{"id":36621277,"url":"https://github.com/wxxiong6/crawl","last_synced_at":"2026-01-12T09:23:48.609Z","repository":{"id":57083087,"uuid":"65803704","full_name":"wxxiong6/crawl","owner":"wxxiong6","description":"php爬虫系统","archived":false,"fork":false,"pushed_at":"2018-09-05T10:40:40.000Z","size":334,"stargazers_count":23,"open_issues_count":1,"forks_count":14,"subscribers_count":3,"default_branch":"master","last_synced_at":"2024-04-20T05:21:10.150Z","etag":null,"topics":["crawl","php","spider"],"latest_commit_sha":null,"homepage":"","language":"PHP","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"other","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/wxxiong6.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}},"created_at":"2016-08-16T08:51:23.000Z","updated_at":"2020-04-28T08:42:59.000Z","dependencies_parsed_at":"2022-08-24T14:58:24.439Z","dependency_job_id":null,"html_url":"https://github.com/wxxiong6/crawl","commit_stats":null,"previous_names":[],"tags_count":2,"template":false,"template_full_name":null,"purl":"pkg:github/wxxiong6/crawl","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/wxxiong6%2Fcrawl","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/wxxiong6%2Fcrawl/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/wxxiong6%2Fcrawl/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/wxxiong6%2Fcrawl/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/wxxiong6","download_url":"https://codeload.github.com/wxxiong6/crawl/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/wxxiong6%2Fcrawl/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":28337705,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-01-12T06:09:07.588Z","status":"ssl_error","status_checked_at":"2026-01-12T06:05:18.301Z","response_time":98,"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":["crawl","php","spider"],"created_at":"2026-01-12T09:23:47.852Z","updated_at":"2026-01-12T09:23:48.589Z","avatar_url":"https://github.com/wxxiong6.png","language":"PHP","funding_links":[],"categories":[],"sub_categories":[],"readme":"php爬虫系统\n====\n\n* 程序只支持CLI,执行前需要把php加入环境变量\n\n# 安装程序\n\n### 1.dbconfig.php 添加正确的数据库配置\n\n### 2. 安装程序 \n```PHP\nphp run install\n```\n# 启动程序\n\n### 安装完成后，在setting表添加来源站点及正则提取规则。\n\n### 启动程序 (参数是 setting 表id)\n```PHP\nphp run run 1 \n```\n\n### 清除项目数据 (参数是 setting 表id)\n```PHP\nphp run clear 1\n ```\n\n### 完整代码目录\n```PHP\n│  crawl.sql\n│  LICENSE\n│  README\n│  run       系统入口程序\n│      \n├─code\n│  ├─config  配置文件\n│  │      config.php\n│  │      dbconfig.php\n│  │      \n│  └─library  类库\n│      │  App.php\n│      │  Crawl.php\n│      │  CrawlCallback.php\n│      │  Import.php\n│      │  Loader.php\n│      │  \n│      └─db   数据库\n│              MysqlPDO.php\n│              \n├─data   数据\n│          \n├─log    日志目录\n│      \n├─tmp\n└─web     web目录\n ```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fwxxiong6%2Fcrawl","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fwxxiong6%2Fcrawl","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fwxxiong6%2Fcrawl/lists"}