{"id":19959751,"url":"https://github.com/maxlen/webcrawler","last_synced_at":"2025-08-22T16:08:51.936Z","repository":{"id":62525672,"uuid":"74571984","full_name":"maxlen/webcrawler","owner":"maxlen","description":"Search engines crawlers","archived":false,"fork":false,"pushed_at":"2017-03-29T13:46:58.000Z","size":11,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-03-01T16:23:52.599Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"PHP","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/maxlen.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}},"created_at":"2016-11-23T11:52:50.000Z","updated_at":"2016-11-24T13:19:52.000Z","dependencies_parsed_at":"2022-11-02T14:16:01.514Z","dependency_job_id":null,"html_url":"https://github.com/maxlen/webcrawler","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/maxlen/webcrawler","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/maxlen%2Fwebcrawler","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/maxlen%2Fwebcrawler/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/maxlen%2Fwebcrawler/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/maxlen%2Fwebcrawler/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/maxlen","download_url":"https://codeload.github.com/maxlen/webcrawler/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/maxlen%2Fwebcrawler/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":271665150,"owners_count":24799302,"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","status":"online","status_checked_at":"2025-08-22T02:00:08.480Z","response_time":65,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"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":[],"created_at":"2024-11-13T01:51:21.583Z","updated_at":"2025-08-22T16:08:51.906Z","avatar_url":"https://github.com/maxlen.png","language":"PHP","funding_links":[],"categories":[],"sub_categories":[],"readme":"# webcrawler\nSearch engines crawlers\n\n### Google example:\n```\n  $proxy = []; //['host' =\u003e '*.*.*.*', 'port' =\u003e '', 'login' =\u003e '', 'password' =\u003e '']\n  $params = ['query' =\u003e 'test search', 'page' =\u003e $page, 'proxy' =\u003e $proxy];\n  $crawler = new WebCrawler(['strategy' =\u003e new GoogleSearch()]);\n  print_r($crawler-\u003ecrawl($params));\n```\n\n### Site-parse example:\n```\n  $params = ['url' =\u003e 'http://your-site.com', 'proxy' =\u003e []];\n  $crawler = new WebCrawler(['strategy' =\u003e new SiteSearch()]);\n  print_r($crawler-\u003ecrawl($params));\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmaxlen%2Fwebcrawler","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fmaxlen%2Fwebcrawler","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmaxlen%2Fwebcrawler/lists"}