{"id":189242,"name":null,"description":"A whirlwind tour of Common Crawl's data using Python","url":"https://github.com/commoncrawl/whirlwind-python","last_synced_at":"2025-09-10T03:37:37.977Z","repository":{"id":245649934,"uuid":"818861054","full_name":"commoncrawl/whirlwind-python","owner":"commoncrawl","description":"A whirlwind tour of Common Crawl's data using Python","archived":false,"fork":false,"pushed_at":"2025-07-29T12:09:03.000Z","size":465,"stargazers_count":26,"open_issues_count":0,"forks_count":6,"subscribers_count":10,"default_branch":"main","last_synced_at":"2025-09-05T13:20:17.694Z","etag":null,"topics":["archive","python","tutorial","warc"],"latest_commit_sha":null,"homepage":"","language":"Python","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":"2024-06-23T04:49:21.000Z","updated_at":"2025-08-24T17:35:36.000Z","dependencies_parsed_at":null,"dependency_job_id":"68686a0c-5508-40c5-bc21-3f272a8ef6a6","html_url":"https://github.com/commoncrawl/whirlwind-python","commit_stats":null,"previous_names":["commoncrawl/whirlwind-python"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/commoncrawl/whirlwind-python","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/commoncrawl%2Fwhirlwind-python","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/commoncrawl%2Fwhirlwind-python/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/commoncrawl%2Fwhirlwind-python/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/commoncrawl%2Fwhirlwind-python/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/commoncrawl","download_url":"https://codeload.github.com/commoncrawl/whirlwind-python/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/commoncrawl%2Fwhirlwind-python/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":274407392,"owners_count":25279276,"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":10323827,"full_name":"commoncrawl/whirlwind-python","default_branch":"main","committers":[{"name":"Greg Lindahl","email":"greg@commomncrawl.org","login":null,"count":7},{"name":"Greg Lindahl","email":"lindahl@pbm.com","login":"wumpus","count":5},{"name":"silentninja","email":"mmukesh95@hotmail.com","login":"silentninja","count":1},{"name":"Tawanda Moyo","email":"moyotawanda@gmail.com","login":"tawandamoyo","count":1},{"name":"Jason Culverhouse","email":"jason@flipboard.com","login":"jasonculverhouse","count":1},{"name":"Thom Vaughan","email":"thom@commoncrawl.org","login":"thunderpoot","count":1},{"name":"Laurie Burchell","email":"laurie@commoncrawl.org","login":"laurieburchell","count":1}],"total_commits":17,"total_committers":7,"total_bot_commits":0,"total_bot_committers":0,"mean_commits":2.4285714285714284,"dds":0.5882352941176471,"past_year_committers":[{"name":"Greg Lindahl","email":"greg@commomncrawl.org","login":null,"count":7},{"name":"Greg Lindahl","email":"lindahl@pbm.com","login":"wumpus","count":5},{"name":"silentninja","email":"mmukesh95@hotmail.com","login":"silentninja","count":1},{"name":"Tawanda Moyo","email":"moyotawanda@gmail.com","login":"tawandamoyo","count":1},{"name":"Jason Culverhouse","email":"jason@flipboard.com","login":"jasonculverhouse","count":1},{"name":"Thom Vaughan","email":"thom@commoncrawl.org","login":"thunderpoot","count":1},{"name":"Laurie Burchell","email":"laurie@commoncrawl.org","login":"laurieburchell","count":1}],"past_year_total_commits":17,"past_year_total_committers":7,"past_year_total_bot_commits":0,"past_year_total_bot_committers":0,"past_year_mean_commits":2.4285714285714284,"past_year_dds":0.5882352941176471,"last_synced_at":"2025-06-12T20:01:32.876Z","last_synced_commit":"a1b9275e360fcb616ac5523a622bad0c4eaeef20","created_at":"2025-06-12T08:40:51.433Z","updated_at":"2025-06-12T20:02:17.685Z","commits_url":"https://commits.ecosyste.ms/api/v1/hosts/GitHub/repositories/commoncrawl%2Fwhirlwind-python/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/whirlwind-python","html_url":"https://github.com/commoncrawl/whirlwind-python","last_synced_at":"2025-08-31T18:27:40.656Z","status":null,"issues_count":2,"pull_requests_count":15,"avg_time_to_close_issue":1660076.5,"avg_time_to_close_pull_request":2268237.153846154,"issues_closed_count":2,"pull_requests_closed_count":13,"pull_request_authors_count":8,"issue_authors_count":2,"avg_comments_per_issue":1.0,"avg_comments_per_pull_request":0.6,"merged_pull_requests_count":9,"bot_issues_count":0,"bot_pull_requests_count":0,"past_year_issues_count":2,"past_year_pull_requests_count":10,"past_year_avg_time_to_close_issue":1660076.5,"past_year_avg_time_to_close_pull_request":1936423.25,"past_year_issues_closed_count":2,"past_year_pull_requests_closed_count":8,"past_year_pull_request_authors_count":5,"past_year_issue_authors_count":2,"past_year_avg_comments_per_issue":1.0,"past_year_avg_comments_per_pull_request":0.7,"past_year_bot_issues_count":0,"past_year_bot_pull_requests_count":0,"past_year_merged_pull_requests_count":6,"created_at":"2025-06-12T08:40:52.534Z","updated_at":"2025-09-03T06:06:49.151Z","repository_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/repositories/commoncrawl%2Fwhirlwind-python","issues_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/repositories/commoncrawl%2Fwhirlwind-python/issues","issue_labels_count":{},"pull_request_labels_count":{"documentation":2},"issue_author_associations_count":{"NONE":1,"CONTRIBUTOR":1},"pull_request_author_associations_count":{"MEMBER":12,"NONE":7,"CONTRIBUTOR":4},"issue_authors":{"silentninja":1,"duarteocarmo":1},"pull_request_authors":{"wumpus":8,"jasonculverhouse":4,"silentninja":2,"HarikalarKutusu":2,"laurieburchell":2,"thunderpoot":2,"dalhuijsen":1,"plever":1,"tawandamoyo":1},"host":{"name":"GitHub","url":"https://github.com","kind":"github","last_synced_at":"2025-09-06T00:00:15.144Z","repositories_count":10127824,"issues_count":31789776,"pull_requests_count":99123033,"authors_count":10713673,"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":{"CONTRIBUTOR":1,"NONE":1},"past_year_pull_request_author_associations_count":{"MEMBER":8,"NONE":4,"CONTRIBUTOR":1},"past_year_issue_authors":{"duarteocarmo":1,"silentninja":1},"past_year_pull_request_authors":{"wumpus":6,"silentninja":2,"laurieburchell":2,"dalhuijsen":1,"plever":1,"tawandamoyo":1},"maintainers":[{"login":"wumpus","count":8,"url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/authors/wumpus"},{"login":"thunderpoot","count":2,"url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/authors/thunderpoot"},{"login":"laurieburchell","count":2,"url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/authors/laurieburchell"}],"active_maintainers":[{"login":"wumpus","count":6,"url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/authors/wumpus"},{"login":"laurieburchell","count":2,"url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/authors/laurieburchell"}]},"events":{"total":{"IssuesEvent":4,"WatchEvent":17,"DeleteEvent":5,"IssueCommentEvent":8,"PushEvent":38,"PullRequestReviewEvent":2,"PullRequestEvent":15,"ForkEvent":6,"CreateEvent":7},"last_year":{"IssuesEvent":4,"WatchEvent":17,"DeleteEvent":5,"IssueCommentEvent":8,"PushEvent":38,"PullRequestReviewEvent":2,"PullRequestEvent":15,"ForkEvent":6,"CreateEvent":7}},"keywords":["archive","python","tutorial","warc"],"dependencies":[],"score":5.204006687076795,"created_at":"2025-09-09T02:58:07.600Z","updated_at":"2025-10-07T08:42:12.161Z","avatar_url":"https://github.com/commoncrawl.png","language":"Python","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/189242","html_url":"https://science.ecosyste.ms/projects/189242"}