{"id":34501859,"url":"https://github.com/woojubb/html-article-extractor","last_synced_at":"2025-12-24T02:04:38.265Z","repository":{"id":57267287,"uuid":"163909305","full_name":"woojubb/html-article-extractor","owner":"woojubb","description":"A web page content extractor","archived":false,"fork":false,"pushed_at":"2024-08-13T05:30:20.000Z","size":23,"stargazers_count":21,"open_issues_count":0,"forks_count":1,"subscribers_count":0,"default_branch":"master","last_synced_at":"2025-10-20T10:36:09.839Z","etag":null,"topics":["article-extracting","article-extractor","crawler","crawling","extraction","extractor"],"latest_commit_sha":null,"homepage":null,"language":"JavaScript","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/woojubb.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":"2019-01-03T01:43:07.000Z","updated_at":"2025-08-08T18:50:11.000Z","dependencies_parsed_at":"2022-08-31T22:00:27.105Z","dependency_job_id":null,"html_url":"https://github.com/woojubb/html-article-extractor","commit_stats":null,"previous_names":["jungyoun/html-article-extractor"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/woojubb/html-article-extractor","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/woojubb%2Fhtml-article-extractor","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/woojubb%2Fhtml-article-extractor/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/woojubb%2Fhtml-article-extractor/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/woojubb%2Fhtml-article-extractor/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/woojubb","download_url":"https://codeload.github.com/woojubb/html-article-extractor/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/woojubb%2Fhtml-article-extractor/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":27992996,"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":"2025-12-24T02:00:07.193Z","response_time":83,"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":["article-extracting","article-extractor","crawler","crawling","extraction","extractor"],"created_at":"2025-12-24T02:04:37.605Z","updated_at":"2025-12-24T02:04:38.257Z","avatar_url":"https://github.com/woojubb.png","language":"JavaScript","funding_links":[],"categories":[],"sub_categories":[],"readme":"# html-article-extractor\nA web page content extractor for News websites\n\n# installation\n```javascript\nnpm install html-article-extractor\n```\n\n# usage\n```javascript\nvar htmlArticleExtractor = require(\"html-article-extractor\");\n\nvar dom = new JSDOM(\"...\");\nvar body = dom.window.document.body\nresult = htmlArticleExtractor(body);\nconsole.log(result)\n```\n\nOutputs:\n```\n{\n    html: '\u003cdiv\u003econtents\u003c/div\u003e',\n    text: 'contents'\n}\n```\n\n# example\n```\ngit clone https://github.com/jungyoun/html-article-extractor\ncd html-article-extractor\nnpm install\nnode example/crawler.js\n```\n\n# demo\nhttps://online-article-extractor.herokuapp.com/","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fwoojubb%2Fhtml-article-extractor","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fwoojubb%2Fhtml-article-extractor","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fwoojubb%2Fhtml-article-extractor/lists"}