feat: add Google Jobs extractor and fix scraper reliability gaps
CI / skip-ci-check (pull_request) Successful in 8s
CI / docker-ci (pull_request) Successful in 10s
CI / secret-scan (pull_request) Successful in 7s

Ship a Camoufox-backed Google Jobs source, restore Glassdoor results discarded by a python-jobspy GraphQL quirk, and fix Himalayas/Gradcracker zero-job failures. Also harden prior-skip dismiss matching and multi-profile basic-auth switching for CA/US runs.
This commit is contained in:
2026-07-09 15:11:53 -04:00
parent 84e6835b11
commit 40c7cdece3
47 changed files with 1989 additions and 87 deletions
+35
View File
@@ -336,6 +336,37 @@
"undici-types": "~7.16.0"
}
},
"extractors/google-jobs": {
"name": "google-jobs-extractor",
"version": "0.0.1",
"dependencies": {
"camoufox-js": "^0.8.0",
"job-ops-shared": "^1.0.0",
"playwright": "^1.57.0",
"tsx": "^4.4.0"
},
"devDependencies": {
"@types/node": "^24.0.0",
"typescript": "~5.9.0"
}
},
"extractors/google-jobs/node_modules/@types/node": {
"version": "24.13.3",
"resolved": "https://registry.npmjs.org/@types/node/-/node-24.13.3.tgz",
"integrity": "sha512-Dh8vAsV36ig5wa9OX4pXvMc9D3Veibfw2wix0CUwYODLD8nkj9UsLjASr49nPg+2eKzxhBV+v7L8pXvT4e639Q==",
"dev": true,
"license": "MIT",
"dependencies": {
"undici-types": "~7.18.0"
}
},
"extractors/google-jobs/node_modules/undici-types": {
"version": "7.18.2",
"resolved": "https://registry.npmjs.org/undici-types/-/undici-types-7.18.2.tgz",
"integrity": "sha512-AsuCzffGHJybSaRrmr5eHr81mwJU3kjw6M+uprWvCXiNeN9SOGwQ3Jn8jb8m3Z6izVgknn1R0FTCEAP2QrLY/w==",
"dev": true,
"license": "MIT"
},
"extractors/gradcracker": {
"name": "gradcracker-extractor",
"version": "0.0.1",
@@ -14253,6 +14284,10 @@
"url": "https://github.com/sponsors/sindresorhus"
}
},
"node_modules/google-jobs-extractor": {
"resolved": "extractors/google-jobs",
"link": true
},
"node_modules/gopd": {
"version": "1.2.0",
"resolved": "https://registry.npmjs.org/gopd/-/gopd-1.2.0.tgz",