{"id":189262,"name":null,"description":"Various Jupyter notebooks about Common Crawl data","url":"https://github.com/commoncrawl/cc-notebooks","last_synced_at":"2025-09-10T03:38:48.743Z","repository":{"id":47653838,"uuid":"197762383","full_name":"commoncrawl/cc-notebooks","owner":"commoncrawl","description":"Various Jupyter notebooks about Common Crawl data","archived":false,"fork":false,"pushed_at":"2025-04-01T16:54:24.000Z","size":3154,"stargazers_count":54,"open_issues_count":0,"forks_count":11,"subscribers_count":18,"default_branch":"main","last_synced_at":"2025-06-12T08:49:21.096Z","etag":null,"topics":["aws-athena","common-crawl","commoncrawl","jupyter-notebook","webarchiving","webgraph-framework"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","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":"2019-07-19T11:38:10.000Z","updated_at":"2025-06-04T14:05:06.000Z","dependencies_parsed_at":"2025-04-01T17:41:20.476Z","dependency_job_id":"218d32cd-0bf7-4786-a18e-407efcffc175","html_url":"https://github.com/commoncrawl/cc-notebooks","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/commoncrawl/cc-notebooks","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/commoncrawl%2Fcc-notebooks","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/commoncrawl%2Fcc-notebooks/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/commoncrawl%2Fcc-notebooks/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/commoncrawl%2Fcc-notebooks/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/commoncrawl","download_url":"https://codeload.github.com/commoncrawl/cc-notebooks/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/commoncrawl%2Fcc-notebooks/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":274407400,"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":10323918,"full_name":"commoncrawl/cc-notebooks","default_branch":"main","committers":[{"name":"Sebastian Nagel","email":"snagel@apache.org","login":"sebastian-nagel","count":23},{"name":"Alex Xue","email":"alexxue2001@gmail.com","login":"Xue-Alex","count":2}],"total_commits":25,"total_committers":2,"total_bot_commits":0,"total_bot_committers":0,"mean_commits":12.5,"dds":0.07999999999999996,"past_year_committers":[{"name":"Sebastian Nagel","email":"sebastian@commoncrawl.org","login":"sebastian-nagel","count":2}],"past_year_total_commits":2,"past_year_total_committers":1,"past_year_total_bot_commits":0,"past_year_total_bot_committers":0,"past_year_mean_commits":2.0,"past_year_dds":0.0,"last_synced_at":"2025-06-12T20:03:31.703Z","last_synced_commit":"9016b80dfce0ff85f823eb6d64d60326895a2a20","created_at":"2025-06-12T08:41:01.145Z","updated_at":"2025-06-12T20:03:31.703Z","commits_url":"https://commits.ecosyste.ms/api/v1/hosts/GitHub/repositories/commoncrawl%2Fcc-notebooks/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-notebooks","html_url":"https://github.com/commoncrawl/cc-notebooks","last_synced_at":"2025-08-31T14:15:16.582Z","status":null,"issues_count":2,"pull_requests_count":4,"avg_time_to_close_issue":95751658.5,"avg_time_to_close_pull_request":3089610.25,"issues_closed_count":2,"pull_requests_closed_count":4,"pull_request_authors_count":2,"issue_authors_count":1,"avg_comments_per_issue":1.0,"avg_comments_per_pull_request":0.75,"merged_pull_requests_count":4,"bot_issues_count":0,"bot_pull_requests_count":0,"past_year_issues_count":0,"past_year_pull_requests_count":2,"past_year_avg_time_to_close_issue":null,"past_year_avg_time_to_close_pull_request":5449348.0,"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":0,"past_year_avg_comments_per_issue":null,"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":"2025-06-12T08:41:06.392Z","updated_at":"2025-08-31T14:15:16.584Z","repository_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/repositories/commoncrawl%2Fcc-notebooks","issues_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/repositories/commoncrawl%2Fcc-notebooks/issues","issue_labels_count":{"enhancement":1},"pull_request_labels_count":{},"issue_author_associations_count":{"CONTRIBUTOR":2},"pull_request_author_associations_count":{"CONTRIBUTOR":2,"COLLABORATOR":2},"issue_authors":{"sebastian-nagel":2},"pull_request_authors":{"Xue-Alex":2,"sebastian-nagel":2},"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":{},"past_year_pull_request_labels_count":{},"past_year_issue_author_associations_count":{},"past_year_pull_request_author_associations_count":{"CONTRIBUTOR":2},"past_year_issue_authors":{},"past_year_pull_request_authors":{"sebastian-nagel":2},"maintainers":[{"login":"Xue-Alex","count":2,"url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/authors/Xue-Alex"}],"active_maintainers":[]},"events":{"total":{"IssuesEvent":2,"WatchEvent":10,"IssueCommentEvent":2,"PushEvent":3,"PullRequestEvent":1,"ForkEvent":2},"last_year":{"IssuesEvent":2,"WatchEvent":10,"IssueCommentEvent":2,"PushEvent":3,"PullRequestEvent":1,"ForkEvent":2}},"keywords":["aws-athena","common-crawl","commoncrawl","jupyter-notebook","webarchiving","webgraph-framework"],"dependencies":[],"score":4.68213122712422,"created_at":"2025-09-09T02:58:07.661Z","updated_at":"2025-10-07T08:42:12.444Z","avatar_url":"https://github.com/commoncrawl.png","language":"Jupyter Notebook","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/189262","html_url":"https://science.ecosyste.ms/projects/189262"}