{"id":22711176,"url":"https://github.com/manzil-infinity180/website-scrapper","last_synced_at":"2026-02-27T15:39:09.450Z","repository":{"id":265962064,"uuid":"886647303","full_name":"manzil-infinity180/website-scrapper","owner":"manzil-infinity180","description":"A demo project for scrapping website using puppeteer(js/ts) and scrapy(python)","archived":false,"fork":false,"pushed_at":"2025-10-28T05:08:27.000Z","size":33570,"stargazers_count":3,"open_issues_count":2,"forks_count":1,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-10-28T07:07:03.439Z","etag":null,"topics":["internship","jobs","remote","scraping"],"latest_commit_sha":null,"homepage":"","language":"TypeScript","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/manzil-infinity180.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2024-11-11T10:59:27.000Z","updated_at":"2025-10-28T05:08:25.000Z","dependencies_parsed_at":"2025-02-04T22:37:20.316Z","dependency_job_id":null,"html_url":"https://github.com/manzil-infinity180/website-scrapper","commit_stats":null,"previous_names":["manzil-infinity180/website-scrapper"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/manzil-infinity180/website-scrapper","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/manzil-infinity180%2Fwebsite-scrapper","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/manzil-infinity180%2Fwebsite-scrapper/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/manzil-infinity180%2Fwebsite-scrapper/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/manzil-infinity180%2Fwebsite-scrapper/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/manzil-infinity180","download_url":"https://codeload.github.com/manzil-infinity180/website-scrapper/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/manzil-infinity180%2Fwebsite-scrapper/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":29901984,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-02-27T14:46:13.553Z","status":"ssl_error","status_checked_at":"2026-02-27T14:46:10.522Z","response_time":57,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.5:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["internship","jobs","remote","scraping"],"created_at":"2024-12-10T12:14:47.191Z","updated_at":"2026-02-27T15:39:09.432Z","avatar_url":"https://github.com/manzil-infinity180.png","language":"TypeScript","funding_links":[],"categories":[],"sub_categories":[],"readme":"# website-scrapper\n\n* This is just the demo project for scraping different websites and social media\n   - I am using puppeteer(javascript/typescript) with cheerio and other library or package\n   - Using scrpy(python) + with some proxy provider\n- puppeteer-extra-plugin-stealth: To make it harder for bot detection technology to detect headless browser instances.\n- puppeteer-extra-plugin-recaptcha: To solve reCAPTCHAs and hCaptchas automatically.\n- puppeteer-extra-plugin-adblocker: To remove ads and trackers, reducing bandwidth and load times as a result.\n- puppeteer-extra-plugin-devtools: To make browser debugging possible from anywhere by creating a secure tunnel to the DevTools.\n- puppeteer-extra-plugin-repl: To make debugging fun with an interactive REPL (Read-Eval-Print-Loop) interface.\n- puppeteer-extra-plugin-block-resources: To block dynamically page resources such as images, media, CSS, and JS files.\n- puppeteer-extra-plugin-anonymize-ua: To anonymize the User-Agent header on page navigation. Learn about why this is important in our guide on User-Agent for web scraping.\n- puppeteer-extra-plugin-user-preferences: To set custom Chrome/Chromium user preferences.\n\n\n## Demo - (Under Development)\n\u003e Read More\n\u003e https://www.webshare.io/academy-article/puppeteer-extra#conclusion\n\n\u003e Scrape Any **Twitter** Post\n\u003e [Click Here](https://github.com/manzil-infinity180/website-scrapper/tree/main/src/twitter)\n\n\n## See Latest YC job/internship\n\u003e [Click Here](https://github.com/manzil-infinity180/website-scrapper/tree/main/yc-daily-post)\n\u003cp align=\"center\"\u003e\n  \u003ca href=\"https://github.com/manzil-infinity180/website-scrapper/tree/main/yc-daily-post\"\u003e\n\u003cimg src=\"https://upload.wikimedia.org/wikipedia/commons/thumb/b/b2/Y_Combinator_logo.svg/1200px-Y_Combinator_logo.svg.png\" width=\"200\" /\u003e\n  \u003c/a\u003e\n\u003c/p\u003e\n\n\n\n## See Latest Javascript Remote job \n\u003e [Click Here](https://github.com/manzil-infinity180/website-scrapper/tree/main/javascript-jobs-post)\n\u003cp align=\"center\"\u003e\n  \u003ca href=\"https://github.com/manzil-infinity180/website-scrapper/tree/main/javascript-jobs-post\"\u003e\n\u003cimg src=\"https://upload.wikimedia.org/wikipedia/commons/6/6a/JavaScript-logo.png\" width=\"200\" /\u003e\n  \u003c/a\u003e\n\u003c/p\u003e\n\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmanzil-infinity180%2Fwebsite-scrapper","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fmanzil-infinity180%2Fwebsite-scrapper","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmanzil-infinity180%2Fwebsite-scrapper/lists"}