{"id":189245,"name":null,"description":"Statistics of Common Crawl monthly archives mined from URL index files","url":"https://github.com/commoncrawl/cc-crawl-statistics","last_synced_at":"2025-09-10T03:38:46.909Z","repository":{"id":43997923,"uuid":"63318430","full_name":"commoncrawl/cc-crawl-statistics","owner":"commoncrawl","description":"Statistics of Common Crawl monthly archives mined from URL index files","archived":false,"fork":false,"pushed_at":"2025-08-28T10:04:53.000Z","size":405794,"stargazers_count":188,"open_issues_count":2,"forks_count":12,"subscribers_count":17,"default_branch":"master","last_synced_at":"2025-08-28T17:23:53.584Z","etag":null,"topics":["common-crawl","commoncrawl","statistics"],"latest_commit_sha":null,"homepage":"https://commoncrawl.github.io/cc-crawl-statistics/","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":"2016-07-14T08:38:12.000Z","updated_at":"2025-08-25T16:34:47.000Z","dependencies_parsed_at":"2023-01-28T20:45:58.644Z","dependency_job_id":"db2d31c3-d61a-44f1-aa97-c4c99d1fae70","html_url":"https://github.com/commoncrawl/cc-crawl-statistics","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/commoncrawl/cc-crawl-statistics","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/commoncrawl%2Fcc-crawl-statistics","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/commoncrawl%2Fcc-crawl-statistics/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/commoncrawl%2Fcc-crawl-statistics/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/commoncrawl%2Fcc-crawl-statistics/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/commoncrawl","download_url":"https://codeload.github.com/commoncrawl/cc-crawl-statistics/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/commoncrawl%2Fcc-crawl-statistics/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":274407396,"owners_count":25279277,"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":10323855,"full_name":"commoncrawl/cc-crawl-statistics","default_branch":"master","committers":[{"name":"Sebastian Nagel","email":"sebastian@commoncrawl.org","login":"sebastian-nagel","count":204},{"name":"Thom Vaughan","email":"thom@commoncrawl.org","login":"thunderpoot","count":24},{"name":"Julien Nioche","email":"julien@digitalpebble.com","login":"jnioche","count":4},{"name":"Pedro Ortiz Suarez","email":"pedro@commoncrawl.org","login":"pjox","count":3},{"name":"Julien Nioche","email":"julien@commoncrawl.org","login":null,"count":2},{"name":"Greg Lindahl","email":"greg@commomncrawl.org","login":null,"count":1}],"total_commits":238,"total_committers":6,"total_bot_commits":0,"total_bot_committers":0,"mean_commits":39.666666666666664,"dds":0.1428571428571429,"past_year_committers":[{"name":"Sebastian Nagel","email":"sebastian@commoncrawl.org","login":"sebastian-nagel","count":16},{"name":"Thom Vaughan","email":"thom@commoncrawl.org","login":"thunderpoot","count":16},{"name":"Pedro Ortiz Suarez","email":"pedro@commoncrawl.org","login":"pjox","count":1}],"past_year_total_commits":33,"past_year_total_committers":3,"past_year_total_bot_commits":0,"past_year_total_bot_committers":0,"past_year_mean_commits":11.0,"past_year_dds":0.5151515151515151,"last_synced_at":"2025-06-12T20:02:44.234Z","last_synced_commit":"b97c079d5be081cdd9ca1aa3a3f6dde43fd65dcd","created_at":"2025-06-12T08:40:53.222Z","updated_at":"2025-06-12T20:02:51.690Z","commits_url":"https://commits.ecosyste.ms/api/v1/hosts/GitHub/repositories/commoncrawl%2Fcc-crawl-statistics/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/cc-crawl-statistics","html_url":"https://github.com/commoncrawl/cc-crawl-statistics","last_synced_at":"2025-08-29T12:02:20.017Z","status":null,"issues_count":8,"pull_requests_count":5,"avg_time_to_close_issue":2054063.75,"avg_time_to_close_pull_request":921502.0,"issues_closed_count":8,"pull_requests_closed_count":4,"pull_request_authors_count":1,"issue_authors_count":8,"avg_comments_per_issue":1.625,"avg_comments_per_pull_request":0.4,"merged_pull_requests_count":4,"bot_issues_count":0,"bot_pull_requests_count":0,"past_year_issues_count":1,"past_year_pull_requests_count":3,"past_year_avg_time_to_close_issue":150964.0,"past_year_avg_time_to_close_pull_request":402912.5,"past_year_issues_closed_count":1,"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":1.0,"past_year_avg_comments_per_pull_request":0.0,"past_year_bot_issues_count":0,"past_year_bot_pull_requests_count":0,"past_year_merged_pull_requests_count":2,"created_at":"2025-06-12T08:40:54.874Z","updated_at":"2025-09-01T17:39:07.492Z","repository_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/repositories/commoncrawl%2Fcc-crawl-statistics","issues_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/repositories/commoncrawl%2Fcc-crawl-statistics/issues","issue_labels_count":{"question":3,"wontfix":1},"pull_request_labels_count":{},"issue_author_associations_count":{"NONE":7,"CONTRIBUTOR":2,"MEMBER":1},"pull_request_author_associations_count":{"CONTRIBUTOR":10},"issue_authors":{"tfmorris":1,"drunkpig":1,"pjox":1,"RichardKCollins":1,"johanovic":1,"SeekPoint":1,"sebastian-nagel":1,"edsu":1,"handecelikkanat":1,"happywhitelake":1},"pull_request_authors":{"sebastian-nagel":10},"host":{"name":"GitHub","url":"https://github.com","kind":"github","last_synced_at":"2025-09-10T00:00:25.260Z","repositories_count":10197629,"issues_count":32206487,"pull_requests_count":101687211,"authors_count":10742123,"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":{"question":1},"past_year_pull_request_labels_count":{},"past_year_issue_author_associations_count":{"CONTRIBUTOR":2,"NONE":1},"past_year_pull_request_author_associations_count":{"CONTRIBUTOR":6},"past_year_issue_authors":{"drunkpig":1,"handecelikkanat":1,"sebastian-nagel":1},"past_year_pull_request_authors":{"sebastian-nagel":6},"maintainers":[{"login":"pjox","count":1,"url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/authors/pjox"}],"active_maintainers":[]},"events":{"total":{"IssuesEvent":2,"WatchEvent":40,"DeleteEvent":3,"IssueCommentEvent":4,"PushEvent":29,"PullRequestReviewEvent":3,"PullRequestReviewCommentEvent":1,"PullRequestEvent":7,"ForkEvent":1,"CreateEvent":2},"last_year":{"IssuesEvent":2,"WatchEvent":40,"DeleteEvent":3,"IssueCommentEvent":4,"PushEvent":29,"PullRequestReviewEvent":3,"PullRequestReviewCommentEvent":1,"PullRequestEvent":7,"ForkEvent":1,"CreateEvent":2}},"keywords":["common-crawl","commoncrawl","statistics"],"dependencies":[{"ecosystem":"pypi","filepath":"requirements_plot.txt","sha":null,"kind":"manifest","created_at":"2023-01-28T20:45:58.607Z","updated_at":"2023-01-28T20:45:58.607Z","repository_link":"https://github.com/commoncrawl/cc-crawl-statistics/blob/master/requirements_plot.txt","dependencies":[{"id":7214187422,"package_name":"ggplot","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":7214187423,"package_name":"idna","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":7214187424,"package_name":"pandas","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":7214187425,"package_name":"pygraphviz","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":7214187426,"package_name":"rpy2","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false}]},{"ecosystem":"pypi","filepath":"requirements.txt","sha":null,"kind":"manifest","created_at":"2023-01-28T20:45:58.540Z","updated_at":"2023-01-28T20:45:58.540Z","repository_link":"https://github.com/commoncrawl/cc-crawl-statistics/blob/master/requirements.txt","dependencies":[{"id":7214187376,"package_name":"hyperloglog","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":7214187377,"package_name":"isoweek","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":7214187378,"package_name":"mrjob","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":7214187379,"package_name":"tldextract","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":7214187380,"package_name":"ujson","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false}]}],"score":7.038783541388542,"created_at":"2025-09-09T02:58:07.615Z","updated_at":"2025-10-07T08:42:12.218Z","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":["archived","warc","centrality-measures","pagerank","webgraph","webgraph-framework"],"project_url":"https://science.ecosyste.ms/api/v1/projects/189245","html_url":"https://science.ecosyste.ms/projects/189245"}