps(platform, stateWithWindow);
return { ok: true, data: stateWithWindow };
} catch (error: unknown) {
/** 窗口创建失败时写入的失败状态,供 popup/content 显示错误进度。 */
const failedState: CrawlTaskState = {
...nextState,
status: 'failed',
steps: nextState.steps.map((step, index) =>
index === 0 ? { ...step, status: 'failed', message: '打开平台窗口失败' } : step,
),
};
await setCrawlTaskState(failedState);
return { ok: false, data: failedState, error: error instanceof Error ? error.message : '打开平台窗口失败' };
}
}
/** 按平台 steps 顺序执行页面跳转、DOM 等待、字段抓取和进度更新。 */
async function runCrawlSteps(platform: PlatformConfig, initialState: CrawlTaskState): Promise<void> {
if (!initialState.windowId) {
return;
}
try {
/** 新窗口中的目标标签页 ID后续所有跳转和脚本注入都依赖它。 */
const tabId = await getWindowActiveTabId(initialState.windowId);
for (let stepIndex = 0; stepIndex < platform.steps.length; stepIndex += 1) {
/** 当前正在执行的平台页面步骤配置。 */
const step = platform.steps[stepIndex];
if (!(await isTaskRunning(initialState.id))) {
return;
}
await markStepRunning(initialState.id, stepIndex);
await openStepPage(tabId, step.url);
/** 当前页面核心 DOM 是否已经出现。 */
const isReady = await waitForStepReady(tabId, step);
if (!isReady) {
await markStepFailed(initialState.id, stepIndex, '页面关键 DOM 未加载完成');
await markTaskFailed(initialState.id);
return;
}
/** 注入页面执行后的字段抓取结果。 */
const data = await scrapeStepFields(tabId, step);
console.log(`[crawl] ${platform.name} - ${step.name} 提取成功`, data);
await markStepSuccess(initialState.id, stepIndex);
}
await markTaskCompleted(initialState.id);
} catch (error: unknown) {
console.error('[crawl] 执行失败', error);
await markTaskFailed(initialState.id, error instanceof Error ? error.message : '爬取执行失败');
}
}
/** 获取指定窗口中的活动 tab ID。 */
async function getWindowActiveTabId(windowId: number): Promise<number> {
/** 指定窗口中查询到的标签页列表。 */
const tabs = await chrome.tabs.query({ windowId, active: true });
/** 当前窗口里用于承载爬取页面的活动标签页。 */
const tab = tabs[0];
if (!tab?.id) {
throw new Error('未找到爬取窗口中的标签页');
}
return tab.id;
}
/** 打开某个 steps 页面,并等待浏览器报告 tab 加载完成。 */
async function openStepPage(tabId: number, url: string): Promise<void> {
await chrome.tabs.update(tabId, { url, active: true });
await waitForTabLoaded(tabId);
}
/** 等待 tab 完成页面加载。 */
function waitForTabLoaded(tabId: number): Promise<void> {
return new Promise((resolve) => {
/** 页面加载兜底定时器,避免某些站点不触发 complete 时流程永久挂起。 */
const timeout = globalThis.setTimeout(() => {
chrome.tabs.onUpdated.removeListener(handleUpdated);
resolve();
}, 15000);
/** chrome.tabs.onUpdated 的监听器,用于捕获指定 tab 的 complete 状态。 */
function handleUpdated(updatedTabId: number, changeInfo: { status?: string }) {
if (updatedTabId === tabId && changeInfo.status === 'complete') {
globalThis.clearTimeout(timeout);
chrome.tabs.onUpdated.removeListener(handleUpdated);
resolve();
}
}
chrome.tabs.onUpdated.addListener(handleUpdated);
});
}
/** 等待步骤配置中的 checkSelector 出现;第一次超时后刷新页面再重试一次。 */
async function waitForStepReady(tabId: number, step: PlatformStepConfig): Promise<boolean> {
if (await waitForSelector(tabId, step.checkSelector, 5000)) {
return true;
}
await chrome.tabs.reload(tabId);
await waitForTabLoaded(tabId);
return waitForSelector(tabId, step.checkSelector, 5000);
}
/** 在目标页面轮询检查指定 selector 是否存在。 */
async function waitForSelector(tabId: number, selector: string, timeoutMs: number): Promise<boolean> {
/** 轮询开始时间,用于控制最大等待时长。 */
const startedAt = Date.now();
while (Date.now() - startedAt < timeoutMs) {
/** 当前页面是否已经能查询到目标元素。 */
const exists = await checkSelectorExists(tabId, selector);
if (exists) {
return true;
}
await sleep(500);
}
return false;
}
/** 注入轻量脚本检查页面里是否存在指定 selector。 */
async function checkSelectorExists(tabId: number, selector: string): Promise<boolean> {
/** chrome.scripting.executeScript 返回的注入执行结果。 */
const results = await chrome.scripting.executeScript({
target: { tabId },
func: (targetSelector: string) => Boolean(document.querySelector(targetSelector)),
args: [selector],
});
return Boolean(results[0]?.result);
}
/** 注入 domScraper 到目标页面,并根据当前 step.fields 提取页面数据。 */
async function scrapeStepFields(tabId: number, step: PlatformStepConfig): Promise<DomScrapeResult | null> {
/** 目标页面执行 DOM 抓取后返回的结果数组。 */
const results = await chrome.scripting.executeScript({
target: { tabId },
func: scrapeDomFields,
args: [step.fields],
});
return results[0]?.result ?? null;
}
/** 判断指定任务是否仍处于 running 状态。 */
async function isTaskRunning(taskId: string): Promise<boolean> {
/** 当前 storage 中的任务状态。 */
const state = await getCrawlTaskState();
return state?.id === taskId && state.status === 'running';
}
/** 将指定步骤标记为运行中,同时把其它未完成步骤保持为等待。 */
async function markStepRunning(taskId: string, stepIndex: number): Promise<void> {
await updateCrawlTaskState(taskId, (state) => ({
...state,
currentStepIndex: stepIndex,
status: 'running',
steps: state.steps.map((step, index) => ({
...step,
status: index === stepIndex ? 'running' : step.status,
message: index === stepIndex ? undefined : step.message,
})),
}));
}
/** 将指定步骤标记为成功。 */
async function markStepSuccess(taskId: string, stepIndex: number): Promise<void> {
await updateCrawlTaskState(taskId, (state) => ({
...state,
steps: state.steps.map((step, index) =>
index === stepIndex ? { ...step, status: 'success', message: undefined } : step,
),
}));
}
/** 将指定步骤标记为失败,并记录失败原因。 */
async function markStepFailed(taskId: string, stepIndex: number, message: string): Promise<void> {
await updateCrawlTaskState(taskId, (state) => ({
...state,
currentStepIndex: stepIndex,
steps: state.steps.map((step, index) =>
index === stepIndex ? { ...step, status: 'failed', message } : step,
),
}));
}
/** 将整个任务标记为完成。 */
async function markTaskCompleted(taskId: string): Promise<void> {
await updateCrawlTaskState(taskId, (state) => ({
...state,
status: 'completed',
steps: state.steps.map((step) => (step.status === 'running' ? { ...step, status: 'success' } : step)),
}));
}
/** 将整个任务标记为失败。 */
async function markTaskFailed(taskId: string, message = '爬取失败'): Promise<void> {
await updateCrawlTaskState(taskId, (state) => ({
...state,
status: 'failed',
steps: state.steps.map((step, index) =>
index === state.currentStepIndex && step.status === 'running' ? { ...step, status: 'failed', message } : step,
),
}));
}
/** 读取任务状态后执行不可变更新,避免覆盖已取消或已替换的任务。 */
async function updateCrawlTaskState(
taskId: string,
updater: (state: CrawlTaskState) => CrawlTaskState,
): Promise<void> {
/** 当前 storage 中最新的任务状态。 */
const state = await getCrawlTaskState();
if (!state || state.id !== taskId || state.status === 'canceled') {
return;
}
await setCrawlTaskState(updater(state));
}
/** 睡眠工具,用于轮询 DOM 等待。 */
function sleep(ms: number): Promise<void> {
return new Promise((resolve) => {
globalThis.setTimeout(resolve, ms);
});
}
/** 取消当前爬取任务,并尝试关闭正在爬取的平台窗口。 */
async function cancelCrawl(): Promise<CrawlStateResponse> {
/** 当前保存的爬取任务状态。 */
const state = await getCrawlTaskState();
if (!state) {
return { ok: true, data: null };
}
/** 用户取消后的任务状态,当前执行步骤会显示为失败并附带取消原因。 */
const canceledState: CrawlTaskState = {
...state,
status: 'canceled',
steps: state.steps.map((step, index) =>
index === state.currentStepIndex ? { ...step, status: 'failed', message: '用户已取消' } : step,
),
};
await setCrawlTaskState(canceledState);
if (state.windowId) {
await removeWindow(state.windowId);
}
return { ok: true, data: canceledState };
}
/** 从 chrome.storage.local 读取当前爬取任务状态。 */
async function getCrawlTaskState(): Promise<CrawlTaskState | null> {
/** chrome.storage.local 返回的原始键值对象。 */
const result = await chrome.storage.local.get(CRAWL_TASK_STORAGE_KEY);
/** 取出的任务状态候选值,需要经过结构校验后才能使用。 */
const state = result[CRAWL_TASK_STORAGE_KEY];
return isCrawlTaskState(state) ? state : null;
}
/** 将最新爬取任务状态写入 chrome.storage.local供 popup 和 content script 同步读取。 */
async function setCrawlTaskState(state: CrawlTaskState): Promise<void> {
await chrome.storage.local.set({ [CRAWL_TASK_STORAGE_KEY]: state });
}
/** 打开一个普通浏览器窗口承载目标平台页面。 */
function createCrawlWindow(url: string): Promise<chrome.windows.Window> {
return new Promise((resolve, reject) => {
chrome.windows.create(
{
url,
type: 'normal',
focused: true,
width: 1280,
height: 900,
},
(windowInfo) => {
/** Chrome 扩展 API 回调中的运行时错误。 */
const runtimeError = chrome.runtime.lastError;
if (runtimeError) {
reject(new Error(runtimeError.message));
return;
}
if (!windowInfo?.id) {
reject(new Error('窗口创建失败'));
return;
}
resolve(windowInfo);
},
);
});
}
/** 根据窗口 ID 关闭爬取窗口;关闭失败时不阻塞取消状态写入。 */
function removeWindow(windowId: number): Promise<void> {
return new Promise((resolve) => {
chrome.windows.remove(windowId, () => {
resolve();
});
});
}
/** 粗略判断 storage 中读取到的值是否像一个爬取任务状态对象。 */
function isCrawlTaskState(value: unknown): value is CrawlTaskState {
return typeof value === 'object' && value !== null && 'id' in value && 'steps' in value;
}

View File

@@ -0,0 +1,231 @@
import {platformConfigs} from "@/config/platforms";
import {getAuthState} from "@/shared/store";
import {getCrawlTaskState} from "@/background/task/taskState";
import {startCrawl} from "@/background/task/crawlTask";
import {extensionHeartbeatApi, getScanQuotaApi} from "@/api/me";
const ALARM_MORNING = "DIANSHAN_AUTO_SCAN_MORNING";
const ALARM_EVENING = "DIANSHAN_AUTO_SCAN_EVENING";
let schedulerInited = false;
/**
* 初始化定时爬取调度器(只需要调用一次)
*
* 中文备注:
* - MV3 service worker 可能被回收,模块会被重新执行;用 schedulerInited 防止重复注册监听
*/
export function initAutoScanScheduler() {
if (schedulerInited) return;
schedulerInited = true;
chrome.alarms.onAlarm.addListener((alarm) => {
void handleAlarm(alarm.name);
});
// 中文备注:启动时也做一次重建,避免用户只开扩展不打开浏览器启动事件时遗漏
void rescheduleAutoScanAlarms("init");
}
/**
* 重建定时爬取 alarms
*
* 中文备注:
* - 需求:需要“调用接口拿到配置好的定时时间”,这里会先调用 `/api/me/scan-quota` 做一次拉取(并允许后端在该接口里下发定时字段)
* - 如果接口没有下发定时字段,则回退到配对时存下来的 `authState.morningBriefHour/eveningRecapHour/timezone`
*/
export async function rescheduleAutoScanAlarms(reason: string) {
const auth = getAuthState();
if (!auth?.token) {
// 中文备注:未配对/未登录时,直接清掉所有自动爬取 alarm
await chrome.alarms.clear(ALARM_MORNING);
await chrome.alarms.clear(ALARM_EVENING);
return;
}
// 中文备注:按需求“调用接口拿配置”,同时也能借机触发 ext_outdated/unauthorized 等错误暴露
let quota: any = null;
try {
quota = await getScanQuotaApi();
} catch {
quota = null;
}
// 中文备注:配置字段优先级:接口下发 > authState 里缓存
const timezone = quota?.timezone || auth?.timezone || "Asia/Shanghai";
const morningHour = normaliseHour(quota?.morningBriefHour ?? quota?.morning_brief_hour ?? auth?.morningBriefHour);
const eveningHour = normaliseHour(quota?.eveningRecapHour ?? quota?.evening_recap_hour ?? auth?.eveningRecapHour);
// 中文备注:分别创建两个一次性 alarm触发后会在 handleAlarm 里再次续约下一次
if (morningHour === null) {
await chrome.alarms.clear(ALARM_MORNING);
} else {
const when = getNextRunAtMs(timezone, morningHour);
chrome.alarms.create(ALARM_MORNING, {when});
}
if (eveningHour === null) {
await chrome.alarms.clear(ALARM_EVENING);
} else {
const when = getNextRunAtMs(timezone, eveningHour);
chrome.alarms.create(ALARM_EVENING, {when});
}
// 中文备注:心跳可选,用于后端观测扩展侧是否成功配置定时
void extensionHeartbeatApi({
skip_reason: null,
ext_version: chrome.runtime.getManifest().version,
tick_at: new Date().toISOString(),
reason,
}).catch(() => undefined);
}
async function handleAlarm(name: string) {
if (name !== ALARM_MORNING && name !== ALARM_EVENING) return;
const auth = getAuthState();
if (!auth?.token) {
// 中文备注:没有 token 直接忽略,并清理 alarm
await chrome.alarms.clear(name);
return;
}
// 中文备注如果当前已有任务running/paused本次自动扫描跳过避免并发打开多个窗口
const state = await getCrawlTaskState();
if (state && ["running", "paused"].includes(state.status)) {
void extensionHeartbeatApi({
skip_reason: "task_in_progress",
ext_version: chrome.runtime.getManifest().version,
tick_at: new Date().toISOString(),
}).catch(() => undefined);
await rescheduleAutoScanAlarms("skip_task_in_progress");
return;
}
// 中文备注scheduled 扫描默认使用第一个平台(当前仅 Shopee
const platformId = platformConfigs[0]?.id;
if (!platformId) {
void extensionHeartbeatApi({
skip_reason: "no_platform_config",
ext_version: chrome.runtime.getManifest().version,
tick_at: new Date().toISOString(),
}).catch(() => undefined);
await rescheduleAutoScanAlarms("no_platform_config");
return;
}
// 中文备注:触发 scheduled 扫描
const started: any = await startCrawl(platformId, "scheduled");
if (started && typeof started === "object" && "error" in started && !("id" in started)) {
void extensionHeartbeatApi({
skip_reason: String((started as any).error || "start_failed"),
ext_version: chrome.runtime.getManifest().version,
tick_at: new Date().toISOString(),
}).catch(() => undefined);
await rescheduleAutoScanAlarms("start_failed");
return;
}
// 中文备注:触发后立刻续约下一次(一次性 alarm
await rescheduleAutoScanAlarms("after_alarm_fired");
}
function normaliseHour(v: any): number | null {
if (v === null || v === undefined || v === "") return null;
const n = Number(v);
if (!Number.isFinite(n)) return null;
if (n < 0 || n > 23) return null;
return Math.floor(n);
}
/**
* 计算“品牌时区”下,下一个整点触发时间(返回 UTC ms
*
* 中文备注:
* - 这里不用第三方库,靠 Intl + 时区偏移换算
* - 采用“一次性 alarm + 触发后续约”的方式,能更好适配 DST/时区变化
*/
function getNextRunAtMs(timezone: string, targetHour: number) {
const now = new Date();
const nowParts = getZonedParts(now, timezone);
const nowTotalSec = nowParts.hour * 3600 + nowParts.minute * 60 + nowParts.second;
const targetTotalSec = targetHour * 3600;
// 中文备注:如果当前时区时间已经过了目标小时,则取下一天
const addDays = nowTotalSec >= targetTotalSec ? 1 : 0;
const next = addDays === 0
? {year: nowParts.year, month: nowParts.month, day: nowParts.day}
: addDaysToYmd(nowParts.year, nowParts.month, nowParts.day, addDays);
return zonedTimeToUtcMs(timezone, next.year, next.month, next.day, targetHour, 0, 0);
}
function getZonedParts(date: Date, timeZone: string) {
const dtf = new Intl.DateTimeFormat("en-US", {
timeZone,
year: "numeric",
month: "2-digit",
day: "2-digit",
hour: "2-digit",
minute: "2-digit",
second: "2-digit",
hour12: false,
});
const parts = dtf.formatToParts(date);
const out: any = {};
for (const p of parts) {
if (p.type === "year" || p.type === "month" || p.type === "day" || p.type === "hour" || p.type === "minute" || p.type === "second") {
out[p.type] = Number(p.value);
}
}
return {
year: out.year,
month: out.month,
day: out.day,
hour: out.hour,
minute: out.minute,
second: out.second,
};
}
function addDaysToYmd(year: number, month: number, day: number, addDays: number) {
const d = new Date(Date.UTC(year, month - 1, day + addDays, 0, 0, 0));
return {year: d.getUTCFullYear(), month: d.getUTCMonth() + 1, day: d.getUTCDate()};
}
function zonedTimeToUtcMs(timeZone: string, year: number, month: number, day: number, hour: number, minute: number, second: number) {
// 中文备注:先用 UTC 作为“猜测”,再根据该时刻时区偏移修正到正确 UTC
const guessUtcMs = Date.UTC(year, month - 1, day, hour, minute, second);
let offsetMin = getTimeZoneOffsetMinutes(timeZone, new Date(guessUtcMs));
let adjusted = guessUtcMs - offsetMin * 60 * 1000;
// 中文备注DST 场景下,第一次修正后偏移可能变化,再算一次确保收敛
offsetMin = getTimeZoneOffsetMinutes(timeZone, new Date(adjusted));
adjusted = guessUtcMs - offsetMin * 60 * 1000;
return adjusted;
}
function getTimeZoneOffsetMinutes(timeZone: string, date: Date) {
const dtf = new Intl.DateTimeFormat("en-US", {
timeZone,
timeZoneName: "shortOffset",
hour: "2-digit",
minute: "2-digit",
hour12: false,
});
const parts = dtf.formatToParts(date);
const tzName = parts.find((p) => p.type === "timeZoneName")?.value || "GMT+0";
// 兼容GMT+8 / GMT+08:00 / GMT-5
const m = tzName.match(/GMT([+-])(\d{1,2})(?::?(\d{2}))?/);
if (!m) return 0;
const sign = m[1] === "-" ? -1 : 1;
const hh = Number(m[2] || 0);
const mm = Number(m[3] || 0);
return sign * (hh * 60 + mm);
}

View File

@@ -0,0 +1,288 @@
import {platformConfigs} from '@/config/platforms';
import type {CrawlTaskState} from '@/types';
import {getCrawlTaskState} from "@/background/task/taskState";
import {cancelCrawl, startCrawl} from "@/background/task/crawlTask";
import {setAuthState} from "@/shared/store";
/** 存储任务状态的 Key需与存储层保持一致 */
const CRAWL_TASK_STORAGE_KEY = 'crawlTaskState';
/** 外部通信的长连接端口名称 */
const EXTERNAL_PORT_NAME = 'DIANSHAN_CRAWL';
/** 定义外部(网页侧)可以发起的动作类型 */
type ExternalAction =
| 'DIANSHAN_PING' // 探测插件是否安装/活跃
| 'DIANSHAN_AUTH_CHECK' // 网页侧检查扩展是否已配对
| 'DIANSHAN_SSO_HANDOFF' // 网页侧回传 extension token配对结果
| 'DIANSHAN_START_CRAWL' // 从网页发起爬取
| 'DIANSHAN_GET_CRAWL_STATE' // 获取当前进度
| 'DIANSHAN_CANCEL_CRAWL' // 取消爬取
| 'STORE_AI_PING'; // 兼容性探测
/** 外部消息结构 */
interface ExternalMessage {
type?: ExternalAction;
action?: ExternalAction;
payload?: {
platformId?: string;
// 中文备注:网页侧配对后回传的登录信息(全部用 any按要求不定义复杂类型
authState?: any;
// 中文备注:兼容网页侧老参数(例如 ingestContext扩展侧目前不使用但保留以免网页传多字段报错。
[key: string]: any;
};
}
/** 返回给网页的统一响应格式 */
interface ExternalResponse<T = unknown> {
ok: boolean;
success?: boolean;
type?: string;
data?: T;
error?: string;
}
/** 网页侧接收到的复合载荷:包含任务状态和(完成后的)抓取结果 */
interface CrawlWebPayload {
state: CrawlTaskState | null;
result: Record<string, unknown> | null;
}
/** 维护当前所有已连接的网页端口(用于实时广播进度) */
const externalPorts = new Set<chrome.runtime.Port>();
/**
* 处理外部网页发送的单次指令(一问一答模式)
*/
export async function handleExternalMessage(message: ExternalMessage): Promise<ExternalResponse> {
const action = message.type ?? message.action;
switch (action) {
// 插件存活探测:返回版本号及支持的平台列表
case 'STORE_AI_PING':
case 'DIANSHAN_PING':
return {
ok: true,
success: true,
data: {
version: chrome.runtime.getManifest().version,
platforms: platformConfigs.map((platform) => ({
id: platform.id,
name: platform.name,
})),
},
};
// 网页发起爬取指令
case 'DIANSHAN_START_CRAWL':
return startCrawlForWebsite(message.payload?.platformId);
// 网页侧检查扩展是否已配对(是否已存 extension token
case 'DIANSHAN_AUTH_CHECK': {
const res = await chrome.storage.local.get("auth_state");
const auth: any = res?.["auth_state"];
return {
ok: true,
success: true,
type: "DIANSHAN_AUTH_STATE",
data: {
authed: !!auth?.token,
userEmail: auth?.userEmail ?? null,
},
};
}
// 网页侧把配对得到的 extension token 回传给扩展
case 'DIANSHAN_SSO_HANDOFF': {
const authState = message.payload?.authState;
if (!authState?.token) {
return {ok: false, error: 'missing_extension_token'};
}
await setAuthState(authState);
return {
ok: true,
success: true,
type: "DIANSHAN_SSO_OK",
data: {saved: true},
};
}
// 主动查询当前进度
case 'DIANSHAN_GET_CRAWL_STATE':
return {
ok: true,
data: buildCrawlWebPayload(await getCrawlTaskState()),
};
// 网页强制取消任务
case 'DIANSHAN_CANCEL_CRAWL':
await cancelCrawl();
return {
ok: true,
data: buildCrawlWebPayload(null),
};
default:
return {ok: false, error: 'unknown_external_action'};
}
}
/**
* 处理外部网页的长连接请求(用于实时推送进度)
*/
export function handleExternalConnect(port: chrome.runtime.Port): void {
// 只接受指定名称的端口连接
if (port.name !== EXTERNAL_PORT_NAME) {
port.disconnect();
return;
}
externalPorts.add(port);
// 连接建立时,立即推送一次当前状态
getCrawlTaskState()
.then((state) => {
postToExternalPort(port, {
ok: true,
type: 'DIANSHAN_CRAWL_STATE',
data: buildCrawlWebPayload(state),
});
})
.catch((error: unknown) => {
postToExternalPort(port, {
ok: false,
type: 'DIANSHAN_CRAWL_ERROR',
error: error instanceof Error ? error.message : String(error),
});
});
// 监听网页通过长连接发送的消息
port.onMessage.addListener((message: ExternalMessage) => {
void handleExternalMessage(message)
.then((response) => {
postToExternalPort(port, response);
})
.catch((error: unknown) => {
postToExternalPort(port, {
ok: false,
type: 'DIANSHAN_CRAWL_ERROR',
error: error instanceof Error ? error.message : String(error),
});
});
});
// 端口断开(网页关闭)时,从集合中移除
port.onDisconnect.addListener(() => {
externalPorts.delete(port);
});
}
/**
* 监听 Storage 变化并广播给所有网页端口
* 这是实现网页端进度条“丝滑跳动”的核心逻辑
*/
export function broadcastCrawlStorageChange(changes: Record<string, chrome.storage.StorageChange>, areaName: string): void {
if (areaName !== 'local') return;
const change = changes[CRAWL_TASK_STORAGE_KEY];
if (!change) return;
const nextState = isCrawlTaskState(change.newValue) ? change.newValue : null;
const oldState = isCrawlTaskState(change.oldValue) ? change.oldValue : null;
// 根据状态变化确定通知类型(如:已完成、已取消、普通更新)
const type = getBroadcastType(nextState, oldState);
broadcastToExternalPorts({
ok: true,
type,
data: buildCrawlWebPayload(nextState),
});
}
/**
* 封装网页调起的爬取逻辑:做一层错误兼容处理
*/
async function startCrawlForWebsite(platformId?: string): Promise<ExternalResponse<CrawlWebPayload>> {
// 调用核心爬取逻辑
// 中文备注网页侧触发属于手动触发manual
const response: any = await startCrawl(platformId ?? platformConfigs[0]?.id ?? '', "manual");
// 检查返回的是错误对象还是成功的任务状态
const isError = response && typeof response === 'object' && 'error' in response && !('id' in response);
const state = !isError ? (response as CrawlTaskState) : null;
return {
ok: !isError,
type: 'DIANSHAN_CRAWL_STARTED',
data: buildCrawlWebPayload(state),
error: isError ? String(response.error ?? 'start_failed') : undefined,
};
}
/**
* 构建网页端专用的数据载荷
* 如果任务已完成,则顺便把所有抓取到的结果打包带走
*/
function buildCrawlWebPayload(state: CrawlTaskState | null): CrawlWebPayload {
return {
state,
result: state?.status === 'completed' ? collectStepResults(state) : null,
};
}
/**
* 汇总任务中所有步骤的抓取结果
*/
function collectStepResults(state: CrawlTaskState): Record<string, unknown> {
return Object.fromEntries(
state.steps.map((step) => [
step.uniqueKey,
{
name: step.name,
status: step.status,
result: step.result ?? null,
message: step.message ?? null,
},
]),
);
}
/**
* 根据状态机的变化,转换成对应的外部事件名称
*/
function getBroadcastType(nextState: CrawlTaskState | null, oldState: CrawlTaskState | null): string {
if (!nextState) {
return oldState ? 'DIANSHAN_CRAWL_CLEARED' : 'DIANSHAN_CRAWL_STATE';
}
switch (nextState.status) {
case 'completed': return 'DIANSHAN_CRAWL_DONE';
case 'failed': return 'DIANSHAN_CRAWL_FAILED';
case 'canceled': return 'DIANSHAN_CRAWL_CANCELED';
default: return 'DIANSHAN_CRAWL_STATE';
}
}
/** 向所有已连接的网页广播消息 */
function broadcastToExternalPorts(message: ExternalResponse<CrawlWebPayload>): void {
for (const port of externalPorts) {
postToExternalPort(port, message);
}
}
/** 向单个端口发送消息,并处理连接失效的情况 */
function postToExternalPort(port: chrome.runtime.Port, message: ExternalResponse): void {
try {
port.postMessage(message);
} catch {
// 如果发送失败(通常因为网页已关闭),则强制清理
externalPorts.delete(port);
}
}
/** 类型守卫:判断对象是否为有效的任务状态 */
function isCrawlTaskState(value: unknown): value is CrawlTaskState {
return typeof value === 'object' && value !== null && 'id' in value && 'steps' in value;
}

View File

@@ -0,0 +1,214 @@
/**
* 把“爬取的 raw 结果”组装成后端 ingest/scan 需要的 payload。
* 中文备注:逻辑参考 `my-app/src/utils/extension/scan_payload.ts`,但这里运行在扩展侧,直接上传到后端。
*
* 按你的要求:不定义一堆类型,参数/返回统一用 any。
*/
export function buildIngestScanBody(state: any, rawResult: any, auth: any, trigger: any): any {
const brandId = auth?.brandId;
const storeId = auth?.storeId;
if (!brandId) {
throw new Error("缺少 brandId请先在网页端完成品牌配置并重新配对扩展。");
}
if (!storeId) {
throw new Error("缺少 storeId请先在网页端完成店铺配置并重新配对扩展。");
}
const scannedAt = new Date().toISOString();
const databoard = readStepResult(rawResult, "databoard");
const adscenter = readStepResult(rawResult, "adscenter");
const reviews = readStepResult(rawResult, "message");
const accountHealth = readStepResult(rawResult, "accounthealth");
const business = readObject(databoard["商业分析"]);
return {
brandId,
storeId,
scannedAt,
extractorStatus: getExtractorStatus(state),
extractorErrors: getExtractorErrors(state),
trigger: trigger || "manual",
platformAccountId: auth?.platformAccountId ?? null,
fieldMeta: {},
payload: {
store_id: storeId,
scanned_at: scannedAt,
today: buildTodayPayload(business),
recent_3h: [],
skus: [],
ads: buildAdsPayload(adscenter),
reviews: buildReviewsPayload(reviews, scannedAt),
competitors: [],
review_summary: null,
product_aggregates: null,
traffic_sources: [],
shop_health: buildShopHealthPayload(accountHealth),
},
};
}
function buildTodayPayload(business: any) {
const sales = readMetric(business["销售"]);
const visitors = readMetric(business["访客数"]);
const productClicks = readMetric(business["Product Clicks"]);
const orders = readMetric(business["订单"]);
const conversionRate = readMetric(business["Order Conversion Rate"]);
return {
orders: parseInteger(orders.value),
gmv_cents: parseMoneyCents(sales.value),
cancel_rate: 0,
return_rate: 0,
gmv_delta_yesterday_pct: parsePercent(sales.change),
gmv_net_cents: null,
conversion_rate: parsePercent(conversionRate.value),
visitors: parseNullableInteger(visitors.value),
product_clicks: parseNullableInteger(productClicks.value),
aov_cents: null,
orders_delta_yesterday_pct: parsePercent(orders.change),
conversion_rate_delta_yesterday_pct: parsePercent(conversionRate.change),
visitors_delta_yesterday_pct: parsePercent(visitors.change),
product_clicks_delta_yesterday_pct: parsePercent(productClicks.change),
aov_delta_yesterday_pct: null,
};
}
function buildAdsPayload(adscenter: any) {
const rows = readArray(adscenter["进行中广告列表"]);
return rows.map((item: any, index: number) => {
const row = readObject(item);
const info = readObject(row["广告信息"]);
const name = stringify(info["广告名称"]) || `campaign-${index + 1}`;
return {
campaign_id: name,
campaign_name: name,
type: stringify(info["广告类型"]) || "unknown",
state: "ongoing",
spend_cents: parseMoneyCents(row["花费"]),
clicks: 0,
orders: 0,
revenue_cents: parseMoneyCents(row["销售额"]),
impressions: 0,
roas: parseNumber(row["广告支出回报率"]) ?? 0,
target_roas: parseNumber(row["目标ROAS"]),
daily_budget_cents: parseMoneyCents(row["每日预算"]),
keywords: [],
};
});
}
function buildReviewsPayload(reviews: any, scannedAt: string) {
const rows = readArray(reviews["低星评论"]);
return rows.map((item: any, index: number) => {
const row = readObject(item);
const orderId = stringify(row["订单编号"]);
return {
review_id: orderId || `review-${index + 1}`,
sku_id: null,
rating: 1,
text: stringify(row["评价内容"]) || stringify(row["商品名称"]) || "",
replied: false,
created_at: scannedAt,
};
});
}
function buildShopHealthPayload(accountHealth: any) {
const healthRows = readArray(accountHealth["健康状态"]);
if (healthRows.length === 0) return null;
return {
rating_overall: null,
penalty_points: null,
metrics: {},
};
}
function getExtractorStatus(state: any): any {
if (!state || state.status === "failed" || state.status === "canceled") {
return "failed";
}
const hasFailedStep = Array.isArray(state.steps) && state.steps.some((step: any) => step.status === "failed");
const hasSuccessStep = Array.isArray(state.steps) && state.steps.some((step: any) => step.status === "success");
if (hasFailedStep && hasSuccessStep) return "partial";
if (hasFailedStep) return "failed";
return "ok";
}
function getExtractorErrors(state: any) {
if (!state) return ["missing extension crawl state"];
const list = Array.isArray(state.steps) ? state.steps : [];
return list
.filter((step: any) => step.status === "failed" || step.message)
.map((step: any) => `${step.name}: ${step.message || step.status}`)
.slice(0, 50);
}
function readStepResult(result: any, key: string) {
return readObject(readObject(result?.[key])["result"]);
}
function readMetric(value: any) {
const item = readObject(value);
return {value: item.value, change: item.change};
}
function readObject(value: any) {
return value && typeof value === "object" && !Array.isArray(value) ? value : {};
}
function readArray(value: any) {
return Array.isArray(value) ? value : [];
}
function stringify(value: any) {
return typeof value === "string" ? value.trim() : value == null ? "" : String(value).trim();
}
function parseInteger(value: any) {
return Math.max(0, Math.round(parseNumber(value) ?? 0));
}
function parseNullableInteger(value: any) {
const parsed = parseNumber(value);
return parsed == null ? null : Math.max(0, Math.round(parsed));
}
function parseMoneyCents(value: any) {
const parsed = parseNumber(value);
return Math.max(0, Math.round((parsed ?? 0) * 100));
}
function parsePercent(value: any) {
const text = stringify(value);
if (!text) return null;
const parsed = parseNumber(text);
if (parsed == null) return null;
return text.includes("%") ? parsed / 100 : parsed;
}
function parseNumber(value: any) {
const text = stringify(value)
.replace(/RM/gi, "")
.replace(/,/g, "")
.replace(/%/g, "")
.replace(/[^\d.-]/g, "");
if (!text || text === "-" || text === "." || text === "-.") return null;
const parsed = Number(text);
return Number.isFinite(parsed) ? parsed : null;
}

View File

@@ -0,0 +1,373 @@
import {getPlatformById} from "@/config/platforms";
import type {CrawlTaskState, PlatformStepConfig} from "@/types";
import {openSingleTabWindow, scrapeStepInContent, sleep, waitForTabLoaded} from "@/background/task/helper";
import {clearCrawlTaskState, getCrawlTaskState, setCrawlTaskState, updateCrawlTaskState} from "./taskState";
import {sendTabMessage} from "@/shared/tab";
import {getAuthState} from "@/shared/store";
import {ingestScanApi} from "@/api/scan";
import {buildIngestScanBody} from "@/background/service/scan_payload";
import {getScanQuotaApi} from "@/api/me";
const activeCrawlControllers = new Map<string, AbortController>();
/**
* 创建新的爬取任务:打开目标平台窗口,并把初始状态写入 storage
* @param platformId 平台 id
* @param trigger 触发来源manual/scheduled按 API 文档)
*/
export async function startCrawl(platformId: string, trigger: any = "manual"): Promise<any> {
// 中文备注:没有 extension token 就不允许开始爬取,否则最后上传会失败(也不符合产品预期)
const auth = getAuthState();
if (!auth?.token) {
return {error: "not_authed"};
}
// 中文备注:开始爬取前先向后端确认订阅/权限(扩展 token 可访问的接口GET /api/me/scan-quota
// - manual必须 allowed=true 才允许开始
// - scheduled允许忽略“手动次数上限”等限制但订阅过期subscription_required必须阻断
try {
const quota: any = await getScanQuotaApi();
const allowed = quota?.allowed === true;
const reason = String(quota?.reason || "");
if (String(trigger) === "manual" && !allowed) {
return {error: reason || quota?.message || "scan_not_allowed"};
}
if (String(trigger) === "scheduled" && reason === "subscription_required") {
return {error: "subscription_required"};
}
} catch (e: any) {
// 中文备注:如果接口失败,为了避免“订阅已过期但仍可扫描”的漏洞,这里选择阻断启动
return {error: e?.response?.data?.message || e?.message || "quota_check_failed"};
}
const platform = getPlatformById(platformId);
if (!platform) {
return {error: "platform_not_found"};
}
// 打开爬取窗口(取第一步 URL 作为入口)
const windowInfo = await openSingleTabWindow(platform.steps[0].url);
const startedAt = Date.now();
const nextState: CrawlTaskState = {
id: `${platform.id}-${startedAt}`,
windowId: windowInfo.windowId,
tabId: windowInfo.tabId,
platformId: platform.id,
platformName: platform.name,
startedAt,
status: "running",
currentStepIndex: 0,
steps: platform.steps.map((item, index) => ({
name: item.name,
uniqueKey: item.uniqueKey,
status: index === 0 ? "running" : "pending",
})),
};
// 中文备注CrawlTaskState 没有 trigger 字段(保持类型最小改动),这里用 any 写入,后续上传时会读取。
(nextState as any).trigger = trigger;
await setCrawlTaskState(nextState);
// 写入任务执行器 controller用于取消/窗口关闭暂停)
const controller = new AbortController();
activeCrawlControllers.set(nextState.id, controller);
void runCrawlSteps(nextState.id, nextState.tabId!, platform.steps, controller.signal).finally(() => {
activeCrawlControllers.delete(nextState.id);
});
return nextState;
}
/**
* 按平台 steps 顺序执行页面跳转、DOM 等待、字段抓取、进度更新
*/
async function runCrawlSteps(taskId: string, tabId: number, steps: PlatformStepConfig[], signal: AbortSignal, startIndex = 0) {
// 中文备注startIndex 用于“继续/恢复”场景,从上次没爬完的步骤开始跑。
for (let i = startIndex; i < steps.length; i += 1) {
const step = steps[i];
let shouldRetryStep = true;
// 进入新 step更新 currentStepIndex + step 状态
await updateCrawlTaskState(taskId, (s) => ({
...s,
currentStepIndex: i,
steps: s.steps.map((stepItem, idx) => ({
...stepItem,
status: idx === i ? "running" : stepItem.status,
})),
}));
while (shouldRetryStep) {
if (signal.aborted) return;
// 1) 跳转到目标 URL 并等待加载完成
await chrome.tabs.update(tabId, {url: step.url, active: true});
const loaded = await waitForTabLoaded(tabId, signal);
if (!loaded) return;
// 2) 交给 content script 抓取
const res: any = await scrapeStepInContent(tabId, step, signal);
if (signal.aborted) return;
// 3) 处理“需要人工介入”的中断(登录/验证码/页面不存在等)
if (res.interrupt) {
await updateCrawlTaskState(taskId, (s) => ({...s, status: "paused", pause: res.interrupt}));
// 死等恢复:直到 UI 把状态从 paused 改回 running
while ((await getCrawlTaskState())?.status === "paused") {
if (signal.aborted) return;
if (!(await sleep(1000, signal))) return;
}
continue;
}
// 4) 处理抓取结果
if (res.ok) {
await updateCrawlTaskState(taskId, (s) => ({
...s,
steps: s.steps.map((item, idx) => (idx === i ? {...item, status: "success", result: res.data} : item)),
}));
shouldRetryStep = false;
} else {
// 抓取失败重试
if (!(await sleep(2000, signal))) return;
}
}
}
// 全部步骤完成:标记 completed 并统一收尾(上传 -> 清理 -> 关窗)
await updateCrawlTaskState(taskId, (s) => ({...s, status: "completed"}));
await finalizeCompletedTask(taskId, signal);
}
/**
* 取消当前爬取任务:停止执行器、清空记录、关闭爬取窗口
*/
export async function cancelCrawl() {
const state = await getCrawlTaskState();
if (!state) return;
const controller = activeCrawlControllers.get(state.id);
if (controller) {
controller.abort();
activeCrawlControllers.delete(state.id);
}
await clearCrawlTaskState();
if (state.windowId) {
chrome.windows.remove(state.windowId).catch(() => undefined);
}
}
/**
* 关闭/忽略当前任务的 UI 提示:只清空状态并尝试关闭窗口(不额外走取消流程)
*/
export async function dismissCrawl(): Promise<void> {
const state = await getCrawlTaskState();
if (!state) {
await clearCrawlTaskState();
return;
}
// 中文备注如果还有执行器在跑dismiss 等同取消,避免后台继续执行。
const controller = activeCrawlControllers.get(state.id);
if (controller) {
controller.abort();
activeCrawlControllers.delete(state.id);
}
await clearCrawlTaskState();
if (state.windowId) {
chrome.windows.remove(state.windowId).catch(() => undefined);
}
}
/**
* 用户手动关闭爬取窗口:自动暂停任务,并中止当前执行器
*/
export async function pauseCrawlOnWindowRemoved(windowId: number): Promise<void> {
const state = await getCrawlTaskState();
if (!state) return;
if (state.status !== "running") return;
if (state.windowId !== windowId) return;
const controller = activeCrawlControllers.get(state.id);
if (controller) {
controller.abort();
activeCrawlControllers.delete(state.id);
}
await updateCrawlTaskState(state.id, (s) => ({
...s,
status: "paused",
pause: {
reason: "window_closed",
message: "检测到爬取窗口被关闭。点击“继续”后将重新打开窗口,并从上次进度继续爬取。",
},
// 中文备注:窗口/tab 已不存在,置空避免 UI 侧再尝试聚焦旧窗口。
windowId: undefined,
tabId: undefined,
}));
}
/**
* 爬取 tab 被关闭:同样按“窗口被关闭”暂停处理(兜底)
*/
export async function pauseCrawlOnTabRemoved(tabId: number): Promise<void> {
const state = await getCrawlTaskState();
if (!state) return;
if (state.status !== "running") return;
if (state.tabId !== tabId) return;
const controller = activeCrawlControllers.get(state.id);
if (controller) {
controller.abort();
activeCrawlControllers.delete(state.id);
}
await updateCrawlTaskState(state.id, (s) => ({
...s,
status: "paused",
pause: {
reason: "window_closed",
message: "检测到爬取页面被关闭。点击“继续”后将重新打开窗口,并从上次进度继续爬取。",
},
windowId: undefined,
tabId: undefined,
}));
}
/**
* 继续/恢复暂停任务
*/
export async function resumeCrawl(): Promise<CrawlTaskState | null> {
const state = await getCrawlTaskState();
if (!state) return null;
if (state.status !== "paused") {
return state;
}
// 1) 登录/验证码等中断:窗口还在,直接恢复 running 即可
if (state.pause?.reason !== "window_closed" && state.windowId && state.tabId) {
await updateCrawlTaskState(state.id, (s) => ({...s, status: "running", pause: undefined}));
return await getCrawlTaskState();
}
// 2) 窗口被关闭导致的暂停:需要重开窗口并从未完成 step 继续
const platform = getPlatformById(state.platformId);
if (!platform) return state;
const resumeIndex = Math.max(0, Math.min(state.currentStepIndex ?? 0, platform.steps.length - 1));
// 中文备注:从 currentStepIndex 往后找第一个未 success 的 step
let startIndex = resumeIndex;
for (let i = resumeIndex; i < state.steps.length; i += 1) {
if (state.steps[i]?.status !== "success") {
startIndex = i;
break;
}
}
const openUrl = platform.steps[startIndex]?.url ?? platform.steps[resumeIndex]?.url ?? platform.steps[0].url;
const windowInfo = await openSingleTabWindow(openUrl);
const nextState: CrawlTaskState = {
...state,
windowId: windowInfo.windowId,
tabId: windowInfo.tabId,
status: "running",
pause: undefined,
currentStepIndex: startIndex,
steps: state.steps.map((step, idx) => ({
...step,
// 中文备注:继续时把当前要执行的 step 标为 running已 success 的不动
status: idx === startIndex && step.status !== "success" ? "running" : step.status,
})),
};
await setCrawlTaskState(nextState);
const controller = new AbortController();
activeCrawlControllers.set(nextState.id, controller);
void runCrawlSteps(nextState.id, nextState.tabId!, platform.steps, controller.signal, startIndex).finally(() => {
activeCrawlControllers.delete(nextState.id);
});
return nextState;
}
/**
* 完成后的统一收尾:扩展直传后端 -> 广播完成 -> 清空任务 -> 关窗
*/
async function finalizeCompletedTask(taskId: string, signal: AbortSignal) {
const state = await getCrawlTaskState();
if (!state || state.id !== taskId) return;
if (state.status !== "completed") return;
// 中文备注:按新需求,爬取完成后由扩展直接提交到后端(不再交给网页提交)
try {
const auth = getAuthState();
const rawResult = collectStepResults(state);
const trigger = (state as any).trigger || "manual";
const body = buildIngestScanBody(state, rawResult, auth, trigger);
await ingestScanApi(body);
} catch (e: any) {
const errorText =
e?.response?.data?.message
|| e?.response?.data?.data?.apiCode
|| e?.message
|| "上传失败";
await updateCrawlTaskState(taskId, (s) => ({
...s,
status: "failed",
// 中文备注:把上传失败原因挂到当前 step 的 message 上popup/overlay 可以直接展示。
steps: s.steps.map((step, idx) => (idx === s.currentStepIndex ? {...step, message: String(errorText)} : step)),
}));
console.error("[crawl] ingest/scan failed:", e);
return;
}
// 1) 给爬取 tab 发一个事件(如页面内有监听可直接接收)
if (state.tabId) {
sendTabMessage(state.tabId, "CRAWL_COMPLETED", {
taskId: state.id,
platformId: state.platformId,
platformName: state.platformName,
startedAt: state.startedAt,
result: collectStepResults(state),
});
}
// 2) 留一点时间让 storage 广播完成态出队
await sleep(300, signal);
// 3) 清空任务记录popup/overlay 会收到 storage 变化自动重置 UI
await clearCrawlTaskState();
// 4) 关闭爬取窗口
if (state.windowId) {
chrome.windows.remove(state.windowId).catch(() => undefined);
}
}
function collectStepResults(state: CrawlTaskState): Record<string, unknown> {
return Object.fromEntries(
state.steps.map((step) => [
step.uniqueKey,
{
name: step.name,
status: step.status,
result: step.result ?? null,
message: step.message ?? null,
},
]),
);
}

View File

@@ -0,0 +1,171 @@
import {CrawlPauseInfo, PlatformStepConfig} from "@/types";
import {DomScrapeResult} from "@/background/domScraper";
/**
* 打开一个纯净的单标签窗口,并提醒用户注意
* @param url 目标网址
*/
export async function openSingleTabWindow(url: string) {
return new Promise<{ windowId: number; tabId: number }>((resolve, reject) => {
chrome.windows.create({
url,
type: 'popup',
width: 1260,
height: 900,
focused: true // 初始设为聚焦,方便窗口弹出
}, (win) => {
// 1. 检查创建是否报错
if (chrome.runtime.lastError) {
return reject(new Error(chrome.runtime.lastError.message));
}
if (win?.id && win.tabs?.[0]?.id) {
// 2. 让窗口在任务栏“闪烁”,提醒用户(比如处理登录或验证码)
// 使用 void 表示不等待结果catch 防止窗口意外关闭导致崩溃
void chrome.windows.update(win.id, { drawAttention: true }).catch(() => {});
// 3. 返回双 ID 供后续爬取逻辑使用
resolve({
windowId: win.id,
tabId: win.tabs[0].id
});
} else {
reject(new Error('窗口初始化失败'));
}
});
});
}
/**
* 等待指定的标签页加载完成
* @param tabId 标签页ID
* @param signal 中断信号
*/
export function waitForTabLoaded(tabId: number, signal: AbortSignal): Promise<boolean> {
return new Promise((resolve) => {
if (signal.aborted) {
resolve(false);
return;
}
const timeout = globalThis.setTimeout(() => {
cleanup();
resolve(true);
}, 15000);
function cleanup() {
globalThis.clearTimeout(timeout);
chrome.tabs.onUpdated.removeListener(handleUpdated);
signal.removeEventListener('abort', handleAbort);
}
function handleAbort() {
cleanup();
resolve(false);
}
function handleUpdated(updatedTabId: number, changeInfo: { status?: string }) {
if (updatedTabId === tabId && changeInfo.status === 'complete') {
cleanup();
resolve(true);
}
}
chrome.tabs.onUpdated.addListener(handleUpdated);
signal.addEventListener('abort', handleAbort, {once: true});
});
}
/**
* 让 content script 在目标页面执行抓取或探测
*/
interface PageRunnerResponse {
ok: boolean;
data?: DomScrapeResult | null;
interrupt?: CrawlPauseInfo;
error?: string;
}
export async function scrapeStepInContent(tabId: number, step: PlatformStepConfig, signal: AbortSignal): Promise<PageRunnerResponse> {
const startTime = Date.now();
const TIMEOUT = 20000; // 最多等 20 秒
while (Date.now() - startTime < TIMEOUT) {
if (signal.aborted) return {ok: false, error: 'canceled'};
try {
// 给 Content Script 发消息
const res: any = await chrome.tabs.sendMessage(tabId, {
action: 'SCRAPE_STEP',
payload: {
fields: step.fields, // 要抓哪些字段
checkSelector: step.checkSelector // 用来检测是否“撞盾”的特征选择器
}
});
// 情况 1撞盾了比如检测到了登录框、验证码
// Content Script 发现特征后会返回 interrupt 对象
if (res.interrupt) {
return res;
}
// 情况 2抓取成功
if (res.ok) {
return res;
}
// 情况 3如果 res.ok 是 false 且没有 interrupt说明页面还没渲染出来
// 继续循环重试
} catch (err: any) {
// 特殊处理:如果报错是“接收端不存在”,说明 Content Script 还没加载完
// 这属于正常情况,忽略它,等下一轮循环重试
if (!err.message.includes('receiving end does not exist')) {
console.warn('通信异常:', err.message);
}
}
// 等 500ms 再问下一次
const canContinue = await sleep(500, signal);
if (!canContinue) break;
}
return {ok: false, error: '页面响应超时,可能需要刷新'};
}
/**
* 延迟指定毫秒数,并支持随时中断
* @param ms 延迟毫秒数
* @param signal 中断信号
* @returns {Promise<boolean>} 返回 true 表示等完了,返回 false 表示被中断了
*/
export function sleep(ms: number, signal?: AbortSignal): Promise<boolean> {
return new Promise((resolve) => {
// 1. 如果信号已经中断了,直接返回 false
if (signal?.aborted) {
return resolve(false);
}
// 2. 正常设置定时器
const timer = setTimeout(() => {
cleanup();
resolve(true);
}, ms);
// 3. 定义清理逻辑
const cleanup = () => {
clearTimeout(timer);
signal?.removeEventListener('abort', onAbort);
};
// 4. 监听中断事件
const onAbort = () => {
cleanup();
resolve(false); // 一旦中断,立刻返回 false
};
// 5. 注册监听(只监听一次)
signal?.addEventListener('abort', onAbort, {once: true});
});
}

View File

@@ -0,0 +1,54 @@
import type {CrawlTaskState} from '@/types';
import {sendTabMessage} from "@/shared/tab";
const CRAWL_TASK_STORAGE_KEY = 'crawlTaskState';
/**
* 从本地存储中获取当前的爬取任务状态
* @returns {Promise<CrawlTaskState | null>} 返回任务状态对象,如果不存在或数据非法则返回 null
*/
export async function getCrawlTaskState(): Promise<CrawlTaskState | null> {
const result = await chrome.storage.local.get(CRAWL_TASK_STORAGE_KEY);
const state = result[CRAWL_TASK_STORAGE_KEY];
return (state as CrawlTaskState) || null;
}
/**
* 设置并保存爬取任务状态,并同步广播给对应的标签页
* @param {CrawlTaskState} state - 需要保存的新状态对象
*/
export async function setCrawlTaskState(state: CrawlTaskState): Promise<void> {
// 持久化到本地存储
await chrome.storage.local.set({[CRAWL_TASK_STORAGE_KEY]: state});
// 将更新后的状态发送给正在执行任务的标签页内容脚本
if (!state.tabId) return
sendTabMessage(state.tabId, 'CRAWL_STATE_UPDATE', state)
}
/**
* 从本地存储中清除当前的爬取任务状态(通常用于任务结束或彻底重置)
*/
export async function clearCrawlTaskState(): Promise<void> {
await chrome.storage.local.remove(CRAWL_TASK_STORAGE_KEY);
}
/**
* 局部更新爬取任务状态
* 只有当任务 ID 匹配且任务未被取消时,才会执行更新逻辑
* @param {string} taskId - 任务的唯一标识符
* @param {(state: CrawlTaskState) => CrawlTaskState} updater - 接收旧状态并返回新状态的回调函数
*/
export async function updateCrawlTaskState(
taskId: string,
updater: (state: CrawlTaskState) => CrawlTaskState,
): Promise<void> {
const state = await getCrawlTaskState();
// 检查任务是否存在、ID 是否一致、以及任务是否已被标记为取消
if (!state || state.id !== taskId || state.status === 'canceled') {
return;
}
// 执行更新并保存
await setCrawlTaskState(updater(state));
}

View File

@@ -1,40 +1,15 @@
import type { CrawlTaskState } from '@/types'; import type { CrawlTaskState } from '@/types';
/** 启动爬取任务的后台消息。 */
export interface StartCrawlCommand {
/** 消息动作类型:请求 background 创建爬取窗口并初始化任务状态。 */
action: 'START_CRAWL';
/** 启动爬取所需参数。 */
payload: {
/** 当前要爬取的平台 ID对应 config/platforms.ts 中的平台配置。 */
platformId: string;
};
}
/** 获取当前爬取任务状态的后台消息。 */ // background 统一响应结构。
export interface GetCrawlStateCommand {
/** 消息动作类型:请求 background 返回当前任务快照。 */
action: 'GET_CRAWL_STATE';
}
/** 取消当前爬取任务的后台消息。 */
export interface CancelCrawlCommand {
/** 消息动作类型:请求 background 标记任务取消并关闭爬取窗口。 */
action: 'CANCEL_CRAWL';
}
/** popup/content script 能发送给 background 的全部消息类型。 */
export type BackgroundCommand = StartCrawlCommand | GetCrawlStateCommand | CancelCrawlCommand;
/** background 统一响应结构。 */
export interface BackgroundResponse<T = unknown> { export interface BackgroundResponse<T = unknown> {
/** 当前请求是否处理成功。 */ // 当前请求是否处理成功。
ok: boolean; ok: boolean;
/** 成功或部分失败时返回的业务数据。 */ // 成功或部分失败时返回的业务数据。
data?: T; data?: T;
/** 请求失败时返回的错误文案。 */ // 请求失败时返回的错误文案。
error?: string; error?: string;
} }
/** 获取或变更爬取任务后返回的响应结构。 */ // 获取或变更爬取任务后返回的响应结构。
export type CrawlStateResponse = BackgroundResponse<CrawlTaskState | null>; export type CrawlStateResponse = BackgroundResponse<CrawlTaskState | null>;

12
src/config.ts Normal file
View File

@@ -0,0 +1,12 @@
/**
* 扩展侧构建时配置。
* 中文备注:
* - `APP_URL` 用于“登录按钮”打开的网站地址(也用于外部网页与扩展通信的可信来源)。
* - 默认使用本地开发地址 `http://localhost:3000`。
*/
export const APP_URL: string =
(import.meta as any).env?.VITE_APP_URL ?? "http://localhost:3000";
export const APP_ORIGIN: string = new URL(APP_URL).origin;

View File

@@ -1,7 +1,6 @@
import type {PlatformConfig} from '@/types';
import type { PlatformConfig } from '@/types'; export const platformConfigs: PlatformConfig[] = [
export const PLATFORM_CONFIGS: PlatformConfig[] = [
{ {
id: 'Shopee', id: 'Shopee',
name: 'Shopee 后台', name: 'Shopee 后台',
@@ -10,7 +9,7 @@ export const PLATFORM_CONFIGS: PlatformConfig[] = [
name: '数据看板', name: '数据看板',
uniqueKey: 'databoard', uniqueKey: 'databoard',
url: 'https://seller.shopee.com.my/', url: 'https://seller.shopee.com.my/',
checkSelector: '.rate-manager-content', checkSelector: '.page-container',
fields: [ fields: [
{ {
label: "出货统计", label: "出货统计",
@@ -36,46 +35,46 @@ export const PLATFORM_CONFIGS: PlatformConfig[] = [
}, },
{ {
label: "商业分析", label: "商业分析",
className: ".data-dashboard-async-data-wrapper .custom-row", className: ".data-dashboard .metrics",
keys: [ keys: [
{ {
label: "销售", label: "销售",
className: ".custom-col-5:nth-child(1) ", className: ".metric:nth-child(1) ",
keys: [ keys: [
{ label: "value", className: ".dashboard-item-value" }, {label: "value", className: ".metric-value"},
{ label: "change", className: ".dashboard-item-rate-number" } {label: "change", className: ".metric-rate"}
] ]
}, },
{ {
label: "访客数", label: "访客数",
className: ".custom-col-5:nth-child(2) ", className: ".metric:nth-child(2) ",
keys: [ keys: [
{ label: "value", className: ".dashboard-item-value" }, {label: "value", className: ".metric-value"},
{ label: "change", className: ".dashboard-item-rate-number" } {label: "change", className: ".metric-rate"}
] ]
}, },
{ {
label: "Product Clicks", label: "Product Clicks",
className: ".custom-col-5:nth-child(3)", className: ".metric:nth-child(3)",
keys: [ keys: [
{ label: "value", className: ".dashboard-item-value" }, {label: "value", className: ".metric-value"},
{ label: "change", className: ".dashboard-item-rate-number" } {label: "change", className: ".metric-rate"}
] ]
}, },
{ {
label: "订单", label: "订单",
className: ".custom-col-5:nth-child(4)", className: ".metric:nth-child(4)",
keys: [ keys: [
{ label: "value", className: ".dashboard-item-value" }, {label: "value", className: ".metric-value"},
{ label: "change", className: ".dashboard-item-rate-number" } {label: "change", className: ".metric-rate"}
] ]
}, },
{ {
label: "Order Conversion Rate", label: "Order Conversion Rate",
className: ".custom-col-5:nth-child(5)", className: ".metric:nth-child(5)",
keys: [ keys: [
{ label: "value", className: ".dashboard-item-value" }, {label: "value", className: ".metric-value"},
{ label: "change", className: ".dashboard-item-rate-number" } {label: "change", className: ".metric-rate"}
] ]
}, },
] ]
@@ -88,42 +87,224 @@ export const PLATFORM_CONFIGS: PlatformConfig[] = [
label: "广告余额", label: "广告余额",
className: ".ads-data-cell:nth-of-type(1) ", className: ".ads-data-cell:nth-of-type(1) ",
keys: [ keys: [
{ label: "value", className: ".ads-data-report-number" }, {label: "value", className: ".ads-data-report-number"},
] ]
}, },
{ {
label: "销售额", label: "销售额",
className: ".ads-data-cell:nth-child(3) ", className: ".ads-data-cell:nth-child(3) ",
keys: [ keys: [
{ label: "value", className: ".ads-data-report-number" }, {label: "value", className: ".ads-data-report-number"},
{ label: "change", className: ".ratio " } {label: "change", className: ".ratio "}
] ]
}, },
{ {
label: "花费", label: "花费",
className: ".ads-data-cell:nth-child(4)", className: ".ads-data-cell:nth-child(4)",
keys: [ keys: [
{ label: "value", className: ".ads-data-report-number" }, {label: "value", className: ".ads-data-report-number"},
{ label: "change", className: ".ratio " } {label: "change", className: ".ratio "}
] ]
}, },
{ {
label: "广告支出回报率", label: "广告支出回报率",
className: ".ads-data-cell:nth-child(5)", className: ".ads-data-cell:nth-child(5)",
keys: [ keys: [
{ label: "value", className: ".ads-data-report-number" }, {label: "value", className: ".ads-data-report-number"},
{ label: "change", className: ".ratio " } {label: "change", className: ".ratio "}
] ]
}, },
] ]
}, },
], ],
}, },
{
name: "广告中心",
uniqueKey: "adscenter",
url: "https://seller.shopee.com.my/portal/marketing/pas/index",
checkSelector: '.page-container',
fields: [
{
label: "我的账户",
className: ".my-account-wrap",
keys: [
{
label: "广告余额",
className: ".credit-expense-label-wrapper:nth-child(1) .ellipsis-content"
},
{
label: "今日广告花费",
className: ".credit-expense-label-wrapper:nth-child(2) .ellipsis-content"
},
]
},
{
label: "进行中广告列表",
className: ".eds-table__body-container",
type: 2,
condition: {
list: [".eds-radio-group label:nth-child(3)"],
time: 400
},
tableParts: [
{name: "fixed", select: ".eds-table__fix-body"},
{name: "main", select: ".eds-table__main-body"}
],
keys: [
{
label: "广告信息",
className: ".info-containter",
part: "fixed",
keys: [
{
label: "广告名称",
className: ".campaign-name-container"
},
{
label: "广告类型",
className: ".gmv-max-noti"
},
{
label: "结束时间",
className: ".time-edit-wrapper"
}
]
},
{
label: "每日预算",
part: "main",
className: "td:nth-child(1)"
},
{
label: "目标ROAS",
part: "main",
className: "td:nth-child(2)"
},
{
label: "花费",
part: "main",
className: "td:nth-child(4)"
},
{
label: "销售额",
part: "main",
className: "td:nth-child(5)"
},
{
label: "广告支出回报率",
part: "main",
className: "td:nth-child(6)"
}
],
pagination: {
nextBtn: ".eds-pager__button-next", // 下一页按钮
disabledClass: ".eds-button--disabled", // 按钮禁用时的class用来判断结束
maxPage: 1, // 最大爬取页数
delay: 2000 // 翻页后的等待加载时间
},
}
]
},
{
name: "评论管理",
uniqueKey: "message",
url: "https://seller.shopee.com.my/portal/settings/shop/rating?pageNumber=1&fromPageNumber=1&cursor=0&pageSize=20&replied=TO_REPLY&ratingStar=2&ratingStar=1",
checkSelector: '.page-container',
fields: [
{
label: "低星评论",
className: ".border-solid.rounded",
type: 1,
keys: [
{
label: "用户",
className: ".flex.items-center.justify-start .ml-2"
},
{
label: "订单编号",
className: ".underline.px-1"
},
{
label: "商品名称",
className: ".min-w-0.font-medium.break-all"
},
{
label: "规格",
className: ".min-w-0.font-medium.break-all + div"
},
{
label: "评价内容",
className: ".min-w-0.overflow-hidden",
condition: {
list: [
"span.cursor-pointer"
],
time: 200,
},
},
],
pagination: {
nextBtn: ".eds-react-pagination-pager__button-next",
maxPage: 2, // 最大爬取页数
delay: 2000 // 翻页后的等待加载时间
},
},
]
},
{
name: "账户健康状态2",
uniqueKey: "accounthealth",
url: "https://seller.shopee.com.my/portal/accounthealth/home",
checkSelector: '.page-container',
fields: [
{
label: "健康状态",
className: ".metric-content",
type: 1,
keys: [
{
label: "模块名",
className: ".metric-type"
},
{
label: "值",
className: ".metric-item",
type: 1,
keys: [
{
label: "指标",
className: "p.metric-text"
},
{
label: "值",
className: ".metric-my"
},
{
label: "目标",
className: ".metric-target"
},
{
label: "使用类型",
className: ".metric-applied-to"
},
]
},
],
},
]
}
], ],
}, },
] ]
/** 根据平台 ID 返回对应的平台抓取配置。 */ /**
* 根据平台 ID 返回对应的平台抓取配置。
*/
export function getPlatformById(platformId: string) { export function getPlatformById(platformId: string) {
return PLATFORM_CONFIGS.find((item) => item.id === platformId) ?? null; return platformConfigs.find((item) => item.id === platformId) ?? null;
} }

View File

@@ -1,20 +1,20 @@
<script setup lang="ts"> <script setup lang="ts">
import {computed, onMounted, onUnmounted, ref} from 'vue'; import {computed, onMounted, onUnmounted, ref} from 'vue';
import type {CrawlTaskState} from '@/types'; import type {CrawlTaskState} from '@/types';
/** 当前后台保存的爬取任务快照,用于决定是否展示右下角浮窗。 */ // 当前后台保存的爬取任务快照,用于决定是否展示右下角浮窗。
const crawlState = ref<CrawlTaskState | null>(null); const crawlState = ref<CrawlTaskState | null>(null);
/** 当前爬取任务已经运行的秒数,页面上会格式化为 mm:ss。 */ // 当前爬取任务已经运行的秒数,页面上会格式化为 mm:ss。
const elapsedSeconds = ref(0); const elapsedSeconds = ref(0);
/** 控制右下角时间轴面板是否展开。 */ // 控制右下角时间轴面板是否展开。
const isPanelOpen = ref(false); const isPanelOpen = ref(false);
/** 轮询后台爬取状态和刷新计时器的定时器 ID。 */ // 轮询后台爬取状态和刷新计时器的定时器 ID。
let timer: number | undefined; let timer: number | undefined;
/** 只有任务处于运行中时,才在网页右下角展示计时按钮。 */ // 只有任务处于运行中时,才在网页右下角展示计时按钮。
const isVisible = computed(() => crawlState.value?.status === 'running'); const isVisible = computed(() => crawlState.value ? ['running', 'paused'].includes(crawlState.value.status) : false);
/** 内容脚本挂载后立即同步一次状态,并开始每秒刷新计时和任务进度。 */ // 内容脚本挂载后立即同步一次状态,并开始每秒刷新计时和任务进度。
onMounted(() => { onMounted(() => {
void refreshCrawlState(); void refreshCrawlState();
timer = window.setInterval(() => { timer = window.setInterval(() => {
@@ -23,16 +23,18 @@ onMounted(() => {
}, 1000); }, 1000);
}); });
/** 内容脚本卸载时清理定时器,避免页面残留轮询。 */ // 内容脚本卸载时清理定时器,避免页面残留轮询。
onUnmounted(() => { onUnmounted(() => {
if (timer) { if (timer) {
window.clearInterval(timer); window.clearInterval(timer);
} }
}); });
/** 从 background 获取最新爬取任务状态,并在任务结束时自动收起面板。 */ /**
* 从 background 获取最新爬取任务状态,并在任务结束时自动收起面板。
*/
async function refreshCrawlState() { async function refreshCrawlState() {
/** background 返回的当前爬取任务状态响应。 */ // background 返回的当前爬取任务状态响应。
const response = await sendBackgroundMessage<CrawlTaskState | null>({action: 'GET_CRAWL_STATE'}); const response = await sendBackgroundMessage<CrawlTaskState | null>({action: 'GET_CRAWL_STATE'});
if (response.ok) { if (response.ok) {
@@ -45,7 +47,9 @@ async function refreshCrawlState() {
} }
} }
/** 根据任务开始时间实时计算已经运行的秒数。 */ /**
* 根据任务开始时间实时计算已经运行的秒数。
*/
function updateElapsedSeconds() { function updateElapsedSeconds() {
if (!crawlState.value) { if (!crawlState.value) {
elapsedSeconds.value = 0; elapsedSeconds.value = 0;
@@ -55,18 +59,22 @@ function updateElapsedSeconds() {
elapsedSeconds.value = Math.max(0, Math.floor((Date.now() - crawlState.value.startedAt) / 1000)); elapsedSeconds.value = Math.max(0, Math.floor((Date.now() - crawlState.value.startedAt) / 1000));
} }
/** 将秒数格式化为 mm:ss展示在圆形计时按钮和面板标题里。 */ /**
* 将秒数格式化为 mm:ss展示在圆形计时按钮和面板标题里。
*/
function formatElapsed(totalSeconds: number): string { function formatElapsed(totalSeconds: number): string {
/** 运行时长中的分钟部分。 */ // 运行时长中的分钟部分。
const minutes = Math.floor(totalSeconds / 60).toString().padStart(2, '0'); const minutes = Math.floor(totalSeconds / 60).toString().padStart(2, '0');
/** 运行时长中的秒数部分。 */ // 运行时长中的秒数部分。
const seconds = (totalSeconds % 60).toString().padStart(2, '0'); const seconds = (totalSeconds % 60).toString().padStart(2, '0');
return `${minutes}:${seconds}`; return `${minutes}:${seconds}`;
} }
/** 将步骤状态枚举转换成中文展示文案。 */ /**
* 将步骤状态枚举转换成中文展示文案。
*/
function getStepText(status: string): string { function getStepText(status: string): string {
/** 步骤状态到展示文案的映射表。 */ // 步骤状态到展示文案的映射表。
const textMap: Record<string, string> = { const textMap: Record<string, string> = {
pending: '等待中', pending: '等待中',
running: '爬取中', running: '爬取中',
@@ -77,7 +85,17 @@ function getStepText(status: string): string {
return textMap[status] ?? status; return textMap[status] ?? status;
} }
/** 发送消息到 background非扩展环境下返回空成功响应方便本地页面不报错。 */ /**
* 请求 background 继续暂停中的爬取任务。
*/
async function handleResumeCrawl() {
await sendBackgroundMessage({ action: 'RESUME_CRAWL' });
await refreshCrawlState();
}
/**
* 发送消息到 background非扩展环境下返回空成功响应方便本地页面不报错。
*/
function sendBackgroundMessage<T>(message: unknown): Promise<{ ok: boolean; data?: T; error?: string }> { function sendBackgroundMessage<T>(message: unknown): Promise<{ ok: boolean; data?: T; error?: string }> {
if (typeof chrome === 'undefined' || !chrome.runtime?.sendMessage) { if (typeof chrome === 'undefined' || !chrome.runtime?.sendMessage) {
return Promise.resolve({ok: true, data: null as T}); return Promise.resolve({ok: true, data: null as T});
@@ -104,15 +122,20 @@ function sendBackgroundMessage<T>(message: unknown): Promise<{ ok: boolean; data
<ol class="dianshan-crawl-timeline"> <ol class="dianshan-crawl-timeline">
<li v-for="(step, index) in crawlState.steps" :key="step.uniqueKey" :class="`is-${step.status}`"> <li v-for="(step, index) in crawlState.steps" :key="step.uniqueKey" :class="`is-${step.status}`">
<span class="dianshan-crawl-dot"></span> <span class="dianshan-crawl-dot"></span>
<div class="dianshan-crawl-step"> <div class="dianshan-crawl-step">
<strong>{{ index + 1 }}. {{ step.name }}</strong> <strong>{{ index + 1 }}. {{ step.name }}</strong>
<em>{{ getStepText(step.status) }}</em> <em>{{ getStepText(step.status) }}</em>
<small v-if="step.message">{{ step.message }}</small> <small v-if="step.message">{{ step.message }}</small>
</div> </div>
</li> </li>
</ol> </ol>
</section>
</div> <div v-if="crawlState.status === 'paused' && crawlState.pause" class="dianshan-crawl-pause">
<p>{{ crawlState.pause.message }}</p>
<button type="button" @click="handleResumeCrawl">我已处理继续</button>
</div>
</section>
</div>
</template> </template>
<style scoped> <style scoped>
@@ -213,6 +236,35 @@ function sendBackgroundMessage<T>(message: unknown): Promise<{ ok: boolean; data
color: #b91c1c; color: #b91c1c;
} }
.dianshan-crawl-pause {
display: grid;
gap: 8px;
margin-top: 12px;
padding: 10px;
border: 1px solid #f59e0b;
border-radius: 8px;
background: #fffbeb;
}
.dianshan-crawl-pause p {
margin: 0;
color: #92400e;
font-size: 12px;
line-height: 1.5;
}
.dianshan-crawl-pause button {
width: 100%;
border: 0;
border-radius: 6px;
padding: 8px 10px;
color: #ffffff;
background: #059669;
cursor: pointer;
font-size: 12px;
font-weight: 700;
}
.is-running .dianshan-crawl-dot, .is-running .dianshan-crawl-dot,
.is-success .dianshan-crawl-dot { .is-success .dianshan-crawl-dot {
background: #10b981; background: #10b981;

615
src/content/crawlOverlay.ts Normal file
View File

@@ -0,0 +1,615 @@
import type { CrawlTaskState, CrawlStepStatus, CrawlTaskStatus } from '@/types';
const OVERLAY_HOST_ID = 'dianshan-crawl-overlay-host';
const MASK_HOST_ID = 'dianshan-crawl-mask-host';
type OverlayPhase = 'running' | 'paused' | 'done' | 'failed' | 'cancelled';
interface OverlayRefs {
host: HTMLDivElement;
root: ShadowRoot;
container: HTMLDivElement;
expanded: HTMLDivElement;
capsule: HTMLButtonElement;
stepsList: HTMLDivElement;
pauseBanner: HTMLDivElement;
pauseMessage: HTMLDivElement;
resumeBtn: HTMLButtonElement;
cancelBtn: HTMLButtonElement;
minimiseBtn: HTMLButtonElement;
titleEl: HTMLDivElement;
subtitleEl: HTMLDivElement;
currentDetail: HTMLDivElement;
autocloseBanner: HTMLDivElement;
autocloseText: HTMLDivElement;
stayOpenBtn: HTMLButtonElement;
}
let refs: OverlayRefs | null = null;
let maskHost: HTMLDivElement | null = null;
let currentState: CrawlTaskState | null = null;
let clockTimer: number | null = null;
let autoCollapseTimer: number | null = null;
let hasExpandedOnceForThisTask = false;
let hasKeptOpen = false;
export function mountCrawlOverlay(): void {
if (document.getElementById(OVERLAY_HOST_ID)) {
return;
}
if (!document.body) {
document.addEventListener('DOMContentLoaded', mountCrawlOverlay, { once: true });
return;
}
refs = buildDom();
refs.host.style.display = 'none';
maskHost = buildMaskHost();
// 中文备注:接收 background 通过 sendTabMessage(tabId, 'CRAWL_STATE_UPDATE', state) 推送的任务状态。
// 旧逻辑使用 type='crawl_state_update',这里改为适配当前的 action/payload 协议。
chrome.runtime.onMessage.addListener((raw) => {
const msg = raw as { action?: string; payload?: unknown } | undefined;
if (msg?.action === 'CRAWL_STATE_UPDATE') {
applyState(isCrawlTaskState(msg.payload) ? (msg.payload as CrawlTaskState) : null);
}
return false;
});
// Initial state snapshot (tab-gated in background; other tabs get null).
void refreshForThisTab();
}
async function refreshForThisTab(): Promise<void> {
if (!chrome.runtime?.sendMessage) return;
try {
const response = await chrome.runtime.sendMessage({ action: 'GET_CRAWL_STATE_FOR_TAB' });
const next = (response && typeof response === 'object' ? (response as { data?: unknown }).data : null) ?? null;
applyState(isCrawlTaskState(next) ? (next as CrawlTaskState) : null);
} catch {
// ignore
}
}
function isCrawlTaskState(value: unknown): value is CrawlTaskState {
return typeof value === 'object' && value !== null && 'id' in value && 'steps' in value;
}
function phaseFor(state: CrawlTaskState): OverlayPhase {
if (state.status === 'paused') return 'paused';
if (state.status === 'completed') return 'done';
if (state.status === 'failed') return 'failed';
if (state.status === 'canceled') return 'cancelled';
return 'running';
}
function isActive(status: CrawlTaskStatus): boolean {
return status === 'running' || status === 'paused' || status === 'completed' || status === 'failed' || status === 'canceled';
}
function isTerminal(status: CrawlTaskStatus): boolean {
return status === 'completed' || status === 'failed' || status === 'canceled';
}
function applyState(next: CrawlTaskState | null): void {
if (!refs) return;
const prevId = currentState?.id;
currentState = next;
if (!next || !isActive(next.status)) {
refs.host.style.display = 'none';
setMaskActive(false);
clearTimers();
return;
}
if (prevId !== next.id) {
hasExpandedOnceForThisTask = false;
hasKeptOpen = false;
}
refs.host.style.display = 'block';
// Mask blocks page interaction while running. Paused lifts mask so user can solve captcha/login.
setMaskActive(next.status === 'running');
// 中文备注:默认折叠为左下角“圆形计时菜单”,用户点击后再展开查看进度。
if (!hasExpandedOnceForThisTask && next.status === 'running') {
hasExpandedOnceForThisTask = true;
setCollapsed(true);
if (autoCollapseTimer) {
window.clearTimeout(autoCollapseTimer);
autoCollapseTimer = null;
}
}
if (next.status === 'paused') {
setCollapsed(false);
}
// Keep the elapsed subtitle ticking without waiting for storage writes.
if (!clockTimer) {
clockTimer = window.setInterval(() => {
if (currentState) render(currentState);
}, 1000);
}
render(next);
}
function clearTimers(): void {
if (clockTimer) {
window.clearInterval(clockTimer);
clockTimer = null;
}
if (autoCollapseTimer) {
window.clearTimeout(autoCollapseTimer);
autoCollapseTimer = null;
}
}
function setCollapsed(collapsed: boolean): void {
if (!refs) return;
refs.container.dataset.collapsed = collapsed ? '1' : '0';
}
function setMaskActive(active: boolean): void {
if (!maskHost) return;
maskHost.style.display = active ? 'block' : 'none';
}
function render(state: CrawlTaskState): void {
if (!refs) return;
const phase = phaseFor(state);
refs.container.dataset.phase = phase;
const elapsedSeconds = Math.max(0, Math.floor((Date.now() - state.startedAt) / 1000));
const time = formatElapsed(elapsedSeconds);
refs.titleEl.textContent = state.platformName || '爬取任务';
const okCount = state.steps.filter((s) => s.status === 'success').length;
const totalCount = state.steps.length;
let subtitle = '';
if (phase === 'paused') subtitle = `已暂停 · ${time}`;
else if (phase === 'done') subtitle = `已完成 · ${okCount}/${totalCount}`;
else if (phase === 'failed') subtitle = `失败 · ${okCount}/${totalCount}`;
else if (phase === 'cancelled') subtitle = `已取消 · ${okCount}/${totalCount}`;
else subtitle = `运行中 · ${okCount}/${totalCount} · ${time}`;
refs.subtitleEl.textContent = subtitle;
refs.currentDetail.textContent = buildCurrentDetail(state);
// Steps
refs.stepsList.innerHTML = '';
for (const step of state.steps) {
const row = document.createElement('div');
row.className = 'step';
row.dataset.status = mapStepStatus(step.status);
const dot = document.createElement('div');
dot.className = 'dot';
dot.textContent = dotFor(step.status);
const label = document.createElement('div');
label.className = 'step-label';
label.textContent = step.name;
row.appendChild(dot);
row.appendChild(label);
refs.stepsList.appendChild(row);
}
// Pause banner
if (state.status === 'paused' && state.pause) {
refs.pauseBanner.style.display = 'block';
refs.pauseMessage.textContent = state.pause.message;
} else {
refs.pauseBanner.style.display = 'none';
}
// Cancel button only while running (mask active).
refs.cancelBtn.style.display = state.status === 'running' ? 'inline-flex' : 'none';
// Autoclose banner on terminal, when autocloseAt exists and user didn't keep open.
if (isTerminal(state.status)) {
refs.autocloseBanner.style.display = 'block';
const autocloseAt = state.autocloseAt;
if (autocloseAt && !hasKeptOpen) {
const remaining = Math.max(0, Math.ceil((autocloseAt - Date.now()) / 1000));
refs.autocloseText.textContent = `窗口将在 ${remaining}s 后自动关闭`;
refs.stayOpenBtn.style.display = 'inline-flex';
} else {
refs.autocloseText.textContent = '窗口将保持打开';
refs.stayOpenBtn.style.display = 'none';
}
} else {
refs.autocloseBanner.style.display = 'none';
}
// Capsule text
// 中文备注圆形菜单上只显示计时mm:ss
const capsuleTime = refs.capsule.querySelector('.capsule-time') as HTMLSpanElement | null;
if (capsuleTime) {
capsuleTime.textContent = time;
}
const capsuleText = refs.capsule.querySelector('.capsule-text') as HTMLSpanElement | null;
if (capsuleText) {
capsuleText.textContent =
phase === 'paused'
? '已暂停'
: isTerminal(state.status)
? phase === 'done'
? '已完成'
: phase === 'failed'
? '失败'
: '已取消'
: `爬取中 ${time}`;
}
}
function buildCurrentDetail(state: CrawlTaskState): string {
const step = state.steps[state.currentStepIndex];
if (!step) return '';
if (state.status === 'paused' && state.pause) return state.pause.message;
if (state.status === 'failed') return step.message ?? '爬取失败';
if (state.status === 'canceled') return step.message ?? '已取消';
if (state.status === 'completed') return '爬取完成';
return step.message ?? `正在处理:${step.name}`;
}
function formatElapsed(totalSeconds: number): string {
const minutes = Math.floor(totalSeconds / 60).toString().padStart(2, '0');
const seconds = (totalSeconds % 60).toString().padStart(2, '0');
return `${minutes}:${seconds}`;
}
function mapStepStatus(status: CrawlStepStatus): 'active' | 'ok' | 'partial' | 'failed' | 'pending' {
if (status === 'running') return 'active';
if (status === 'success') return 'ok';
if (status === 'failed') return 'failed';
return 'pending';
}
function dotFor(status: CrawlStepStatus): string {
if (status === 'success') return '✓';
if (status === 'failed') return '×';
if (status === 'running') return '•';
return '·';
}
function buildDom(): OverlayRefs {
const host = document.createElement('div');
host.id = OVERLAY_HOST_ID;
host.style.all = 'initial';
host.style.position = 'fixed';
// 中文备注:爬取窗口左下角放圆形菜单(计时 + 入口)
host.style.left = '24px';
host.style.bottom = '24px';
host.style.zIndex = '2147483647';
const root = host.attachShadow({ mode: 'closed' });
const container = document.createElement('div');
container.className = 'container';
container.dataset.collapsed = '0';
container.dataset.phase = 'running';
container.innerHTML = `
${styleTag()}
<div class="expanded">
<div class="header">
<div class="radar-wrap">
<div class="radar"><div class="sweep"></div><div class="ping"></div></div>
</div>
<div class="titles">
<div class="title"></div>
<div class="subtitle"></div>
</div>
<button class="minimise-btn" type="button" aria-label="最小化"></button>
</div>
<div class="body">
<div class="steps-list"></div>
<div class="current-detail"></div>
<div class="pause-banner" style="display:none">
<div class="pause-row">
<div class="pause-icon">!</div>
<div style="flex:1 1 auto">
<div class="pause-message"></div>
<div class="pause-auto-hint">处理完成后可点下方按钮继续</div>
<button class="resume-btn" type="button">我已完成 · 继续爬取</button>
</div>
</div>
</div>
</div>
<div class="autoclose-banner" style="display:none">
<div class="autoclose-text"></div>
<button class="stay-open-btn" type="button">保持打开</button>
</div>
<div class="footer">
<div class="coffee-hint">扫描期间你可以继续做别的事 · 完成后回到扩展查看结果</div>
<button class="cancel-btn" type="button">取消爬取</button>
</div>
</div>
<button class="capsule" type="button" aria-label="展开面板">
<div class="radar-mini"><div class="sweep-mini"></div></div>
<span class="capsule-time">爬取中</span>
</button>
`;
root.appendChild(container);
document.body.appendChild(host);
const titleEl = container.querySelector('.title') as HTMLDivElement;
const subtitleEl = container.querySelector('.subtitle') as HTMLDivElement;
const stepsList = container.querySelector('.steps-list') as HTMLDivElement;
const pauseBanner = container.querySelector('.pause-banner') as HTMLDivElement;
const pauseMessage = container.querySelector('.pause-message') as HTMLDivElement;
const resumeBtn = container.querySelector('.resume-btn') as HTMLButtonElement;
const cancelBtn = container.querySelector('.cancel-btn') as HTMLButtonElement;
const minimiseBtn = container.querySelector('.minimise-btn') as HTMLButtonElement;
const capsule = container.querySelector('.capsule') as HTMLButtonElement;
const currentDetail = container.querySelector('.current-detail') as HTMLDivElement;
const autocloseBanner = container.querySelector('.autoclose-banner') as HTMLDivElement;
const autocloseText = container.querySelector('.autoclose-text') as HTMLDivElement;
const stayOpenBtn = container.querySelector('.stay-open-btn') as HTMLButtonElement;
minimiseBtn.addEventListener('click', () => setCollapsed(true));
capsule.addEventListener('click', () => setCollapsed(false));
// Cancel with 2-step confirm
let cancelConfirmTimer: number | null = null;
cancelBtn.addEventListener('click', () => {
if (cancelBtn.dataset.confirming === '1') {
void chrome.runtime.sendMessage({ action: 'CANCEL_CRAWL' });
cancelBtn.dataset.confirming = '0';
cancelBtn.textContent = '取消爬取';
if (cancelConfirmTimer) window.clearTimeout(cancelConfirmTimer);
cancelConfirmTimer = null;
return;
}
cancelBtn.dataset.confirming = '1';
cancelBtn.textContent = '确认取消?';
cancelConfirmTimer = window.setTimeout(() => {
cancelBtn.dataset.confirming = '0';
cancelBtn.textContent = '取消爬取';
cancelConfirmTimer = null;
}, 3000);
});
resumeBtn.addEventListener('click', () => {
void chrome.runtime.sendMessage({ action: 'RESUME_CRAWL' });
});
stayOpenBtn.addEventListener('click', () => {
hasKeptOpen = true;
void chrome.runtime.sendMessage({ action: 'CANCEL_AUTOCLOSE' });
if (currentState) render(currentState);
});
return {
host,
root,
container,
expanded: container.querySelector('.expanded') as HTMLDivElement,
capsule,
stepsList,
pauseBanner,
pauseMessage,
resumeBtn,
cancelBtn,
minimiseBtn,
titleEl,
subtitleEl,
currentDetail,
autocloseBanner,
autocloseText,
stayOpenBtn,
};
}
function buildMaskHost(): HTMLDivElement {
const existing = document.getElementById(MASK_HOST_ID) as HTMLDivElement | null;
if (existing) return existing;
const m = document.createElement('div');
m.id = MASK_HOST_ID;
m.style.all = 'initial';
m.style.position = 'fixed';
m.style.top = '0';
m.style.left = '0';
m.style.right = '0';
m.style.bottom = '0';
m.style.zIndex = '2147483646';
m.style.background = 'rgba(15, 23, 42, 0.04)';
m.style.cursor = 'progress';
m.style.pointerEvents = 'auto';
m.style.display = 'none';
m.setAttribute('aria-hidden', 'true');
const tip = document.createElement('div');
tip.id = 'dianshan-mask-tip';
tip.style.all = 'initial';
tip.style.position = 'fixed';
tip.style.maxWidth = '280px';
tip.style.padding = '8px 12px';
tip.style.background = '#0f172a';
tip.style.color = '#f8fafc';
tip.style.fontFamily = "-apple-system,'Segoe UI','PingFang SC','Microsoft YaHei',sans-serif";
tip.style.fontSize = '12px';
tip.style.lineHeight = '1.45';
tip.style.borderRadius = '6px';
tip.style.boxShadow = '0 4px 14px rgba(0,0,0,0.18), 0 1px 3px rgba(0,0,0,0.12)';
tip.style.pointerEvents = 'none';
tip.style.zIndex = '1';
tip.style.opacity = '0';
tip.style.transition = 'opacity 120ms ease';
tip.textContent = '正在爬取,请稍候…(暂停时可操作页面)';
m.appendChild(tip);
const swallow = (e: Event) => {
e.stopPropagation();
e.preventDefault();
};
for (const evt of ['click', 'dblclick', 'mousedown', 'mouseup', 'pointerdown', 'pointerup', 'wheel', 'touchstart', 'touchend', 'contextmenu']) {
m.addEventListener(evt, swallow, { capture: true, passive: false });
}
m.addEventListener(
'mousemove',
(e) => {
tip.style.opacity = '1';
const margin = 8;
const offsetX = 16;
const offsetY = 22;
const w = window.innerWidth;
const h = window.innerHeight;
const rect = tip.getBoundingClientRect();
let left = (e as MouseEvent).clientX + offsetX;
let top = (e as MouseEvent).clientY + offsetY;
if (left + rect.width > w - margin) left = (e as MouseEvent).clientX - rect.width - offsetX;
if (top + rect.height > h - margin) top = (e as MouseEvent).clientY - rect.height - offsetY;
tip.style.left = Math.max(margin, left) + 'px';
tip.style.top = Math.max(margin, top) + 'px';
},
{ passive: true },
);
m.addEventListener('mouseleave', () => {
tip.style.opacity = '0';
});
document.body.appendChild(m);
return m;
}
function styleTag(): string {
// Copied/adapted from StoreAI overlay style for a 1:1 UI feel.
return `<style>
:host, .container, .expanded, .capsule, button {
font-family: -apple-system, 'Segoe UI', 'PingFang SC', 'Microsoft YaHei', sans-serif;
font-size: 13px;
color: #e6edf3;
box-sizing: border-box;
}
.container {
width: 360px;
background: linear-gradient(180deg, #0d1117 0%, #161b22 100%);
border: 1px solid #30363d;
border-radius: 14px;
box-shadow: 0 10px 32px rgba(0,0,0,0.45), 0 2px 8px rgba(0,0,0,0.25);
overflow: hidden;
transition: all 220ms ease;
}
.container[data-collapsed="1"] { width: auto; background: transparent; border: none; box-shadow: none; }
.container[data-collapsed="1"] .expanded { display: none; }
.container[data-collapsed="0"] .capsule { display: none; }
.container[data-phase="paused"] { border-color: #d29922; box-shadow: 0 10px 32px rgba(210,153,34,0.3); }
.container[data-phase="done"] { border-color: #238636; }
.container[data-phase="failed"] { border-color: #da3633; }
.expanded { display: flex; flex-direction: column; }
.header { display: flex; align-items: center; gap: 12px; padding: 14px 16px 10px 16px; }
.radar-wrap { flex: 0 0 44px; height: 44px; }
.radar {
width: 44px; height: 44px; border-radius: 50%;
position: relative; overflow: hidden;
background: radial-gradient(circle at center, rgba(46,160,67,0.12), rgba(46,160,67,0.02) 70%, transparent 80%);
border: 1px solid rgba(46,160,67,0.35);
}
.sweep {
position: absolute; inset: 0;
background: conic-gradient(from 0deg, rgba(46,160,67,0) 0deg, rgba(46,160,67,0.7) 50deg, rgba(46,160,67,0) 60deg);
animation: sweep 2s linear infinite;
}
.ping {
position: absolute; left: 50%; top: 50%; width: 8px; height: 8px;
background: #2ea043; border-radius: 50%; transform: translate(-50%,-50%);
box-shadow: 0 0 0 0 rgba(46,160,67,0.7);
animation: ping 2s ease-out infinite;
}
@keyframes sweep { from { transform: rotate(0deg); } to { transform: rotate(360deg); } }
@keyframes ping {
0% { box-shadow: 0 0 0 0 rgba(46,160,67,0.7); }
100% { box-shadow: 0 0 0 18px rgba(46,160,67,0); }
}
.container[data-phase="paused"] .sweep,
.container[data-phase="done"] .sweep,
.container[data-phase="failed"] .sweep,
.container[data-phase="cancelled"] .sweep { animation: none; opacity: 0.3; }
.container[data-phase="done"] .ping { background: #2ea043; animation: none; }
.container[data-phase="paused"] .ping { background: #d29922; animation: none; }
.container[data-phase="failed"] .ping { background: #da3633; animation: none; }
.titles { flex: 1 1 auto; min-width: 0; }
.title { font-size: 14px; font-weight: 600; color: #f0f6fc; line-height: 1.3; margin: 0; white-space: nowrap; overflow: hidden; text-overflow: ellipsis; }
.subtitle { font-size: 12px; color: #8b949e; margin-top: 2px; white-space: nowrap; overflow: hidden; text-overflow: ellipsis; }
.minimise-btn {
flex: 0 0 auto;
background: transparent; color: #8b949e;
border: 1px solid #30363d; border-radius: 6px;
width: 28px; height: 28px; cursor: pointer;
font-size: 16px; line-height: 1;
transition: all 120ms ease;
}
.minimise-btn:hover { color: #e6edf3; border-color: #8b949e; }
.body { padding: 2px 16px 12px 16px; }
.steps-list { display: flex; flex-direction: column; gap: 6px; }
.step { display: flex; align-items: center; gap: 8px; font-size: 12px; line-height: 1.4; padding: 4px 0; color: #8b949e; }
.step[data-status="active"] { color: #58a6ff; }
.step[data-status="ok"] { color: #3fb950; }
.step[data-status="partial"] { color: #d29922; }
.step[data-status="failed"] { color: #f85149; }
.step .dot { flex: 0 0 auto; display: inline-flex; width: 16px; height: 16px; align-items: center; justify-content: center; font-size: 10px; font-weight: 700; }
.step .step-label { flex: 1 1 auto; min-width: 0; white-space: nowrap; overflow: hidden; text-overflow: ellipsis; }
.current-detail {
margin-top: 10px;
padding: 8px 10px;
background: rgba(110,118,129,0.08);
border: 1px dashed rgba(139,148,158,0.25);
border-radius: 6px;
color: #c9d1d9;
font-size: 11.5px; line-height: 1.4;
}
.pause-banner { margin-top: 12px; padding: 10px 12px; background: rgba(210,153,34,0.08); border: 1px solid rgba(210,153,34,0.35); border-radius: 8px; }
.pause-row { display: flex; align-items: flex-start; gap: 10px; }
.pause-icon { flex: 0 0 22px; width: 22px; height: 22px; background: #d29922; color: #0d1117; border-radius: 50%; display: inline-flex; align-items: center; justify-content: center; font-weight: 700; font-size: 13px; }
.pause-message { flex: 1 1 auto; color: #e6edf3; font-size: 12px; line-height: 1.45; }
.pause-auto-hint { margin-top: 8px; font-size: 11px; color: #d29922; line-height: 1.45; opacity: 0.85; }
.resume-btn { margin-top: 10px; width: 100%; padding: 8px 10px; background: #d29922; color: #0d1117; border: none; border-radius: 6px; font-size: 12px; font-weight: 600; cursor: pointer; transition: filter 120ms ease; }
.resume-btn:hover { filter: brightness(1.1); }
.autoclose-banner { margin: 0 16px 8px 16px; padding: 10px 12px; display: flex; align-items: center; justify-content: space-between; gap: 10px; background: rgba(88,166,255,0.08); border: 1px solid rgba(88,166,255,0.35); border-radius: 8px; }
.autoclose-text { flex: 1 1 auto; min-width: 0; font-size: 11.5px; color: #c9d1d9; line-height: 1.4; }
.stay-open-btn { flex: 0 0 auto; padding: 6px 12px; background: #58a6ff; color: #0d1117; border: none; border-radius: 5px; font-size: 11px; font-weight: 600; cursor: pointer; transition: filter 120ms ease; }
.stay-open-btn:hover { filter: brightness(1.1); }
.footer { padding: 10px 16px 14px 16px; border-top: 1px solid rgba(48,54,61,0.6); display: flex; flex-direction: column; gap: 10px; }
.coffee-hint { font-size: 11px; color: #8b949e; line-height: 1.5; }
.cancel-btn { align-self: flex-start; padding: 5px 10px; background: transparent; color: #8b949e; border: 1px solid #30363d; border-radius: 6px; font-size: 11px; cursor: pointer; transition: all 120ms ease; }
.cancel-btn:hover { color: #f85149; border-color: #f85149; }
/* 中文备注:圆形菜单(左下角)只展示计时;点击展开查看详细进度 */
.capsule { width: 56px; height: 56px; padding: 0; display: inline-flex; align-items: center; justify-content: center; background: #0d1117; color: #e6edf3; border: 1px solid #30363d; border-radius: 50%; box-shadow: 0 4px 14px rgba(0,0,0,0.4); cursor: pointer; font-size: 12px; transition: all 120ms ease; position: relative; }
.capsule:hover { transform: translateY(-1px); }
.radar-mini { position: absolute; inset: 6px; border-radius: 50%; overflow: hidden; background: radial-gradient(circle at center, rgba(46,160,67,0.20), rgba(46,160,67,0.03) 70%, transparent 82%); border: 1px solid rgba(46,160,67,0.40); }
.sweep-mini { position: absolute; inset: 0; background: conic-gradient(from 0deg, rgba(46,160,67,0) 0deg, rgba(46,160,67,0.8) 50deg, rgba(46,160,67,0) 60deg); animation: sweep 2s linear infinite; }
.capsule-time { position: relative; z-index: 1; font-variant-numeric: tabular-nums; font-weight: 700; letter-spacing: 0.2px; }
</style>`;
}

View File

@@ -1,22 +1,12 @@
import { createApp } from 'vue'; import { setupPageRunner } from './pageRunner';
import App from './App.vue'; import { mountCrawlOverlay } from './crawlOverlay';
/** 将内容脚本应用挂载到页面中。 */ /**
* 将内容脚本应用挂载到页面中。
*/
function mountApp() { function mountApp() {
if (document.getElementById('dianshan-crx-root')) { setupPageRunner();
return; mountCrawlOverlay();
}
/** 内容脚本在宿主页面中的根容器,用于避免污染业务页面结构。 */
const container = document.createElement('div');
container.id = 'dianshan-crx-root';
/** Vue 应用实际挂载的节点。 */
const appRoot = document.createElement('div');
container.appendChild(appRoot);
document.body.appendChild(container);
createApp(App).mount(appRoot);
} }
if (document.readyState === 'loading') { if (document.readyState === 'loading') {

207
src/content/pageRunner.ts Normal file
View File

@@ -0,0 +1,207 @@
import { processFields, type DomScrapeResult } from '@/background/domScraper';
import type { CrawlPauseInfo, PlatformFieldConfig } from '@/types';
interface ScrapeStepMessage {
action: 'SCRAPE_STEP';
payload: {
fields: PlatformFieldConfig[];
checkSelector: string;
};
}
interface CheckInterruptMessage {
action: 'CHECK_INTERRUPT';
}
type PageRunnerMessage = ScrapeStepMessage | CheckInterruptMessage;
interface PageRunnerResponse {
ok: boolean;
data?: DomScrapeResult | null;
interrupt?: CrawlPauseInfo;
error?: string;
}
/**
* 注册页面执行器,供 background 在目标网页中触发中断检测和 DOM 抓取。
*/
export function setupPageRunner(): void {
chrome.runtime.onMessage.addListener((message: PageRunnerMessage, _sender, sendResponse) => {
void handlePageRunnerMessage(message).then(sendResponse);
return true;
});
}
/**
* 处理 background 发来的页面执行消息。
*/
async function handlePageRunnerMessage(message: PageRunnerMessage): Promise<PageRunnerResponse> {
if (message.action === 'CHECK_INTERRUPT') {
return { ok: true, interrupt: detectPageInterrupt() };
}
if (message.action === 'SCRAPE_STEP') {
const interrupt = detectPageInterrupt();
if (interrupt) {
return { ok: false, interrupt };
}
const readyElement = await waitForStableSelector(message.payload.checkSelector, 18000);
if (!readyElement) {
return {
ok: false,
interrupt: {
reason: 'page_not_ready',
message: '页面关键内容暂未加载,请确认页面是否正常显示后继续',
},
};
}
const data = await processFields(message.payload.fields, document.body);
return { ok: true, data };
}
return { ok: false, error: '未知页面执行指令' };
}
/**
* 检测当前页面是否需要用户手动处理登录、验证码或页面不存在。
*/
function detectPageInterrupt(): CrawlPauseInfo | undefined {
if (isShieldPage()) {
return {
reason: 'shield',
message: '检测到验证码或风控验证,请在打开的商家后台窗口处理完成后继续',
};
}
if (isLoginPage()) {
return {
reason: 'reauth',
message: '检测到需要重新登录,请在打开的商家后台窗口登录完成后继续',
};
}
if (isNotFoundPage()) {
return {
reason: 'not_found',
message: '当前页面不存在或已失效,请确认平台配置里的页面地址是否正确',
};
}
}
/**
* 判断是否进入验证码、流量盾或风控验证页。
*/
function isShieldPage(): boolean {
const path = location.pathname.toLowerCase();
if (path.startsWith('/verify/captcha') || path.startsWith('/verify/traffic')) {
return true;
}
const shieldElement = document.querySelector(
'[data-name="verification"], .ant-captcha, #captchaContainer, [class*="captcha" i], [id*="captcha" i]',
);
return shieldElement ? isVisibleElement(shieldElement) : false;
}
/**
* 判断当前页面是否需要登录或二次验证密码。
*/
function isLoginPage(): boolean {
const path = location.pathname.toLowerCase();
if (
/^\/(?:buyer\/)?login\b/i.test(path) ||
/^\/account\/(?:signin|login)\b/i.test(path) ||
/^\/portal\/login\b/i.test(path)
) {
return true;
}
const visiblePasswordInput = Array.from(document.querySelectorAll('input[type="password"]')).some(isVisibleElement);
if (visiblePasswordInput) {
return true;
}
const bodyText = document.body.innerText.slice(0, 3000);
const loginTextPatterns = [
/enter\s+(your\s+)?password\s+to\s+continue/i,
/sign\s+in\s+(again\s+)?to\s+continue/i,
/please\s+(re-?)?enter\s+(your\s+)?password/i,
/请(再次|重新)?输入(您的)?密码/,
/请登录|重新登录|登录后继续/,
];
return loginTextPatterns.some((pattern) => pattern.test(bodyText));
}
/**
* 判断当前页面是否是不存在、下架或错误页面。
*/
function isNotFoundPage(): boolean {
const text = document.body.innerText.slice(0, 8000);
const title = document.title;
const notFoundPatterns = [
/page\s+not\s+found/i,
/the\s+page\s+you\s+are\s+looking\s+for/i,
/this\s+page\s+(has\s+been\s+)?removed/i,
/product\s+(is\s+)?unavailable/i,
/页面不存在|找不到(此|该)?页面|抱歉.*不存在|(商品|产品)已下架/,
];
return notFoundPatterns.some((pattern) => pattern.test(title) || pattern.test(text));
}
/**
* 等待页面中出现稳定的关键元素。
*/
async function waitForStableSelector(selector: string, timeoutMs: number): Promise<Element | null> {
const deadline = Date.now() + timeoutMs;
while (Date.now() < deadline) {
const element = document.querySelector(selector);
if (element && isVisibleElement(element)) {
await sleep(600);
const stableElement = document.querySelector(selector);
return stableElement && isVisibleElement(stableElement) ? stableElement : null;
}
await sleep(500);
}
return null;
}
/**
* 判断元素是否真实可见。
*/
function isVisibleElement(element: Element): boolean {
if (!element.isConnected) {
return false;
}
const style = element.ownerDocument.defaultView?.getComputedStyle(element);
if (!style || style.display === 'none' || style.visibility === 'hidden' || Number(style.opacity) < 0.05) {
return false;
}
const rect = element.getBoundingClientRect();
return rect.width > 0 && rect.height > 0;
}
/**
* 简单等待工具。
*/
function sleep(ms: number): Promise<void> {
return new Promise((resolve) => {
window.setTimeout(resolve, ms);
});
}

View File

@@ -1,231 +1,218 @@
<script setup lang="ts"> <script setup lang="ts">
import { computed, onMounted, onUnmounted, ref } from 'vue'; import {platformConfigs} from '@/config/platforms';
import { PLATFORM_CONFIGS } from '@/config/platforms'; import {formatSeconds} from '@/shared/time_format';
import { getToken, logout, mockLogin } from '@/shared/auth'; import {useLogin} from './hook/use-login';
import type { CrawlTaskState } from '@/types'; import {useScan} from './hook/use-scan';
import {useI18n, type PopupUiLang} from './hook/use-i18n';
const token = ref<string | null>(null); const {isLoggedIn, handleLogin, handleLogout} = useLogin();
const selectedPlatformId = ref(PLATFORM_CONFIGS[0]?.id ?? '');
const isLoading = ref(true);
const isScanning = ref(false);
const errorMessage = ref('');
const crawlState = ref<CrawlTaskState | null>(null);
const elapsedSeconds = ref(0);
let timer: number | undefined;
const selectedPlatform = computed(() => // 中文备注Popup 内多语言(只影响文案显示)
PLATFORM_CONFIGS.find((platform) => platform.id === selectedPlatformId.value) ?? null, const {uiLang, setUiLang, t, langOptions} = useI18n();
);
const isLoggedIn = computed(() => token.value !== null); const {
const isCrawling = computed(() => crawlState.value?.status === 'running'); selectedPlatformId,
isScanning,
crawlState,
elapsedSeconds,
taskStatus,
handleScan,
handleCancelCrawl,
handleResumeCrawl,
quotaLoading,
subscriptionExpired,
quotaDeniedMessage,
openBillingPage,
} = useScan();
console.log(crawlState.value)
onMounted(async () => {
token.value = await getToken();
await refreshCrawlState();
timer = window.setInterval(() => {
updateElapsedSeconds();
void refreshCrawlState();
}, 1000);
isLoading.value = false;
});
onUnmounted(() => {
if (timer) {
window.clearInterval(timer);
}
});
async function handleLogin() {
errorMessage.value = '';
token.value = await mockLogin();
}
async function handleLogout() {
errorMessage.value = '';
await logout();
token.value = null;
}
async function handleScan() {
errorMessage.value = '';
if (!selectedPlatform.value) {
errorMessage.value = '请选择要爬取的平台';
return;
}
isScanning.value = true;
/** 从扩展 manifest 读取版本号(兜底 `0.0.0`)。 */
const manifestVersion = (() => {
try { try {
const response = await sendBackgroundMessage<CrawlTaskState>({ return chrome.runtime.getManifest().version;
action: 'START_CRAWL', } catch {
payload: { platformId: selectedPlatform.value.id }, return '0.0.0';
}); }
})();
if (!response.ok) {
errorMessage.value = response.error ?? '打开平台窗口失败';
return;
}
crawlState.value = response.data ?? null; /** 若爬取窗口存在,则将其置顶并吸引注意力。 */
updateElapsedSeconds(); async function focusCrawlWindow(): Promise<void> {
} catch (error: unknown) { if (!crawlState.value?.windowId) return;
errorMessage.value = error instanceof Error ? error.message : '打开平台窗口失败'; try {
} finally { await chrome.windows.update(crawlState.value.windowId, {focused: true, drawAttention: true});
isScanning.value = false; } catch {
// ignore
} }
} }
async function handleCancelCrawl() {
const response = await sendBackgroundMessage<CrawlTaskState>({ action: 'CANCEL_CRAWL' }); /**
crawlState.value = response.data ?? null; * 取消
*/
function requestCancel(): void {
// 中文备注:不要在这里手动把 crawlState 置空。
// 任务状态以 storage 同步为准;手动置空会让 use-scan 的计时器回调访问空对象,导致 popup 闪退(表现为“闪一下”)。
void handleCancelCrawl();
} }
async function refreshCrawlState() { /**
const response = await sendBackgroundMessage<CrawlTaskState | null>({ action: 'GET_CRAWL_STATE' }); * 语言切换
* 中文备注:用事件回调承接,避免在 template 里写复杂类型断言影响可读性。
if (response.ok) { */
crawlState.value = response.data ?? null; function onLangChange(event: Event): void {
updateElapsedSeconds(); const value = (event.target as HTMLSelectElement).value as PopupUiLang;
} void setUiLang(value);
} }
function updateElapsedSeconds() {
if (!crawlState.value) {
elapsedSeconds.value = 0;
return;
}
elapsedSeconds.value = Math.max(0, Math.floor((Date.now() - crawlState.value.startedAt) / 1000));
}
function formatElapsed(totalSeconds: number): string {
const minutes = Math.floor(totalSeconds / 60).toString().padStart(2, '0');
const seconds = (totalSeconds % 60).toString().padStart(2, '0');
return `${minutes}:${seconds}`;
}
function getStepClass(status: string): string {
if (status === 'running') {
return 'border-emerald-500 bg-emerald-50 text-emerald-700';
}
if (status === 'success') {
return 'border-green-500 bg-green-50 text-green-700';
}
if (status === 'failed') {
return 'border-red-500 bg-red-50 text-red-700';
}
return 'border-slate-300 bg-white text-slate-500';
}
function getStepText(status: string): string {
const textMap: Record<string, string> = {
pending: '等待中',
running: '爬取中',
success: '已完成',
failed: '爬取失败',
};
return textMap[status] ?? status;
}
function sendBackgroundMessage<T>(message: unknown): Promise<{ ok: boolean; data?: T; error?: string }> {
if (typeof chrome === 'undefined' || !chrome.runtime?.sendMessage) {
return Promise.resolve({ ok: true, data: null as T });
}
return chrome.runtime.sendMessage(message);
}
</script> </script>
<template> <template>
<main class="w-80 bg-slate-50 text-slate-900"> <div class="container">
<section class="flex min-h-64 flex-col gap-5 p-5"> <header>
<header class="space-y-2"> <div class="logo">
<p class="text-lg font-semibold leading-6">店闪</p> <span class="logo-mark">SA</span>
<p class="text-sm leading-5 text-slate-600">自动打开商家后台按平台配置顺序采集页面数据</p> <span>StoreAI</span>
</header>
<div v-if="isLoading" class="rounded-md border border-slate-200 bg-white px-3 py-4 text-sm text-slate-500">
正在读取登录状态...
</div> </div>
</header>
<template v-else-if="!isLoggedIn"> <!-- 未登录-->
<button type="button" <template v-if="!isLoggedIn">
class="rounded-md bg-slate-900 px-4 py-2.5 text-sm font-medium text-white transition hover:bg-slate-700" <div class="status">{{ t('please_login') }}</div>
@click="handleLogin"> <button style="margin-top: 20px" type="button" @click="handleLogin">
请登录 {{ t('sign_in') }}
</button> </button>
</template> </template>
<template v-else-if="isCrawling && crawlState"> <template v-else>
<section class="space-y-4"> <!-- 未开始-->
<div class="flex items-center justify-between rounded-md bg-white px-3 py-2 shadow-sm"> <template v-if="crawlState == null">
<div>
<p class="text-sm font-medium text-slate-800">{{ crawlState.platformName }}</p>
<p class="text-xs text-slate-500">已运行 {{ formatElapsed(elapsedSeconds) }}</p>
</div>
<button type="button" class="text-xs text-red-600 transition hover:text-red-700"
@click="handleCancelCrawl">
取消
</button>
</div>
<ol class="space-y-3"> <label class="platform-select">
<li v-for="(step, index) in crawlState.steps" :key="step.uniqueKey" <span class="account">{{ t('platform_select') }}</span>
class="relative border-l-2 border-slate-200 pl-4">
<span
class="absolute -left-[7px] top-1 h-3 w-3 rounded-full border-2 border-white bg-slate-300"
:class="{ 'bg-emerald-500': step.status === 'running' || step.status === 'success', 'bg-red-500': step.status === 'failed' }"></span>
<div class="rounded-md border px-3 py-2 text-sm" :class="getStepClass(step.status)">
<div class="flex items-center justify-between gap-3">
<span class="font-medium">{{ index + 1 }}. {{ step.name }}</span>
<span class="text-xs">{{ getStepText(step.status) }}</span>
</div>
<p v-if="step.message" class="mt-1 text-xs">{{ step.message }}</p>
</div>
</li>
</ol>
</section>
</template>
<template v-else>
<label class="space-y-2">
<span class="text-sm font-medium text-slate-700">平台选择</span>
<select v-model="selectedPlatformId" <select v-model="selectedPlatformId"
class="w-full rounded-md border border-slate-300 bg-white px-3 py-2 text-sm outline-none transition focus:border-slate-800 focus:ring-2 focus:ring-slate-200"> class="platform-select__control">
<option v-for="platform in PLATFORM_CONFIGS" :key="platform.id" :value="platform.id"> <option v-for="platform in platformConfigs"
:key="platform.id"
:value="platform.id">
{{ platform.name }} {{ platform.name }}
</option> </option>
</select> </select>
</label> </label>
<button type="button" <!-- 中文备注订阅到期时不允许用户在扩展里直接点立即扫描绕过订阅限制 -->
class="rounded-md bg-emerald-600 px-4 py-2.5 text-sm font-medium text-white transition hover:bg-emerald-500 disabled:cursor-not-allowed disabled:bg-slate-300" <template v-if="subscriptionExpired">
:disabled="isScanning" @click="handleScan"> <div class="status">{{ t('subscription_expired') }}</div>
{{ isScanning ? '正在打开...' : '立即爬取' }} <button type="button" @click="openBillingPage">
</button> {{ t('go_billing') }}
</button>
</template>
<template v-else>
<button type="button" :disabled="isScanning || quotaLoading" @click="handleScan">
{{ quotaLoading ? t('checking_sub') : (isScanning ? t('opening') : t('scan_now')) }}
</button>
<div v-if="quotaDeniedMessage" class="status" style="margin-top: 8px;">
{{ quotaDeniedMessage || t('scan_disabled') }}
</div>
</template>
</template> </template>
<p v-if="errorMessage" class="rounded-md bg-red-50 px-3 py-2 text-sm text-red-700"> <!-- 进行中-->
{{ errorMessage }} <template v-else>
</p> <div :class="['radar-card', taskStatus]">
<div class="radar-row">
<div class="radar">
<div class="sweep"></div>
<div class="ping"></div>
</div>
<div class="radar-titles">
<div class="radar-title">{{ crawlState.platformName }}</div>
<div class="radar-sub">
<template v-if="taskStatus == 'paused'">{{ t('paused') }}</template>
<template v-else-if="taskStatus == 'completed'">{{ t('done') }}</template>
<template v-else-if="taskStatus == 'failed'">{{ t('failed') }}</template>
<template v-else>{{ t('scanning') }}</template>
· {{ formatSeconds(elapsedSeconds) }}
</div>
</div>
</div>
<footer <div class="steps">
class="mt-auto flex items-center justify-between border-t border-slate-200 pt-4 text-xs text-slate-500"> <div v-for="(step, index) in crawlState.steps" :key="step.uniqueKey" class="step">
<button v-if="isLoggedIn" type="button" class="text-slate-600 transition hover:text-slate-900" <div class="step-left">
@click="handleLogout"> <div class="step-dot">
退出 <span v-if="step.status =='success'"></span>
</button> <span v-else-if="step.status =='failed'">×</span>
<span v-else></span> <span v-else-if="step.status =='running'"></span>
<span>v1.0.0</span> </div>
</footer> <div class="step-label">{{ index + 1 }}. {{ step.name }}</div>
</section> </div>
</main> <div class="step-status">
<span v-if="step.status == 'success'">{{ t('step_done') }}</span>
<span v-else-if="step.status == 'failed'">{{ t('step_failed') }}</span>
<span v-else-if="step.status == 'running'">{{ t('step_running') }}</span>
<span v-else-if="step.status == 'pending'">{{ t('step_pending') }}</span>
</div>
</div>
</div>
<div class="actions">
<!-- 运行中-->
<template v-if="taskStatus == 'running'">
<button v-if="taskStatus == 'running'"
type="button"
class="secondary"
@click="focusCrawlWindow">
{{ t('show_tab') }}
</button>
</template>
<!-- 暂停中-->
<template v-else-if="taskStatus == 'paused'">
<button type="button" @click="handleResumeCrawl">
{{ t('continue_now') }}
</button>
</template>
<button id="popup-cancel-btn"
type="button"
class="secondary"
@click="requestCancel">
{{ t('cancel') }}
</button>
</div>
</div>
</template>
</template>
<footer>
<button
v-if="isLoggedIn"
type="button"
class="secondary footer-btn"
@click="handleLogout">
{{ t('sign_out') }}
</button>
<div style="display:flex; align-items:center; gap:8px;">
<label style="display:flex; align-items:center; gap:6px;">
<span style="font-size: 12px; opacity: 0.75;">{{ t('language') }}</span>
<select
:value="uiLang"
style="font-size: 12px; padding: 2px 6px; border-radius: 6px; border: 1px solid rgba(0,0,0,0.12);"
@change="onLangChange"
>
<option v-for="opt in langOptions" :key="opt.value" :value="opt.value">
{{ t(opt.labelKey) }}
</option>
</select>
</label>
<span class="version">v{{ manifestVersion }}</span>
</div>
</footer>
</div>
</template> </template>
<style> <style>

119
src/popup/hook/use-i18n.ts Normal file
View File

@@ -0,0 +1,119 @@
import {computed, onMounted, ref} from 'vue';
/**
* Popup 多语言(仅影响 Popup 文案,不改平台配置/爬取数据)。
* 中文备注:用户要求把切换入口放在 Popup 底部版本号附近,因此这里提供一个轻量的本地 i18n。
*/
/** chrome.storage.local 中保存语言的 key */
const POPUP_UI_LANG_KEY = 'popupUiLang';
/** 目前仅提供中英两种,后续可在这里继续扩展 */
export type PopupUiLang = 'zh-CN' | 'en';
/** 文案字典key 统一用英文标识,方便维护 */
const DICT: Record<PopupUiLang, Record<string, string>> = {
'zh-CN': {
please_login: '请先登录后再开始爬取',
sign_in: '登录',
sign_out: '退出登录',
platform_select: '平台选择',
scan_now: '立即扫描',
checking_sub: '正在检查订阅…',
subscription_expired: '订阅已到期,扫描功能已锁定。',
go_billing: '去订阅/续费',
scan_disabled: '暂时不允许扫描。',
opening: '正在打开…',
scanning: '扫描中',
paused: '已暂停',
done: '已完成',
failed: '失败',
show_tab: '显示页面',
continue_now: '继续',
cancel: '取消',
step_done: '已完成',
step_failed: '失败',
step_running: '进行中',
step_pending: '等待中',
language: '语言',
lang_zh: '中文',
lang_en: 'English',
},
en: {
please_login: 'Please sign in before scanning.',
sign_in: 'Sign in',
sign_out: 'Sign out',
platform_select: 'Platform',
scan_now: 'Scan now',
checking_sub: 'Checking subscription…',
subscription_expired: 'Subscription expired. Scanning is locked.',
go_billing: 'Upgrade / Renew',
scan_disabled: 'Scan not allowed right now.',
opening: 'Opening…',
scanning: 'Scanning',
paused: 'Paused',
done: 'Done',
failed: 'Failed',
show_tab: 'Show tab',
continue_now: 'Continue now',
cancel: 'Cancel',
step_done: 'Completed',
step_failed: 'Failed',
step_running: 'Running',
step_pending: 'Pending',
language: 'Language',
lang_zh: '中文',
lang_en: 'English',
},
};
/**
* Popup 内使用的 i18n composable
*/
export function useI18n() {
const uiLang = ref<PopupUiLang>('zh-CN');
// 中文备注:从本地存储恢复用户上次选择
onMounted(async () => {
try {
if (typeof chrome === 'undefined' || !chrome.storage?.local) return;
const res = await chrome.storage.local.get(POPUP_UI_LANG_KEY);
const stored = res?.[POPUP_UI_LANG_KEY];
if (stored === 'zh-CN' || stored === 'en') {
uiLang.value = stored;
}
} catch {
// ignore
}
});
const t = computed(() => {
return (key: string) => {
return DICT[uiLang.value]?.[key] ?? DICT.en[key] ?? key;
};
});
/**
* 设置语言并持久化
*/
async function setUiLang(lang: PopupUiLang) {
uiLang.value = lang;
try {
if (typeof chrome === 'undefined' || !chrome.storage?.local) return;
await chrome.storage.local.set({[POPUP_UI_LANG_KEY]: lang});
} catch {
// ignore
}
}
return {
uiLang,
t: t.value,
setUiLang,
// 中文备注:给 template 直接使用的语言选项
langOptions: [
{value: 'zh-CN' as const, labelKey: 'lang_zh'},
{value: 'en' as const, labelKey: 'lang_en'},
],
};
}

View File

@@ -0,0 +1,57 @@
import {computed, onMounted, ref} from "vue";
import {APP_URL} from "@/config";
import {clearAuthState, getAuthState, initAuthState} from "@/shared/store";
/**
* Popup 的登录状态与操作
*
* 中文备注:
* - 扩展侧不直接拿 Web token登录/配对在网页侧完成
* - 网页侧拿到 extension token 后,会通过 `onMessageExternal` 回传并写入 `chrome.storage.local['auth_state']`
*/
export const useLogin = () => {
const token = ref<string | null>(null);
// 当前是否已登录(是否已有 extension token
const isLoggedIn = computed(() => token.value !== null);
/**
* 登录:打开网页,让网页完成配对并回传 extension token
*/
const handleLogin = async () => {
const extId = chrome?.runtime?.id || "";
const url = `${APP_URL.replace(/\/$/, "")}/onboarding/extension?from=extension&extId=${encodeURIComponent(extId)}`;
await chrome.tabs.create({url, active: true});
};
/**
* 退出:清空本地 token 与上下文
*/
const handleLogout = async () => {
await clearAuthState();
token.value = null;
};
onMounted(async () => {
// 中文备注:先恢复内存态 authState再读 token 判断是否已配对
await initAuthState();
token.value = getAuthState()?.token ?? null;
// 中文备注:监听 storage 变化,网页回传 token 后popup 自动刷新“已登录”状态
if (chrome?.storage?.onChanged) {
const handler = (changes: Record<string, chrome.storage.StorageChange>, areaName: string) => {
if (areaName !== "local") return;
const change = changes["auth_state"];
if (!change) return;
token.value = (change.newValue as any)?.token ?? null;
};
chrome.storage.onChanged.addListener(handler);
}
});
return {
isLoggedIn,
handleLogin,
handleLogout,
};
};

223
src/popup/hook/use-scan.ts Normal file
View File

@@ -0,0 +1,223 @@
import {computed, onMounted, onUnmounted, ref} from "vue";
import {platformConfigs} from "@/config/platforms";
import type {CrawlTaskState} from "@/types";
import {sendBackgroundMessage} from "@/shared/message";
import {getScanQuotaApi} from "@/api/me";
import {APP_URL} from "@/config";
/**
* Popup 内的爬取状态与操作集合
*
* 中文备注:
* - 订阅存在“隐藏逻辑”:订阅到期时不能让用户绕过网页,直接在扩展 popup 点“立即扫描”
* - 这里会在 popup 打开时调用一次 `/api/me/scan-quota`,如果订阅过期则隐藏“立即扫描”按钮,改为引导去订阅
*/
export const useScan = () => {
/** 当前选中的平台 id */
const selectedPlatformId = ref(platformConfigs[0]?.id ?? "");
/** 防止重复点击 “Scan now” */
const isScanning = ref<boolean>(false);
/** 当前爬取任务状态(从 background 同步) */
const crawlState = ref<CrawlTaskState | null>(null);
const taskStatus = computed(() => crawlState.value?.status);
/** 任务耗时(秒) */
const elapsedSeconds = ref<number>(0);
let timer: number | undefined;
// 中文备注:订阅/权限检查(控制“立即扫描”按钮是否可用)
const quotaLoading = ref<boolean>(false);
const quotaDeniedReason = ref<string | null>(null);
const quotaDeniedMessage = ref<string | null>(null);
const subscriptionExpired = computed(() => quotaDeniedReason.value === "subscription_required");
/**
* 停止计时器并清零
* 中文备注crawlState 被清空时必须停表,否则 timer 回调会访问空对象导致 popup “闪一下”
*/
function stopElapsedTimer() {
if (timer) {
window.clearInterval(timer);
timer = undefined;
}
elapsedSeconds.value = 0;
}
function startElapsedTimer() {
if (crawlState.value === null || timer) return;
timer = window.setInterval(() => {
elapsedSeconds.value = Math.max(0, Math.floor((Date.now() - crawlState.value!.startedAt) / 1000));
}, 1000);
}
function syncCrawlState(state: CrawlTaskState | null) {
crawlState.value = state;
if (state === null) {
stopElapsedTimer();
return;
}
startElapsedTimer();
}
async function refreshCrawlState() {
const response = await sendBackgroundMessage<CrawlTaskState | null>({action: "GET_CRAWL_STATE"});
if (response.ok) {
syncCrawlState(response.data ?? null);
}
}
/**
* 打开订阅页面(网页侧)
*/
async function openBillingPage() {
const url = `${APP_URL.replace(/\/$/, "")}/dashboard/billing`;
await chrome.tabs.create({url, active: true});
}
/**
* 刷新订阅/权限信息(扩展 token 鉴权)
*/
async function refreshQuota() {
if (quotaLoading.value) return;
// 中文备注:未登录(无 auth_state时不请求交给 UI 显示“请登录”即可
const stored: any = await chrome.storage.local.get("auth_state");
if (!stored?.auth_state?.token) {
quotaDeniedReason.value = null;
quotaDeniedMessage.value = null;
return;
}
quotaLoading.value = true;
try {
const quota: any = await getScanQuotaApi();
if (quota?.allowed === true) {
quotaDeniedReason.value = null;
quotaDeniedMessage.value = null;
} else {
quotaDeniedReason.value = String(quota?.reason || "scan_not_allowed");
quotaDeniedMessage.value = String(quota?.message || "");
}
} catch (e: any) {
// 中文备注:接口失败时不在 UI 里误判为“订阅到期”,只记录为不可扫描
quotaDeniedReason.value = "quota_check_failed";
quotaDeniedMessage.value = e?.response?.data?.message || e?.message || "";
} finally {
quotaLoading.value = false;
}
}
/**
* 触发扫描(开始前会先做订阅校验)
*/
const handleScan = async () => {
if (isScanning.value) return;
isScanning.value = true;
try {
// 中文备注:点击“立即扫描”前先刷新一次订阅/权限,避免订阅刚到期但按钮仍可点
await refreshQuota();
if (subscriptionExpired.value) {
await openBillingPage();
return;
}
if (quotaDeniedReason.value) {
console.error("[crawl] scan blocked:", quotaDeniedReason.value, quotaDeniedMessage.value);
return;
}
const response = await sendBackgroundMessage<CrawlTaskState>({
action: "START_CRAWL",
payload: {platformId: selectedPlatformId.value},
});
if (response.ok) {
syncCrawlState(response.data ?? null);
} else {
console.error("[crawl] start failed", response.error);
}
} finally {
isScanning.value = false;
}
};
const handleCancelCrawl = async () => {
const response = await sendBackgroundMessage<CrawlTaskState | null>({action: "CANCEL_CRAWL"});
if (response.ok) {
syncCrawlState(response.data ?? null);
return;
}
console.error("[crawl] cancel failed", response.error);
await refreshCrawlState();
};
const handleResumeCrawl = async () => {
const response = await sendBackgroundMessage<CrawlTaskState | null>({action: "RESUME_CRAWL"});
if (response.ok) {
syncCrawlState(response.data ?? null);
return;
}
console.error("[crawl] resume failed", response.error);
await refreshCrawlState();
};
const handleDismissCrawl = async () => {
const response = await sendBackgroundMessage<CrawlTaskState | null>({action: "DISMISS_CRAWL"});
if (response.ok) {
syncCrawlState(response.data ?? null);
return;
}
console.error("[crawl] dismiss failed", response.error);
await refreshCrawlState();
};
/**
* 监听 storage 变化:
* - crawlTaskState同步任务进度
* - auth_state登录/退出/重新配对后刷新订阅状态
*/
function handleStorageChanged(changes: Record<string, chrome.storage.StorageChange>, areaName: string) {
if (areaName !== "local") return;
if (changes["auth_state"]) {
void refreshQuota();
}
const change = changes["crawlTaskState"];
if (!change) return;
syncCrawlState(isCrawlTaskState(change.newValue) ? change.newValue : null);
}
onMounted(async () => {
await refreshCrawlState();
await refreshQuota();
chrome.storage.onChanged.addListener(handleStorageChanged);
});
onUnmounted(() => {
stopElapsedTimer();
chrome.storage.onChanged.removeListener(handleStorageChanged);
});
return {
selectedPlatformId,
isScanning,
crawlState,
taskStatus,
elapsedSeconds,
handleScan,
handleCancelCrawl,
handleResumeCrawl,
handleDismissCrawl,
// 订阅/权限
quotaLoading,
subscriptionExpired,
quotaDeniedMessage,
openBillingPage,
};
};
function isCrawlTaskState(value: unknown): value is CrawlTaskState {
return typeof value === "object" && value !== null && "id" in value && "steps" in value;
}

View File

@@ -1,5 +1,5 @@
import { createApp } from 'vue'; import { createApp } from 'vue';
import App from './App.vue'; import App from './App.vue';
import './popup.scss';
createApp(App).mount('#app'); createApp(App).mount('#app');

410
src/popup/popup.scss Normal file
View File

@@ -0,0 +1,410 @@
:root {
--bg: #ffffff;
--fg: #0f172a;
--muted: #64748b;
--border: #e2e8f0;
--primary: #0f172a;
--primary-fg: #ffffff;
--accent: #f1f5f9;
--success: #22c55e;
--warning: #eab308;
--danger: #ef4444;
}
* {
box-sizing: border-box;
margin: 0;
padding: 0;
}
body {
width: 360px;
font-family: -apple-system, BlinkMacSystemFont, 'Segoe UI', system-ui, sans-serif;
background: var(--bg);
color: var(--fg);
}
.container {
padding: 16px;
display: flex;
flex-direction: column;
gap: 12px;
}
header {
display: flex;
align-items: center;
justify-content: space-between;
}
.logo {
display: inline-flex;
align-items: center;
gap: 8px;
font-size: 15px;
font-weight: 600;
letter-spacing: -0.01em;
&-mark {
display: inline-flex;
align-items: center;
justify-content: center;
width: 22px;
height: 22px;
background: var(--primary);
color: var(--primary-fg);
border-radius: 5px;
font-size: 11px;
font-weight: 700;
letter-spacing: 0;
}
}
.status {
font-size: 13px;
color: var(--muted);
line-height: 1.5;
}
.account {
font-size: 12px;
color: var(--muted);
overflow: hidden;
text-overflow: ellipsis;
white-space: nowrap;
}
.platform-select {
display: flex;
flex-direction: column;
gap: 6px;
&__control {
padding: 8px 10px;
border: 1px solid var(--border);
border-radius: 6px;
background: #fff;
font-size: 13px;
&:focus {
outline: none;
}
}
}
.last-scan {
display: flex;
align-items: center;
gap: 8px;
font-size: 13px;
padding: 8px 12px;
background: var(--accent);
border-radius: 6px;
}
.dot {
width: 8px;
height: 8px;
border-radius: 50%;
background: var(--muted);
&-green {
background: var(--success);
}
&-yellow {
background: var(--warning);
}
&-red {
background: var(--danger);
}
}
.progress {
font-size: 12px;
color: var(--muted);
padding: 6px 8px;
background: var(--accent);
border-radius: 4px;
font-style: italic;
}
button {
width: 100%;
padding: 9px 12px;
border: none;
border-radius: 6px;
background: var(--primary);
color: var(--primary-fg);
font-size: 13px;
font-weight: 500;
cursor: pointer;
transition: opacity 150ms ease;
&:hover:not(:disabled) {
opacity: 0.9;
}
&.secondary {
background: transparent;
color: var(--muted);
border: 1px solid var(--border);
}
&:disabled {
opacity: 0.5;
cursor: not-allowed;
}
}
footer {
border-top: 1px solid var(--border);
padding-top: 8px;
font-size: 11px;
color: var(--muted);
display: flex;
align-items: center;
justify-content: space-between;
gap: 8px;
.footer-btn {
width: auto;
padding: 4px 10px;
}
.version {
flex: 0 0 auto;
}
}
.radar-card {
background: linear-gradient(180deg, #0f172a 0%, #1e293b 100%);
color: #e2e8f0;
border-radius: 10px;
padding: 14px;
display: flex;
flex-direction: column;
gap: 10px;
&.paused {
background: linear-gradient(180deg, #2b2008 0%, #3d2b0f 100%);
}
&.done {
background: linear-gradient(180deg, #0a2e1a 0%, #134028 100%);
}
&.failed {
background: linear-gradient(180deg, #2a0f0f 0%, #3b1718 100%);
}
&.canceled {
background: linear-gradient(180deg, #1e293b 0%, #263345 100%);
}
&.paused,
&.done,
&.canceled,
&.failed {
.sweep {
animation: none;
opacity: 0.3;
}
}
&.paused {
.ping {
background: #eab308;
animation: none;
}
}
&.done {
.ping {
background: #22c55e;
animation: none;
}
}
&.failed {
.ping {
background: #ef4444;
animation: none;
}
}
&.canceled {
.ping {
background: #94a3b8;
animation: none;
}
}
}
.radar-row {
display: flex;
align-items: center;
gap: 12px;
}
.radar {
flex: 0 0 40px;
width: 40px;
height: 40px;
position: relative;
overflow: hidden;
border-radius: 50%;
background: radial-gradient(
circle at center,
rgba(46, 160, 67, 0.14),
rgba(46, 160, 67, 0.02) 70%,
transparent 80%
);
border: 1px solid rgba(46, 160, 67, 0.35);
.sweep {
position: absolute;
inset: 0;
background: conic-gradient(
from 0deg,
rgba(46, 160, 67, 0) 0deg,
rgba(46, 160, 67, 0.75) 50deg,
rgba(46, 160, 67, 0) 60deg
);
animation: pop-sweep 2s linear infinite;
}
.ping {
position: absolute;
left: 50%;
top: 50%;
width: 7px;
height: 7px;
background: #2ea043;
border-radius: 50%;
transform: translate(-50%, -50%);
box-shadow: 0 0 0 0 rgba(46, 160, 67, 0.7);
animation: pop-ping 2s ease-out infinite;
}
}
@keyframes pop-sweep {
from {
transform: rotate(0deg);
}
to {
transform: rotate(360deg);
}
}
@keyframes pop-ping {
0% {
box-shadow: 0 0 0 0 rgba(46, 160, 67, 0.7);
}
100% {
box-shadow: 0 0 0 14px rgba(46, 160, 67, 0);
}
}
.radar-titles {
flex: 1 1 auto;
min-width: 0;
}
.radar-title {
font-size: 13px;
font-weight: 600;
line-height: 1.2;
color: #f8fafc;
white-space: nowrap;
overflow: hidden;
text-overflow: ellipsis;
}
.radar-sub {
font-size: 11.5px;
color: rgba(226, 232, 240, 0.75);
margin-top: 2px;
white-space: nowrap;
overflow: hidden;
text-overflow: ellipsis;
}
.steps {
display: flex;
flex-direction: column;
gap: 6px;
}
.step {
display: flex;
align-items: center;
justify-content: space-between;
gap: 10px;
font-size: 12px;
color: rgba(226, 232, 240, 0.8);
&-left {
display: inline-flex;
align-items: center;
gap: 8px;
min-width: 0;
flex: 1 1 auto;
}
&-dot {
width: 16px;
height: 16px;
border-radius: 50%;
background: rgba(226, 232, 240, 0.18);
display: inline-flex;
align-items: center;
justify-content: center;
font-size: 10px;
font-weight: 700;
}
&-label {
min-width: 0;
white-space: nowrap;
overflow: hidden;
text-overflow: ellipsis;
}
&-status {
flex: 0 0 auto;
font-size: 11px;
opacity: 0.85;
}
}
.pause-banner {
border-radius: 8px;
border: 1px solid rgba(234, 179, 8, 0.35);
background: rgba(234, 179, 8, 0.08);
padding: 10px 12px;
font-size: 12px;
line-height: 1.45;
p {
margin: 0;
color: #fef3c7;
}
}
.actions {
display: flex;
gap: 8px;
button {
width: auto;
flex: 1 1 0;
&.secondary {
color: rgba(226, 232, 240, 0.85);
border-color: rgba(226, 232, 240, 0.2);
}
}
}

View File

@@ -1,7 +1,8 @@
const AUTH_TOKEN_KEY = 'token'; const AUTH_TOKEN_KEY = 'token';
const MOCK_TOKEN = 'mock-extension-token';
/** 获取当前登录 token。 */ /**
* 获取当前登录 token。
*/
export async function getToken(): Promise<string | null> { export async function getToken(): Promise<string | null> {
const storage = getChromeStorage(); const storage = getChromeStorage();
@@ -14,13 +15,10 @@ export async function getToken(): Promise<string | null> {
return window.localStorage.getItem(AUTH_TOKEN_KEY); return window.localStorage.getItem(AUTH_TOKEN_KEY);
} }
/** 模拟登录,写入一个临时 token方便后续替换真实登录逻辑。 */
export async function mockLogin(): Promise<string> {
await setToken(MOCK_TOKEN);
return MOCK_TOKEN;
}
/** 清除当前登录 token。 */ /**
* 清除当前登录 token。
*/
export async function logout(): Promise<void> { export async function logout(): Promise<void> {
const storage = getChromeStorage(); const storage = getChromeStorage();
@@ -32,7 +30,7 @@ export async function logout(): Promise<void> {
window.localStorage.removeItem(AUTH_TOKEN_KEY); window.localStorage.removeItem(AUTH_TOKEN_KEY);
} }
async function setToken(token: string): Promise<void> { export async function setToken(token: string): Promise<void> {
const storage = getChromeStorage(); const storage = getChromeStorage();
if (storage) { if (storage) {
@@ -44,7 +42,7 @@ async function setToken(token: string): Promise<void> {
} }
/** /**
* 获取谷歌缓存 * * 获取谷歌缓存
*/ */
function getChromeStorage(): chrome.storage.StorageArea | null { function getChromeStorage(): chrome.storage.StorageArea | null {
if (typeof chrome === 'undefined' || !chrome.storage?.local) { if (typeof chrome === 'undefined' || !chrome.storage?.local) {

54
src/shared/message.ts Normal file
View File

@@ -0,0 +1,54 @@
export type MessageAction =
/** 获取当前爬取任务的状态*/
| 'GET_CRAWL_STATE'
/**
* 仅供 content script爬取窗口页内悬浮面板拉取状态
* - 只在“当前 tab == 爬取 tab”时返回状态其它 tab 返回 null。
* 中文备注:用于悬浮面板初始化时拿到任务快照。
*/
| 'GET_CRAWL_STATE_FOR_TAB'
/** 启动一个新的爬取任务 */
| 'START_CRAWL'
/** 彻底取消并停止当前的爬取任务 */
| 'CANCEL_CRAWL'
/** 恢复之前被暂停或因中断而停止的爬取任务 */
| 'RESUME_CRAWL'
/**
* 取消自动关闭(旧悬浮面板按钮会发这个指令)。
* 中文备注:当前版本默认完成后会清理并关闭窗口;这里保留用于兼容,避免后台报“未知指令”。
*/
| 'CANCEL_AUTOCLOSE'
/** 忽略/关闭当前爬取任务的 UI 提示或通知(通常指任务结束后清理界面) */
| 'DISMISS_CRAWL';
interface BackgroundMessage<T = unknown> {
action: MessageAction;
payload?: T;
}
interface BackgroundResponse<T = unknown> {
ok: boolean;
data: T | null;
error?: string;
}
/**
* 发送消息给服务
*/
export function sendBackgroundMessage<T>(data: BackgroundMessage): Promise<BackgroundResponse<T>> {
if (typeof chrome === 'undefined' || !chrome.runtime?.sendMessage) {
return Promise.resolve({ok: true, data: null});
}
return chrome.runtime.sendMessage(data);
}
//接受

98
src/shared/request.ts Normal file
View File

@@ -0,0 +1,98 @@
import axios, {AxiosError, AxiosRequestConfig, AxiosResponse} from "axios";
import {getAuthState} from "@/shared/store";
/**
* axios 封装(扩展侧):要求与 `my-app/src/utils/reqeust.ts` 保持一致的行为。
*
* 中文备注:
* - 统一 baseURL来自配对后下发的 apiBaseUrl
* - 自动带上 Authorization: Bearer <extension_token>
* - 统一处理后端 `{ code, message, data }`:成功返回 data失败 reject 整个响应体
*/
const service = axios.create({
// 中文备注baseURL 会在请求拦截器里按需动态设置,这里先给空值
baseURL: "",
timeout: 30000,
});
// 请求拦截器
service.interceptors.request.use((config: any) => {
// 中文备注:当数据为 FormData 时,自动修改请求头(与网站端一致)
if (config.data instanceof FormData) {
(config as any).headers = {"Content-Type": "multipart/form-data"};
}
const auth = getAuthState();
if (auth?.apiBaseUrl) {
config.baseURL = normaliseApiBaseUrl(auth.apiBaseUrl);
}
if (auth?.token) {
(config.headers as any).Authorization = `Bearer ${auth.token}`;
}
// 中文备注扩展版本门禁API 文档要求 X-Ext-Version用于扫描相关接口
try {
const version = chrome.runtime.getManifest().version;
(config.headers as any)["X-Ext-Version"] = version;
} catch {
// ignore
}
return config;
}, (error: AxiosError) => Promise.reject(error));
// 响应拦截器
service.interceptors.response.use((response: AxiosResponse) => {
const {code, data} = response.data || {};
// 中文备注:与网站端一致,成功码统一返回 data
if ([1, "200"].includes(code)) {
return data;
}
// 中文备注:当为文件流时直接返回(保留网站端兜底逻辑)
if ((response.headers as any)?.["content-types"] === "application/octet-stream") {
return response.data;
}
return Promise.reject(response.data);
}, (error: any) => {
if (error?.message === "Network Error") {
// 中文备注:这里不弹 Toast避免扩展侧打扰需要的话在 UI 层处理
}
return Promise.reject(error);
});
function normaliseApiBaseUrl(apiBaseUrl: string) {
const raw = String(apiBaseUrl || "").replace(/\/$/, "");
if (!raw) return "";
return raw.endsWith("/api") ? raw : `${raw}/api`;
}
function requestPost(url: string, data: any = {}, config: AxiosRequestConfig = {}) {
return service.post(url, data, config);
}
function requestPatch(url: string, data: any = {}, config: AxiosRequestConfig = {}) {
return service.patch(url, data, config);
}
function requestGet(url: string, params: any = {}) {
return service.get(url, {params});
}
function requestDelete(url: string, data: any = {}) {
return service.delete(url, {data});
}
const request = {
get: requestGet,
post: requestPost,
delete: requestDelete,
patch: requestPatch,
};
export default request;

57
src/shared/store.ts Normal file
View File

@@ -0,0 +1,57 @@
/**
* 扩展侧的本地“状态仓库”(轻量版)。
* 中文备注:
* - axios 拦截器需要同步读取 token/apiBaseUrl所以这里维护一份内存态 authState。
* - 真实持久化仍然落在 chrome.storage.local确保扩展重启后可恢复。
* - 按需求:不要定义一堆类型,这里统一用 any。
*/
const AUTH_STATE_KEY = "auth_state";
let authState: any = null;
/**
* 同步读取内存态 authState给 axios 拦截器使用)。
*/
export function getAuthState() {
return authState;
}
/**
* 从 chrome.storage.local 初始化 authState建议在 background 启动时调用一次)。
*/
export async function initAuthState() {
if (typeof chrome === "undefined" || !chrome.storage?.local) {
return null;
}
const result = await chrome.storage.local.get(AUTH_STATE_KEY);
authState = result?.[AUTH_STATE_KEY] ?? null;
return authState;
}
/**
* 写入 authState内存 + 持久化)。
* 中文备注:配对成功后会在这里保存 extension token、apiBaseUrl、brand/store 等上下文。
*/
export async function setAuthState(next: any) {
authState = next ?? null;
if (typeof chrome === "undefined" || !chrome.storage?.local) {
return;
}
if (authState) {
await chrome.storage.local.set({[AUTH_STATE_KEY]: authState});
} else {
await chrome.storage.local.remove(AUTH_STATE_KEY);
}
}
/**
* 清空登录态(等价于退出登录)。
*/
export async function clearAuthState() {
await setAuthState(null);
}

34
src/shared/tab.ts Normal file
View File

@@ -0,0 +1,34 @@
/**
* 后台发给网页Tab的消息行为
*/
export type TabAction =
/** 任务状态更新(进度、状态改变等) */
| 'CRAWL_STATE_UPDATE'
/** 任务发生错误 */
| 'CRAWL_ERROR'
/** 任务完成 */
| 'CRAWL_COMPLETED';
/**
* 后台发给网页的消息格式
*/
interface TabMessage<T = unknown> {
action: TabAction;
payload?: T;
}
/**
* 发送消息给特定的标签页(由后台调用)
*/
export function sendTabMessage<T>(tabId: number, action: TabAction, payload?: T): void {
if (typeof chrome === 'undefined' || !chrome.tabs?.sendMessage) {
return;
}
const message: TabMessage<T> = {action, payload};
chrome.tabs.sendMessage(tabId, message).catch((err) => {
// 这里的错误通常是因为 Tab 被关闭了或者页面刷新了,属于正常现象
console.warn(`[Message] Failed to send ${action} to tab ${tabId}:`, err);
});
}

View File

@@ -0,0 +1,9 @@
/**
* 秒格式化成 00:00
* @param totalSeconds
*/
export function formatSeconds(totalSeconds: number): string {
const minutes = Math.floor(totalSeconds / 60).toString().padStart(2, '0');
const seconds = (totalSeconds % 60).toString().padStart(2, '0');
return `${minutes}:${seconds}`;
}

View File

@@ -1,45 +1,55 @@
/** // 单个爬取步骤的执行状态。
* 单个爬取步骤的执行状态。
*/
export type CrawlStepStatus = 'pending' | 'running' | 'success' | 'failed'; export type CrawlStepStatus = 'pending' | 'running' | 'success' | 'failed';
/** // 整体爬取任务状态。
* 整体爬取任务状态。 export type CrawlTaskStatus = 'running' | 'paused' | 'completed' | 'failed' | 'canceled';
*/
export type CrawlTaskStatus = 'running' | 'completed' | 'failed' | 'canceled';
/** // 时间轴中的单个爬取步骤进度。
* 时间轴中的单个爬取步骤进度。
*/
export interface CrawlProgressStep { export interface CrawlProgressStep {
/** 步骤名称,用于展示给用户。 */ // 步骤名称,用于展示给用户。
name: string; name: string;
/** 步骤唯一标识,对应平台配置 steps 中的 uniqueKey。 */ // 步骤唯一标识,对应平台配置 steps 中的 uniqueKey。
uniqueKey: string; uniqueKey: string;
/** 当前步骤执行状态。 */ // 当前步骤执行状态。
status: CrawlStepStatus; status: CrawlStepStatus;
/** 状态补充说明,如失败原因。 */ // 状态补充说明,如失败原因。
message?: string; message?: string;
// 当前步骤抓取到的数据结果。
result?: unknown;
}
// 爬取暂停原因,通常由登录、验证码或页面不存在触发。
export interface CrawlPauseInfo {
// 暂停原因编码。
reason: 'reauth' | 'shield' | 'not_found' | 'page_not_ready' | 'window_closed';
// 展示给用户看的处理提示。
message: string;
} }
/** /**
* 当前正在执行的爬取任务快照,供 popup 和 content script 同步展示。 * 当前正在执行的爬取任务快照,供 popup 和 content script 同步展示。
*/ */
export interface CrawlTaskState { export interface CrawlTaskState {
/** 任务唯一标识。 */ // 任务唯一标识。
id: string; id: string;
/** 当前爬取平台 ID。 */ // 当前爬取平台 ID。
platformId: string; platformId: string;
/** 当前爬取平台名称。 */ // 当前爬取平台名称。
platformName: string; platformName: string;
/** 爬取窗口 ID由 background 创建窗口后写入。 */ // 爬取窗口 ID由 background 创建窗口后写入。
windowId?: number; windowId?: number;
/** 任务开始时间戳。 */ // 爬取窗口内承载任务的 tab ID用于只在扫描 tab 显示 overlay
tabId?: number;
// 终态时自动关窗的截止时间戳ms。null 表示保持打开undefined 表示未启用。
autocloseAt?: number | null;
// 任务开始时间戳。
startedAt: number; startedAt: number;
/** 当前任务状态。 */ // 当前任务状态。
status: CrawlTaskStatus; status: CrawlTaskStatus;
/** 当前执行到的步骤下标。 */ // 暂停信息;仅 status 为 paused 时存在。
pause?: CrawlPauseInfo;
// 当前执行到的步骤下标。
currentStepIndex: number; currentStepIndex: number;
/** 平台 steps 映射出的时间轴进度。 */ // 平台 steps 映射出的时间轴进度。
steps: CrawlProgressStep[]; steps: CrawlProgressStep[];
} }

View File

@@ -1,4 +1,5 @@
export type { export type {
CrawlPauseInfo,
CrawlProgressStep, CrawlProgressStep,
CrawlStepStatus, CrawlStepStatus,
CrawlTaskState, CrawlTaskState,

View File

@@ -1,100 +1,76 @@
/** // 字段采集类型0 普通元素默认1 列表2 表格(带分页)。
* 字段采集类型0 普通元素默认1 列表2 表格(带分页)。
*/
export type PlatformFieldType = 0 | 1 | 2; export type PlatformFieldType = 0 | 1 | 2;
/** // 条件点击配置,用于进入某个页面或采集某个字段前按顺序点击页面元素。
* 条件点击配置,用于进入某个页面或采集某个字段前按顺序点击页面元素。
*/
export interface PlatformClickCondition { export interface PlatformClickCondition {
/** 需要点击的元素选择器列表,会按数组顺序依次执行。 */ // 需要点击的元素选择器列表,会按数组顺序依次执行。
list: string[]; list: string[];
/** 点击后的等待时间,单位毫秒。 */ // 点击后的等待时间,单位毫秒。
time: number; time: number;
} }
/** // 分页配置,用于列表或表格字段存在翻页时控制下一页采集。
* 分页配置,用于列表或表格字段存在翻页时控制下一页采集。
*/
export interface PlatformPaginationConfig { export interface PlatformPaginationConfig {
/** 下一页按钮的 CSS 选择器。 */ // 下一页按钮的 CSS 选择器。
nextBtn: string; nextBtn: string;
/** 最多采集页数,避免无限翻页。 */ // 最多采集页数,避免无限翻页。
maxPage?: number; maxPage?: number;
/** 每次翻页后的等待时间,单位毫秒。 */ // 每次翻页后的等待时间,单位毫秒。
delay?: number; delay?: number;
/** 下一页按钮不可用时的 class 名称。 */ // 下一页按钮不可用时的 class 名称。
disabledClass?: string; disabledClass?: string;
} }
/** // 表格分段配置,用于兼容一个数据块由多个 table 或多个 table 片段组成的情况。
* 表格分段配置,用于兼容一个数据块由多个 table 或多个 table 片段组成的情况。
*/
export interface PlatformTablePartConfig { export interface PlatformTablePartConfig {
/** 当前 table 或表格片段的名称。 */
label: string;
/** 当前 table 或表格片段的兼容名称,兼容 message.js 中的 name 写法。 */
name?: string; name?: string;
/** 当前 table 或表格片段的 CSS 选择器。 */
className: string;
/** 当前 table 或表格片段的兼容选择器,兼容 message.js 中的 select 写法。 */
select?: string; select?: string;
/** 行元素选择器,不填时由采集逻辑使用默认行选择器。 */
rowSelector?: string;
/** 当前 table 或表格片段下需要采集的字段。 */
keys?: PlatformFieldConfig[];
} }
/** // 页面字段配置,描述一个普通元素、列表元素或表格元素如何从 DOM 中提取数据。
* 页面字段配置,描述一个普通元素、列表元素或表格元素如何从 DOM 中提取数据。
*/
export interface PlatformFieldConfig { export interface PlatformFieldConfig {
/** 字段显示名,也是最终打印数据中的键名。 */ // 字段显示名,也是最终打印数据中的键名。
label: string; label: string;
/** 字段对应的 CSS 选择器。 */ // 字段对应的 CSS 选择器。
className: string; className: string;
/** 需要提取的属性名;不填时默认提取文本,图片和链接会自动取 src/href。 */ // 需要提取的属性名;不填时默认提取文本,图片和链接会自动取 src/href。
attr?: string; attr?: string;
/** 表格字段所属的表格分段名称,用于横向拼接多 table 行数据。 */ // 表格字段所属的表格分段名称,用于横向拼接多 table 行数据。
part?: string; part?: string;
/** 字段类型0 普通元素默认1 列表2 表格。 */ // 字段类型0 普通元素默认1 列表2 表格。
type?: PlatformFieldType; type?: PlatformFieldType;
/** 进入该字段采集前需要执行的点击条件。 */ // 进入该字段采集前需要执行的点击条件。
condition?: PlatformClickCondition; condition?: PlatformClickCondition;
/** 子元素字段;普通元素下表示嵌套键值,列表或表格下表示每项/每行的字段。 */ // 子元素字段;普通元素下表示嵌套键值,列表或表格下表示每项/每行的字段。
keys?: PlatformFieldConfig[]; keys?: PlatformFieldConfig[];
/** 表格专用配置,用于多个 table 或分段 table 的组合采集。 */ // 表格专用配置,用于多个 table 或分段 table 的组合采集。
tableParts?: PlatformTablePartConfig[]; tableParts?: PlatformTablePartConfig[];
/** 分页配置,常用于列表和表格字段。 */ // 分页配置,常用于列表和表格字段。
pagination?: PlatformPaginationConfig; pagination?: PlatformPaginationConfig;
} }
/** // 单个抓取页面步骤配置,描述页面地址、可用性检查和需要采集的字段。
* 单个抓取页面步骤配置,描述页面地址、可用性检查和需要采集的字段。
*/
export interface PlatformStepConfig { export interface PlatformStepConfig {
/** 步骤显示名,用于进度展示。 */ // 步骤显示名,用于进度展示。
name: string; name: string;
/** 步骤唯一标识,用于状态记录和结果归类。 */ // 步骤唯一标识,用于状态记录和结果归类。
uniqueKey: string; uniqueKey: string;
/** 当前步骤需要打开或跳转到的页面地址。 */ // 当前步骤需要打开或跳转到的页面地址。
url: string; url: string;
/** 判断页面 DOM 是否加载完成的 CSS 选择器。 */ // 判断页面 DOM 是否加载完成的 CSS 选择器。
checkSelector: string; checkSelector: string;
/** 当前页面需要采集的字段列表。 */ // 当前页面需要采集的字段列表。
fields: PlatformFieldConfig[]; fields: PlatformFieldConfig[];
/** 进入该步骤前需要执行的点击条件。 */ // 进入该步骤前需要执行的点击条件。
condition?: PlatformClickCondition; condition?: PlatformClickCondition;
} }
/** // 平台抓取配置,描述一个商家后台平台的入口地址和页面抓取顺序。
* 平台抓取配置,描述一个商家后台平台的入口地址和页面抓取顺序。
*/
export interface PlatformConfig { export interface PlatformConfig {
/** 平台唯一标识,用于 popup 选择和后台任务定位。 */ // 平台唯一标识,用于 popup 选择和后台任务定位。
id: string; id: string;
/** 平台显示名称。 */ // 平台显示名称。
name: string; name: string;
/** 当前平台的页面抓取顺序。 */ // 当前平台的页面抓取顺序。
steps: PlatformStepConfig[]; steps: PlatformStepConfig[];
} }

52
step.md
View File

@@ -1,52 +0,0 @@
# 项目结构
```angular2html
src:.
├─assets # 静态资源目录
│ vite.svg # 这里的资源通常用于图标、Logo 或扩展程序内部引用的图片
├─background # 后台脚本 (Background Script / Service Worker)
│ index.ts # 扩展的“大脑”,常驻后台运行,处理事件监听、报文转发、存储管理等
├─config # 配置目录
│ platforms.ts # 自定义配置,各种平台(如不同网站、不同浏览器)的适配配置
├─content # 内容脚本 (Content Script)
│ │ App.vue # 注入到网页中的 UI 组件(通常用于在目标页面侧边栏或浮窗显示界面)
│ │ main.ts # 内容脚本的入口文件,负责将 Vue 组件挂载到宿主页面的 DOM 中
│ │
│ └─views # 内容脚本相关的子视图或组件
├─options # 选项页 (Options Page)
│ App.vue # 扩展设置页面的 UI右键扩展图标点击“选项”打开的页面
│ index.html # 选项页的 HTML 宿主文件
│ main.ts # 选项页的 Vue 入口文件
├─popup # 弹窗页 (Popup Page)
│ App.vue # 点击扩展图标时显示的弹出框 UI
│ index.html # 弹窗页的 HTML 宿主文件
│ main.ts # 弹窗页的 Vue 入口文件
├─shared # 共享代码库 (Shared)
│ # 存放被 background、content、popup 等多个模块共同引用的工具函数、常量、API封装等
└─types # 类型定义目录
index.ts # 存放全局的 TypeScript 接口Interface和类型Type定义
```
# 开发步骤
1.在popup模块中的App.vue中用tailwindcss编写点击扩展图标时出现的弹窗逻辑如下
- 在未登录情况下即storage中token字段是否存在如果不存在弹窗内容只用显示扩展名字、描述、请登录按钮底部扩展版本
- 当点击登录按钮后先模拟登录写死token之后ui如下
- 显示扩展名字、描述、一个平台选择框通过读取config/platforms.ts)的内容for循环显示平台、扫描按钮、最底部Row退出按钮扩展版本号
- 注意token的存储和获取逻辑放到/shared/auth.ts中去如果涉及到接口和枚举的定义请判断是否是全局类型
- 如果是该类型写到一个新文件中并放到types/下如果不是放到当前模块的types/目录下(如果没用,新建)
2.前提当1完成后点击popup的立即爬取已经可以打开一个新的窗口了
- 在所有网页(包括新打开的窗口和所有网页)的右下角都放一个圆形正计时(表示正在爬取中)
- 点击圆形正计时时出现一个popup内容如下
- 以时间轴的形式表示当前爬取进度根据platforms.ts中的steps
- 同时点击扩展的popup里的内容也变得和上面的时间轴内容一致显示爬取进度隐藏立即爬取等按钮
3.前提1和2都已完成ui和交互操作上ok
- 开始爬取网页中的数据查看message.js内容吧里面的爬取方法都提取出来放到background/domScraper.ts中去
- 基于2每次根据steps打开一个新网页后根据它的fields数组字段调用domScraper中的方法来提取数据并打印到控制台即可

View File

@@ -15,7 +15,7 @@
"@crxjs/vite-plugin/client", "@crxjs/vite-plugin/client",
"chrome" "chrome"
], ],
"allowImportingTsExtensions": true, "allowImportingTsExtensions": false,
"allowJs": true, "allowJs": true,
"strict": true, "strict": true,
"strictNullChecks": true, "strictNullChecks": true,

View File

@@ -1 +1 @@
{"root":["./manifest.config.ts","./message.js","./vite.config.ts","./src/background/domscraper.ts","./src/background/index.ts","./src/background/service.ts","./src/background/types.ts","./src/background/service/crawl.ts","./src/background/service/lifecycle.ts","./src/background/service/state.ts","./src/background/service/tab.ts","./src/config/platforms.ts","./src/content/app.vue","./src/content/main.ts","./src/options/app.vue","./src/options/main.ts","./src/popup/app.vue","./src/popup/main.ts","./src/shared/auth.ts","./src/types/crawl.ts","./src/types/index.ts","./src/types/platform.ts"],"version":"5.9.3"} {"root":["./manifest.config.ts","./message.js","./vite.config.ts","./src/config.ts","./src/api/me.ts","./src/api/scan.ts","./src/background/domscraper.ts","./src/background/index.ts","./src/background/types.ts","./src/background/service/autoscanscheduler.ts","./src/background/service/externalbridge.ts","./src/background/service/scan_payload.ts","./src/background/task/crawltask.ts","./src/background/task/helper.ts","./src/background/task/taskstate.ts","./src/config/platforms.ts","./src/content/app.vue","./src/content/crawloverlay.ts","./src/content/main.ts","./src/content/pagerunner.ts","./src/options/app.vue","./src/options/main.ts","./src/popup/app.vue","./src/popup/main.ts","./src/popup/hook/use-i18n.ts","./src/popup/hook/use-login.ts","./src/popup/hook/use-scan.ts","./src/shared/auth.ts","./src/shared/message.ts","./src/shared/request.ts","./src/shared/store.ts","./src/shared/tab.ts","./src/shared/time_format.ts","./src/types/crawl.ts","./src/types/index.ts","./src/types/platform.ts"],"version":"5.9.3"}

View File

@@ -3,7 +3,7 @@ import {crx} from '@crxjs/vite-plugin'
import tailwindcss from '@tailwindcss/vite' import tailwindcss from '@tailwindcss/vite'
import vue from '@vitejs/plugin-vue' import vue from '@vitejs/plugin-vue'
import {defineConfig} from 'vite' import {defineConfig} from 'vite'
import manifest from './manifest.config.ts' import manifest from './manifest.config'
export default defineConfig({ export default defineConfig({
resolve: { resolve: {