feat: implement TED EU scraper with Playwright

- Add Playwright browser automation for TED EU tender scraping
- Install playwright + chromium browser dependencies
- Scraper successfully finds UK-relevant EU tenders (~11 per run)
- Uses headless Chrome with keyword filtering
- Add SCRAPERS_STATUS.md documentation

All 6 main scrapers now operational (digital-marketplace API still down).
Total active tenders: 626
This commit is contained in:
Peter Foster
2026-02-15 13:28:54 +00:00
parent 6ca3e9c576
commit 685ac00f7c
4 changed files with 296 additions and 16 deletions

45
package-lock.json generated
View File

@@ -18,6 +18,7 @@
"jsonwebtoken": "^9.0.0",
"nodemailer": "^8.0.1",
"pg": "^8.10.0",
"playwright": "^1.58.2",
"stripe": "^20.3.1"
}
},
@@ -836,6 +837,20 @@
"integrity": "sha512-OO0pH2lK6a0hZnAdau5ItzHPI6pUlvI7jMVnxUQRtw4owF2wk8lOSabtGDCTP4Ggrg2MbGnWO9X8K1t4+fGMDw==",
"license": "ISC"
},
"node_modules/fsevents": {
"version": "2.3.2",
"resolved": "https://registry.npmjs.org/fsevents/-/fsevents-2.3.2.tgz",
"integrity": "sha512-xiqMQR4xAeHTuB9uWm+fFRcIOgKBMiOBP+eXiyT7jsgVCq1bkVygt00oASowB7EdtpOHaaPgKt812P9ab+DDKA==",
"hasInstallScript": true,
"license": "MIT",
"optional": true,
"os": [
"darwin"
],
"engines": {
"node": "^8.16.0 || ^10.6.0 || >=11.0.0"
}
},
"node_modules/function-bind": {
"version": "1.1.2",
"resolved": "https://registry.npmjs.org/function-bind/-/function-bind-1.1.2.tgz",
@@ -1651,6 +1666,36 @@
"split2": "^4.1.0"
}
},
"node_modules/playwright": {
"version": "1.58.2",
"resolved": "https://registry.npmjs.org/playwright/-/playwright-1.58.2.tgz",
"integrity": "sha512-vA30H8Nvkq/cPBnNw4Q8TWz1EJyqgpuinBcHET0YVJVFldr8JDNiU9LaWAE1KqSkRYazuaBhTpB5ZzShOezQ6A==",
"license": "Apache-2.0",
"dependencies": {
"playwright-core": "1.58.2"
},
"bin": {
"playwright": "cli.js"
},
"engines": {
"node": ">=18"
},
"optionalDependencies": {
"fsevents": "2.3.2"
}
},
"node_modules/playwright-core": {
"version": "1.58.2",
"resolved": "https://registry.npmjs.org/playwright-core/-/playwright-core-1.58.2.tgz",
"integrity": "sha512-yZkEtftgwS8CsfYo7nm0KE8jsvm6i/PTgVtB8DL726wNf6H2IMsDuxCpJj59KDaxCtSnrWan2AeDqM7JBaultg==",
"license": "Apache-2.0",
"bin": {
"playwright-core": "cli.js"
},
"engines": {
"node": ">=18"
}
},
"node_modules/postgres-array": {
"version": "2.0.0",
"resolved": "https://registry.npmjs.org/postgres-array/-/postgres-array-2.0.0.tgz",