{"id":189268,"name":null,"description":"News crawling with StormCrawler - stores content as WARC","url":"https://github.com/commoncrawl/news-crawl","last_synced_at":"2025-09-10T03:38:50.122Z","repository":{"id":94107095,"uuid":"63606686","full_name":"commoncrawl/news-crawl","owner":"commoncrawl","description":"News crawling with StormCrawler - stores content as WARC","archived":false,"fork":false,"pushed_at":"2025-02-19T14:03:34.000Z","size":253,"stargazers_count":346,"open_issues_count":16,"forks_count":37,"subscribers_count":33,"default_branch":"master","last_synced_at":"2025-06-12T08:49:11.194Z","etag":null,"topics":["apache-storm","common-crawl","commoncrawl","crawler","news","storm-crawler","warc","web-crawler"],"latest_commit_sha":null,"homepage":"","language":"Java","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/commoncrawl.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,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2016-07-18T13:47:15.000Z","updated_at":"2025-05-23T19:45:02.000Z","dependencies_parsed_at":"2023-12-13T11:43:07.535Z","dependency_job_id":"1d6f575f-3df9-402e-8e01-bbd6d0da34e3","html_url":"https://github.com/commoncrawl/news-crawl","commit_stats":null,"previous_names":[],"tags_count":1,"template":false,"template_full_name":null,"purl":"pkg:github/commoncrawl/news-crawl","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/commoncrawl%2Fnews-crawl","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/commoncrawl%2Fnews-crawl/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/commoncrawl%2Fnews-crawl/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/commoncrawl%2Fnews-crawl/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/commoncrawl","download_url":"https://codeload.github.com/commoncrawl/news-crawl/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/commoncrawl%2Fnews-crawl/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":274407402,"owners_count":25279278,"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":"2025-09-10T02:00:12.551Z","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"}},"owner":{"login":"commoncrawl","name":"Common Crawl Foundation","uuid":"1194841","kind":"organization","description":"Common Crawl provides an archive of webpages going back to 2007.","email":"info@commoncrawl.org","website":"https://commoncrawl.org","location":null,"twitter":"commoncrawl","company":null,"icon_url":"https://avatars.githubusercontent.com/u/1194841?v=4","repositories_count":50,"last_synced_at":"2024-05-07T18:12:30.238Z","metadata":{"has_sponsors_listing":false},"html_url":"https://github.com/commoncrawl","funding_links":[],"total_stars":2106,"followers":290,"following":0,"created_at":"2022-11-03T05:10:17.348Z","updated_at":"2024-05-07T18:12:39.767Z","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/commoncrawl","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/commoncrawl/repositories"},"packages":[],"commits":{"id":10323876,"full_name":"commoncrawl/news-crawl","default_branch":"master","committers":[{"name":"Sebastian Nagel","email":"sebastian@commoncrawl.org","login":"sebastian-nagel","count":128},{"name":"Julien Nioche","email":"julien@digitalpebble.com","login":"jnioche","count":20}],"total_commits":148,"total_committers":2,"total_bot_commits":0,"total_bot_committers":0,"mean_commits":74.0,"dds":0.1351351351351351,"past_year_committers":[],"past_year_total_commits":0,"past_year_total_committers":0,"past_year_total_bot_commits":0,"past_year_total_bot_committers":0,"past_year_mean_commits":0.0,"past_year_dds":0.0,"last_synced_at":"2025-06-12T20:03:01.450Z","last_synced_commit":"efd0d2407acac5d7970cd915dbf114f76ccb024f","created_at":"2025-06-12T08:40:57.205Z","updated_at":"2025-06-12T20:03:01.451Z","commits_url":"https://commits.ecosyste.ms/api/v1/hosts/GitHub/repositories/commoncrawl%2Fnews-crawl/commits","host":{"name":"GitHub","url":"https://github.com","kind":"github","last_synced_at":"2025-09-10T00:25:43.995Z","repositories_count":5545114,"commits_count":878229909,"contributors_count":32458717,"owners_count":919815,"icon_url":"https://github.com/github.png","host_url":"https://commits.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://commits.ecosyste.ms/api/v1/hosts/GitHub/repositories"}},"issues_stats":{"full_name":"commoncrawl/news-crawl","html_url":"https://github.com/commoncrawl/news-crawl","last_synced_at":"2025-08-31T18:23:32.357Z","status":null,"issues_count":55,"pull_requests_count":12,"avg_time_to_close_issue":11012068.875,"avg_time_to_close_pull_request":5286574.9,"issues_closed_count":40,"pull_requests_closed_count":10,"pull_request_authors_count":3,"issue_authors_count":16,"avg_comments_per_issue":2.9454545454545453,"avg_comments_per_pull_request":1.4166666666666667,"merged_pull_requests_count":2,"bot_issues_count":0,"bot_pull_requests_count":7,"past_year_issues_count":1,"past_year_pull_requests_count":4,"past_year_avg_time_to_close_issue":null,"past_year_avg_time_to_close_pull_request":1897819.0,"past_year_issues_closed_count":0,"past_year_pull_requests_closed_count":2,"past_year_pull_request_authors_count":1,"past_year_issue_authors_count":1,"past_year_avg_comments_per_issue":0.0,"past_year_avg_comments_per_pull_request":2.0,"past_year_bot_issues_count":0,"past_year_bot_pull_requests_count":0,"past_year_merged_pull_requests_count":2,"created_at":"2024-05-07T18:08:36.261Z","updated_at":"2025-09-02T14:14:05.600Z","repository_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/repositories/commoncrawl%2Fnews-crawl","issues_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/repositories/commoncrawl%2Fnews-crawl/issues","issue_labels_count":{"bug":5,"question":5,"enhancement":3,"wontfix":1,"docker":1},"pull_request_labels_count":{"dependencies":7},"issue_author_associations_count":{"COLLABORATOR":30,"NONE":15,"CONTRIBUTOR":8},"pull_request_author_associations_count":{"NONE":11,"CONTRIBUTOR":1},"issue_authors":{"sebastian-nagel":30,"jnioche":8,"john-hewitt":2,"chris-ha458":1,"kaal-zathura24":1,"sljlp":1,"brand17":1,"randomgambit":1,"sandeepsingh":1,"fhamborg":1,"raphaelzhou1":1,"rishrockstar":1,"staylor-ds":1,"Ashbajawed":1,"zikolach":1,"scarcenine":1},"pull_request_authors":{"dependabot[bot]":7,"silentninja":4,"jnioche":1},"host":{"name":"GitHub","url":"https://github.com","kind":"github","last_synced_at":"2025-09-06T00:00:15.144Z","repositories_count":10116192,"issues_count":31648915,"pull_requests_count":98479227,"authors_count":10708464,"icon_url":"https://github.com/github.png","host_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/repositories","owners_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/owners","authors_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/authors"},"past_year_issue_labels_count":{},"past_year_pull_request_labels_count":{},"past_year_issue_author_associations_count":{"COLLABORATOR":1},"past_year_pull_request_author_associations_count":{"NONE":4},"past_year_issue_authors":{"sebastian-nagel":1},"past_year_pull_request_authors":{"silentninja":4},"maintainers":[{"login":"sebastian-nagel","count":30,"url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/authors/sebastian-nagel"}],"active_maintainers":[{"login":"sebastian-nagel","count":1,"url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/authors/sebastian-nagel"}]},"events":{"total":{"IssuesEvent":1,"WatchEvent":32,"IssueCommentEvent":19,"PushEvent":1,"PullRequestReviewEvent":6,"PullRequestReviewCommentEvent":5,"PullRequestEvent":3,"ForkEvent":5},"last_year":{"IssuesEvent":1,"WatchEvent":32,"IssueCommentEvent":19,"PushEvent":1,"PullRequestReviewEvent":6,"PullRequestReviewCommentEvent":5,"PullRequestEvent":3,"ForkEvent":5}},"keywords":["apache-storm","common-crawl","commoncrawl","crawler","news","storm-crawler","warc","web-crawler"],"dependencies":[{"ecosystem":"maven","filepath":"pom.xml","sha":null,"kind":"manifest","created_at":"2023-03-06T08:30:11.807Z","updated_at":"2023-03-06T08:30:11.807Z","repository_link":"https://github.com/commoncrawl/news-crawl/blob/master/pom.xml","dependencies":[{"id":8027524091,"package_name":"com.digitalpebble.stormcrawler:storm-crawler-core","ecosystem":"maven","requirements":"1.18","direct":true,"kind":"runtime","optional":false},{"id":8027524128,"package_name":"org.apache.storm:storm-core","ecosystem":"maven","requirements":"1.2.3","direct":true,"kind":"provided","optional":false},{"id":8027524149,"package_name":"org.apache.storm:flux-core","ecosystem":"maven","requirements":"1.2.3","direct":true,"kind":"runtime","optional":false},{"id":8027524158,"package_name":"com.digitalpebble.stormcrawler:storm-crawler-elasticsearch","ecosystem":"maven","requirements":"1.18","direct":true,"kind":"runtime","optional":false},{"id":8027524160,"package_name":"com.digitalpebble.stormcrawler:storm-crawler-warc","ecosystem":"maven","requirements":"1.18","direct":true,"kind":"runtime","optional":false},{"id":8027524162,"package_name":"com.fasterxml.jackson.core:jackson-databind","ecosystem":"maven","requirements":"2.11.1","direct":true,"kind":"runtime","optional":false},{"id":8027524163,"package_name":"com.github.crawler-commons:crawler-commons","ecosystem":"maven","requirements":"1.1","direct":true,"kind":"runtime","optional":false},{"id":8027524169,"package_name":"com.digitalpebble.stormcrawler:storm-crawler-core","ecosystem":"maven","requirements":"1.18","direct":true,"kind":"test","optional":false},{"id":8027524170,"package_name":"org.mockito:mockito-all","ecosystem":"maven","requirements":"1.10.19","direct":true,"kind":"test","optional":false},{"id":8027524175,"package_name":"com.github.tomakehurst:wiremock","ecosystem":"maven","requirements":"2.26.3","direct":true,"kind":"test","optional":false}]},{"ecosystem":"docker","filepath":"Dockerfile","sha":null,"kind":"manifest","created_at":"2023-03-06T08:30:11.531Z","updated_at":"2023-03-06T08:30:11.531Z","repository_link":"https://github.com/commoncrawl/news-crawl/blob/master/Dockerfile","dependencies":[{"id":8027523910,"package_name":"ubuntu","ecosystem":"docker","requirements":"18.04","direct":true,"kind":"build","optional":false}]},{"ecosystem":"actions","filepath":".github/workflows/maven.yml","sha":null,"kind":"manifest","created_at":"2023-11-14T17:04:25.661Z","updated_at":"2023-11-14T17:04:25.661Z","repository_link":"https://github.com/commoncrawl/news-crawl/blob/master/.github/workflows/maven.yml","dependencies":[{"id":14495870639,"package_name":"actions/checkout","ecosystem":"actions","requirements":"v2","direct":true,"kind":"composite","optional":false},{"id":14495870640,"package_name":"actions/setup-java","ecosystem":"actions","requirements":"v2","direct":true,"kind":"composite","optional":false}]}],"score":6.584791392385717,"created_at":"2025-09-09T02:58:07.680Z","updated_at":"2025-10-07T08:42:12.580Z","avatar_url":"https://github.com/commoncrawl.png","language":"Java","category":null,"sub_category":null,"monthly_downloads":0,"funding_links":[],"readme_doi_urls":[],"works":{},"citation_counts":{},"total_citations":0,"keywords_from_contributors":[],"project_url":"https://science.ecosyste.ms/api/v1/projects/189268","html_url":"https://science.ecosyste.ms/projects/189268"}