{"id":22788489,"url":"https://github.com/darsan-in/job-crawler","last_synced_at":"2026-02-14T00:32:37.415Z","repository":{"id":265027187,"uuid":"689286939","full_name":"darsan-in/Job-Crawler","owner":"darsan-in","description":"The Job Crawler is an integral component of the Job RAID project, designed to automatically scrape and collect data from various job listing websites. This crawler enables Job RAID to aggregate comprehensive job listings, ensuring that users have access to up-to-date and relevant job opportunities.","archived":false,"fork":false,"pushed_at":"2024-11-10T07:45:58.000Z","size":7158,"stargazers_count":3,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-04-15T22:46:55.999Z","etag":null,"topics":["automated-job-listings","crawler-integration","data-extraction","data-gathering","job-aggregator","job-crawler","job-data","job-data-collection","job-data-miner","job-listing-crawler","job-portal-scraping","job-scraping","job-scraping-tool","job-search-automation","job-search-engine","multi-site-job-scraping","real-time-job-data","scraping-jobs","web-crawler","web-scraping"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/darsan-in.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","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}},"created_at":"2023-09-09T10:40:10.000Z","updated_at":"2024-12-04T16:44:16.000Z","dependencies_parsed_at":"2024-11-27T08:46:31.319Z","dependency_job_id":"e11a4ed5-6b24-4569-b6aa-824d94db9d8b","html_url":"https://github.com/darsan-in/Job-Crawler","commit_stats":null,"previous_names":["darsan-in/job-crawler"],"tags_count":1,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/darsan-in%2FJob-Crawler","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/darsan-in%2FJob-Crawler/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/darsan-in%2FJob-Crawler/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/darsan-in%2FJob-Crawler/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/darsan-in","download_url":"https://codeload.github.com/darsan-in/Job-Crawler/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":249181338,"owners_count":21225884,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","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":["automated-job-listings","crawler-integration","data-extraction","data-gathering","job-aggregator","job-crawler","job-data","job-data-collection","job-data-miner","job-listing-crawler","job-portal-scraping","job-scraping","job-scraping-tool","job-search-automation","job-search-engine","multi-site-job-scraping","real-time-job-data","scraping-jobs","web-crawler","web-scraping"],"created_at":"2024-12-12T01:31:47.224Z","updated_at":"2026-02-14T00:32:37.394Z","avatar_url":"https://github.com/darsan-in.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"\u003cdiv align=\"center\"\u003e\r\n\r\n# Job Crawler - Automated Job Data Extraction\r\n\r\n\u003cp id=\"intro\"\u003eThe Job Crawler is an integral component of the Job RAID project, designed to automatically scrape and collect data from various job listing websites. This crawler enables Job RAID to aggregate comprehensive job listings, ensuring that users have access to up-to-date and relevant job opportunities.\u003c/p\u003e\r\n\r\n---\r\n\r\n\u003cp\u003e\r\n\r\n\u003cspan\u003e\r\n  \u003ca href=\"https://github.com/darsan-in/Job-Crawler/commits/main\"\u003e\r\n    \u003cimg src=\"https://img.shields.io/github/last-commit/darsan-in/Job-Crawler?display_timestamp=committer\u0026style=for-the-badge\u0026label=Updated%20On\" alt=\"GitHub last commit\"/\u003e\r\n  \u003c/a\u003e\r\n\u003c/span\u003e\r\n\r\n\u003cspan\u003e\r\n  \u003ca href=\"\"\u003e\r\n    \u003cimg src=\"https://img.shields.io/github/commit-activity/m/darsan-in/Job-Crawler?style=for-the-badge\u0026label=Commit%20Activity\" alt=\"GitHub commit activity\"/\u003e\r\n  \u003c/a\u003e\r\n\u003c/span\u003e\r\n\r\n\u003c/p\u003e\r\n\r\n---\r\n\r\n\u003cp\u003e\r\n\r\n\u003cspan\u003e\r\n  \u003ca href=\"LICENSE\"\u003e\r\n    \u003cimg src=\"https://img.shields.io/github/license/darsan-in/Job-Crawler?style=for-the-badge\u0026label=License\" alt=\"GitHub License\"/\u003e\r\n  \u003c/a\u003e\r\n\u003c/span\u003e\r\n\r\n\u003cspan\u003e\r\n  \u003ca href=\"https://github.com/darsan-in/Job-Crawler/releases\"\u003e\r\n    \u003cimg src=\"https://img.shields.io/github/v/release/darsan-in/Job-Crawler?include_prereleases\u0026sort=date\u0026display_name=tag\u0026style=for-the-badge\u0026label=Latest%20Version\" alt=\"GitHub Release\"/\u003e\r\n  \u003c/a\u003e\r\n\u003c/span\u003e\r\n\r\n\u003c/p\u003e\r\n\r\n\u003cp\u003e\r\n\r\n\u003cspan\u003e\r\n  \u003ca href=\"https://www.codefactor.io/repository/github/darsan-in/Job-Crawler/issues/main\"\u003e\r\n    \u003cimg src=\"https://img.shields.io/codefactor/grade/github/darsan-in/Job-Crawler?style=for-the-badge\u0026label=Code%20Quality%20Grade\" alt=\"CodeFactor Grade\"/\u003e\r\n  \u003c/a\u003e\r\n\u003c/span\u003e\r\n\r\n\u003cspan\u003e\r\n  \u003ca href=\"\"\u003e\r\n    \u003cimg src=\"https://img.shields.io/github/stars/darsan-in/Job-Crawler?style=for-the-badge\u0026label=Stars\" alt=\"GitHub Repo stars\"/\u003e\r\n  \u003c/a\u003e\r\n\u003c/span\u003e\r\n\r\n\u003c/p\u003e\r\n\r\n---\r\n\r\n\u003c/div\u003e\r\n\r\n## Table of Contents 📝\r\n\r\n- [Features and Benefits](#features-and-benefits-)\r\n- [Use Cases](#use-cases-)\r\n- [Friendly request to users](#-friendly-request-to-users)\r\n\r\n- [License](#license-%EF%B8%8F)\r\n- [Contributing to Our Project](#contributing-to-our-project-)\r\n\r\n- [Contact Information](#contact-information)\r\n- [Credits](#credits-)\r\n\r\n## Features and Benefits ✨\r\n\r\n- Automatically scrapes job data from multiple websites\r\n- Ensures up-to-date job listings for accurate search results\r\n- Handles various job listing formats and structures\r\n- Integrates seamlessly with the Job RAID search engine\r\n- Customizable scraping parameters to focus on specific job types\r\n- Efficiently collects large volumes of job data with minimal manual intervention\r\n\r\n## Use Cases ✅\r\n\r\n- Gathering job data from multiple sources to ensure a comprehensive job search platform\r\n- Automating the process of collecting job listings, reducing manual effort\r\n- Updating job listings regularly to provide users with the latest opportunities\r\n- Customizing scraping tasks to focus on high-demand job sectors or regions\r\n- Supporting the backend infrastructure of the Job RAID search engine by supplying it with fresh data\r\n\r\n---\r\n\r\n### 🙏🏻 Friendly Request to Users\r\n\r\nEvery star on this repository is a sign of encouragement, a vote of confidence, and a reminder that our work is making a difference. If this project has brought value to you, even in the smallest way, **please consider showing your support by giving it a star.** ⭐\r\n\r\n_\"Star\" button located at the top-right of the page, near the repository name._\r\n\r\nYour star isn’t just a digital icon—it’s a beacon that tells us we're on the right path, that our efforts are appreciated, and that this work matters. It fuels our passion and drives us to keep improving, building, and sharing.\r\n\r\nIf you believe in what we’re doing, **please share this project with others who might find it helpful.** Together, we can create something truly meaningful.\r\n\r\nThank you for being part of this journey. Your support means the world to us. 🌍💖\r\n\r\n---\r\n\r\n## License ©️\r\n\r\nThis project is licensed under the [MIT](LICENSE).\r\n\r\n## Contributing to Our Project 🤝\r\n\r\nWe’re always open to contributions and fixing issues—your help makes this project better for everyone.\r\n\r\nIf you encounter any errors or issues, please don’t hesitate to [raise an issue](../../issues/new). This ensures we can address problems quickly and improve the project.\r\n\r\nFor those who want to contribute, we kindly ask you to review our [Contribution Guidelines](CONTRIBUTING) before getting started. This helps ensure that all contributions align with the project's direction and comply with our existing [license](LICENSE).\r\n\r\nWe deeply appreciate everyone who contributes or raises issues—your efforts are crucial to building a stronger community. Together, we can create something truly impactful.\r\n\r\nThank you for being part of this journey!\r\n\r\n## Contact Information\r\n\r\nFor any questions, please reach out via hello@darsan.in\r\n\r\n## Credits 🙏🏻\r\n\r\nThanks to [Vicky](https://github.com/itzvixky) for making one of the job crawlers.\r\n\r\n---\r\n\r\n\u003cp align=\"center\"\u003e\r\n\r\n\u003cspan\u003e\r\n\u003ca href=\"https://www.linkedin.com/in/darsan-in/\"\u003e\u003cimg width='45px' height='45px' src=\"https://darsan.in/readme-src/footer-icons/linkedin.png\" alt=\"Darsan at Linkedin\"\u003e\u003c/a\u003e\r\n\u003c/span\u003e\r\n\r\n\u003cspan\u003e\r\n  \u003cimg width='20px' height='20px' src=\"https://darsan.in/readme-src/footer-icons/gap.png\" alt=\"place holder image\"\u003e\r\n\u003c/span\u003e\r\n\r\n\u003cspan\u003e\r\n\u003ca href=\"https://www.youtube.com/@darsan-in\"\u003e\u003cimg width='45px' height='45px' src=\"https://darsan.in/readme-src/footer-icons/youtube.png\" alt=\"Darsan at Youtube\"\u003e\u003c/a\u003e\r\n\u003c/span\u003e\r\n\r\n\u003cspan\u003e\r\n  \u003cimg width='20px' height='20px' src=\"https://darsan.in/readme-src/footer-icons/gap.png\" alt=\"place holder image\"\u003e\r\n\u003c/span\u003e\r\n\r\n\u003cspan\u003e\r\n\u003ca href=\"https://www.npmjs.com/~darsan.in\"\u003e\u003cimg width='45px' height='45px' src=\"https://darsan.in/readme-src/footer-icons/npm.png\" alt=\"Darsan at NPM\"\u003e\u003c/a\u003e\r\n\u003c/span\u003e\r\n\r\n\u003cspan\u003e\r\n  \u003cimg width='20px' height='20px' src=\"https://darsan.in/readme-src/footer-icons/gap.png\" alt=\"place holder image\"\u003e\r\n\u003c/span\u003e\r\n\r\n\u003cspan\u003e\r\n\u003ca href=\"https://github.com/darsan-in\"\u003e\u003cimg width='45px' height='45px' src=\"https://darsan.in/readme-src/footer-icons/github.png\" alt=\"Darsan at Github\"\u003e\u003c/a\u003e\r\n\u003c/span\u003e\r\n\r\n\u003cspan\u003e\r\n  \u003cimg width='20px' height='20px' src=\"https://darsan.in/readme-src/footer-icons/gap.png\" alt=\"place holder image\"\u003e\r\n\u003c/span\u003e\r\n\r\n\u003cspan\u003e\r\n\u003ca href=\"https://darsan.in/\"\u003e\u003cimg width='45px' height='45px' src=\"https://darsan.in/readme-src/footer-icons/website.png\" alt=\"Darsan Website\"\u003e\u003c/a\u003e\r\n\u003c/span\u003e\r\n\r\n\u003cp\u003e\r\n\r\n---\r\n\r\n#### Topics\r\n\r\n\u003cul id=\"keywords\"\u003e\r\n\u003cli\u003ejob crawler\u003c/li\u003e\r\n\u003cli\u003eweb scraping\u003c/li\u003e\r\n\u003cli\u003ejob scraping\u003c/li\u003e\r\n\u003cli\u003edata extraction\u003c/li\u003e\r\n\u003cli\u003eautomated job listings\u003c/li\u003e\r\n\u003cli\u003ejob data collection\u003c/li\u003e\r\n\u003cli\u003ejob aggregator\u003c/li\u003e\r\n\u003cli\u003ejob search automation\u003c/li\u003e\r\n\u003cli\u003eweb crawler\u003c/li\u003e\r\n\u003cli\u003ejob search engine\u003c/li\u003e\r\n\u003cli\u003ereal-time job data\u003c/li\u003e\r\n\u003cli\u003edata gathering\u003c/li\u003e\r\n\u003cli\u003escraping jobs\u003c/li\u003e\r\n\u003cli\u003ejob portal scraping\u003c/li\u003e\r\n\u003cli\u003ejob listing crawler\u003c/li\u003e\r\n\u003cli\u003ejob data\u003c/li\u003e\r\n\u003cli\u003ecrawler integration\u003c/li\u003e\r\n\u003cli\u003ejob scraping tool\u003c/li\u003e\r\n\u003cli\u003ejob data miner\u003c/li\u003e\r\n\u003cli\u003emulti-site job scraping\u003c/li\u003e\r\n\u003c/ul\u003e\r\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdarsan-in%2Fjob-crawler","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fdarsan-in%2Fjob-crawler","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdarsan-in%2Fjob-crawler/lists"}