{"id":20599286,"url":"https://github.com/sonhm3029/crawl-data-bot","last_synced_at":"2026-03-08T07:33:21.645Z","repository":{"id":210733328,"uuid":"725177296","full_name":"sonhm3029/Crawl-data-bot","owner":"sonhm3029","description":"This project making a base crawl data from web bot, include text data and images data","archived":false,"fork":false,"pushed_at":"2024-06-23T11:13:36.000Z","size":610,"stargazers_count":1,"open_issues_count":0,"forks_count":1,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-03-06T15:36:16.806Z","etag":null,"topics":["crawler","google","medical","vietnamese"],"latest_commit_sha":null,"homepage":"","language":"HTML","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/sonhm3029.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}},"created_at":"2023-11-29T15:42:57.000Z","updated_at":"2024-06-23T11:13:39.000Z","dependencies_parsed_at":"2024-06-23T12:28:12.379Z","dependency_job_id":"c20e6ec0-8977-4dba-bfeb-c492bc0a103e","html_url":"https://github.com/sonhm3029/Crawl-data-bot","commit_stats":null,"previous_names":["sonhm3029/crawl-data-bot"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/sonhm3029/Crawl-data-bot","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sonhm3029%2FCrawl-data-bot","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sonhm3029%2FCrawl-data-bot/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sonhm3029%2FCrawl-data-bot/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sonhm3029%2FCrawl-data-bot/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/sonhm3029","download_url":"https://codeload.github.com/sonhm3029/Crawl-data-bot/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sonhm3029%2FCrawl-data-bot/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":30248964,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-03-08T05:41:50.788Z","status":"ssl_error","status_checked_at":"2026-03-08T05:41:39.075Z","response_time":56,"last_error":"SSL_read: 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":["crawler","google","medical","vietnamese"],"created_at":"2024-11-16T08:32:15.364Z","updated_at":"2026-03-08T07:33:21.628Z","avatar_url":"https://github.com/sonhm3029.png","language":"HTML","funding_links":[],"categories":[],"sub_categories":[],"readme":"\"# Crawl-data-bot\"\n\nReference:\n\n![https://stackoverflow.com/questions/67249348/how-to-scrape-high-resolution-images-from-google-images-using-bs4-in-python](https://stackoverflow.com/questions/67249348/how-to-scrape-high-resolution-images-from-google-images-using-bs4-in-python)\n\n## Vinmec URL list\n\n- https://www.vinmec.com/vi/tin-tuc/thong-tin-suc-khoe/san-phu-khoa-va-ho-tro-sinh-san/\n\n- https://www.vinmec.com/vi/tin-tuc/thong-tin-suc-khoe/nhi/\n\n- https://www.vinmec.com/vi/tin-tuc/thong-tin-suc-khoe/suc-khoe-tong-quat/\n\n- https://www.vinmec.com/vi/tin-tuc/thong-tin-suc-khoe/te-bao-goc-cong-nghe-gen/\n\n- https://www.vinmec.com/vi/tin-tuc/thong-tin-suc-khoe/dich-2019-ncov/\n\n- https://www.vinmec.com/tin-tuc/thong-tin-suc-khoe/dinh-duong/\n\n- https://www.vinmec.com/tin-tuc/thong-tin-suc-khoe/song-khoe/\n\n- https://www.vinmec.com/tin-tuc/thong-tin-suc-khoe/lam-dep/\n\n- https://www.vinmec.com/tin-tuc/thong-tin-suc-khoe/thong-tin-duoc/\n\n\u003c!-- ERROR --\u003e\n\n{\n\"url\": \"https://www.vinmec.com/tin-tuc/thong-tin-suc-khoe/song-khoe/\",\n\"num_pages\": 169,\n\"category\": \"Sống khỏe\"\n},\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsonhm3029%2Fcrawl-data-bot","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fsonhm3029%2Fcrawl-data-bot","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsonhm3029%2Fcrawl-data-bot/lists"}