{"id":21170285,"url":"https://github.com/harryandriyan/warta-scrap","last_synced_at":"2025-08-11T06:36:49.317Z","repository":{"id":101808267,"uuid":"101162989","full_name":"harryandriyan/warta-scrap","owner":"harryandriyan","description":"Indonesia Index News Crawler, including 10 online media","archived":false,"fork":false,"pushed_at":"2018-10-12T02:45:36.000Z","size":403,"stargazers_count":76,"open_issues_count":2,"forks_count":28,"subscribers_count":6,"default_branch":"master","last_synced_at":"2024-07-29T09:33:24.733Z","etag":null,"topics":["python","scraper","scrapy"],"latest_commit_sha":null,"homepage":"","language":"Python","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/harryandriyan.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}},"created_at":"2017-08-23T09:30:16.000Z","updated_at":"2024-07-13T06:32:28.000Z","dependencies_parsed_at":"2024-01-07T04:50:25.579Z","dependency_job_id":null,"html_url":"https://github.com/harryandriyan/warta-scrap","commit_stats":null,"previous_names":[],"tags_count":1,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/harryandriyan%2Fwarta-scrap","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/harryandriyan%2Fwarta-scrap/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/harryandriyan%2Fwarta-scrap/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/harryandriyan%2Fwarta-scrap/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/harryandriyan","download_url":"https://codeload.github.com/harryandriyan/warta-scrap/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":225587772,"owners_count":17492632,"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":["python","scraper","scrapy"],"created_at":"2024-11-20T15:57:54.248Z","updated_at":"2024-11-20T15:57:54.842Z","avatar_url":"https://github.com/harryandriyan.png","language":"Python","funding_links":[],"categories":["Speech recognition"],"sub_categories":[],"readme":"# warta-scrap\nIndonesia Index News Crawler, including 10 online\n\n### Online Media List:\n- Detik.com\n  http://news.detik.com/indeks\n- Republika.co.id\n  http://www.republika.co.id/indeks\n- Viva.co.id\n  http://www.viva.co.id/indeks\n- Kompas.com \n  http://indeks.kompas.com/\n- Antaranews.com\n  http://www.antaranews.com/terkini\n- Tempo.co\n  https://www.tempo.co/indeks\n- Okezone.com\n  http://index.okezone.com/\n- Liputan6.com\n  http://www.liputan6.com/indeks\n- Merdeka.com\n  https://www.merdeka.com/berita-hari-ini/\n- Tirto.id\n  https://tirto.id/indeks\n\n### Installation :\nOpen Terminal, and clone this repo:  \n\u003e git clone https://github.com/harryandriyan/warta-scrap\n\nGo to project folder\n\u003e cd warta-scrap\n\nSetup virtualenv\n\u003e virtualenv venv\n\nActivate virtualenv\n\u003e . venv/bin/activate\n\nInstall requirements\n\u003e pip install -r requirements.txt\n\n### How to use\nOpen the specific project, example\n\u003e cd republika\n\nRun crawl command, example\n\u003e scrapy crawl republika -o sampleResult.json -t json","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fharryandriyan%2Fwarta-scrap","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fharryandriyan%2Fwarta-scrap","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fharryandriyan%2Fwarta-scrap/lists"}