{"id":15009885,"url":"https://github.com/desion/tidy_page","last_synced_at":"2025-06-19T04:08:22.109Z","repository":{"id":57417569,"uuid":"82539193","full_name":"desion/tidy_page","owner":"desion","description":"It is a html parser.Given a html document,It can get the content from the document. 给定一个网页提取网页中的正文内容和标题，用于网页解析、内容提取","archived":false,"fork":false,"pushed_at":"2017-05-31T06:08:13.000Z","size":29,"stargazers_count":5,"open_issues_count":1,"forks_count":4,"subscribers_count":2,"default_branch":"master","last_synced_at":"2025-06-19T04:08:15.730Z","etag":null,"topics":["html","parser","python2","spider"],"latest_commit_sha":null,"homepage":null,"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/desion.png","metadata":{"files":{"readme":"README.rst","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":"2017-02-20T09:21:25.000Z","updated_at":"2021-09-14T07:52:43.000Z","dependencies_parsed_at":"2022-08-30T17:00:56.757Z","dependency_job_id":null,"html_url":"https://github.com/desion/tidy_page","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/desion/tidy_page","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/desion%2Ftidy_page","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/desion%2Ftidy_page/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/desion%2Ftidy_page/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/desion%2Ftidy_page/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/desion","download_url":"https://codeload.github.com/desion/tidy_page/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/desion%2Ftidy_page/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":260684179,"owners_count":23046103,"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":["html","parser","python2","spider"],"created_at":"2024-09-24T19:29:01.536Z","updated_at":"2025-06-19T04:08:22.049Z","avatar_url":"https://github.com/desion.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# tidy_page\nIt is a html parser.Given a html document,It can get the content from the document. 给定一个网页提取网页中的正文内容和标题，用于网页解析、内容提取\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdesion%2Ftidy_page","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fdesion%2Ftidy_page","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdesion%2Ftidy_page/lists"}