{"id":189271,"name":null,"description":"Code to build an index that maps warcinfo-id to crawl / warc","url":"https://github.com/commoncrawl/cc-warcinfo-index-builder","last_synced_at":"2025-09-10T03:38:48.779Z","repository":{"id":295741553,"uuid":"991083478","full_name":"commoncrawl/cc-warcinfo-index-builder","owner":"commoncrawl","description":"Code to build an index that maps warcinfo-id to crawl / warc","archived":false,"fork":false,"pushed_at":"2025-05-27T05:48:29.000Z","size":7,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2025-06-12T08:49:04.577Z","etag":null,"topics":[],"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/commoncrawl.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,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2025-05-27T05:25:13.000Z","updated_at":"2025-05-27T05:48:33.000Z","dependencies_parsed_at":"2025-05-27T06:35:46.302Z","dependency_job_id":"58553918-b1a4-4911-97a9-4c265460a4ae","html_url":"https://github.com/commoncrawl/cc-warcinfo-index-builder","commit_stats":null,"previous_names":["commoncrawl/cc-warcinfo-index-builder"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/commoncrawl/cc-warcinfo-index-builder","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/commoncrawl%2Fcc-warcinfo-index-builder","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/commoncrawl%2Fcc-warcinfo-index-builder/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/commoncrawl%2Fcc-warcinfo-index-builder/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/commoncrawl%2Fcc-warcinfo-index-builder/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/commoncrawl","download_url":"https://codeload.github.com/commoncrawl/cc-warcinfo-index-builder/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/commoncrawl%2Fcc-warcinfo-index-builder/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":10323840,"full_name":"commoncrawl/cc-warcinfo-index-builder","default_branch":"master","committers":[{"name":"Greg Lindahl","email":"greg@commomncrawl.org","login":null,"count":10}],"total_commits":10,"total_committers":1,"total_bot_commits":0,"total_bot_committers":0,"mean_commits":10.0,"dds":0.0,"past_year_committers":[{"name":"Greg Lindahl","email":"greg@commomncrawl.org","login":null,"count":10}],"past_year_total_commits":10,"past_year_total_committers":1,"past_year_total_bot_commits":0,"past_year_total_bot_committers":0,"past_year_mean_commits":10.0,"past_year_dds":0.0,"last_synced_at":"2025-06-12T20:01:17.195Z","last_synced_commit":"0dac9ea805a63bdf965f811075838f556857dc0e","created_at":"2025-06-12T08:40:52.264Z","updated_at":"2025-06-12T20:01:17.196Z","commits_url":"https://commits.ecosyste.ms/api/v1/hosts/GitHub/repositories/commoncrawl%2Fcc-warcinfo-index-builder/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-warcinfo-index-builder","html_url":"https://github.com/commoncrawl/cc-warcinfo-index-builder","last_synced_at":"2025-06-12T08:41:00.986Z","status":null,"issues_count":0,"pull_requests_count":0,"avg_time_to_close_issue":null,"avg_time_to_close_pull_request":null,"issues_closed_count":0,"pull_requests_closed_count":0,"pull_request_authors_count":0,"issue_authors_count":0,"avg_comments_per_issue":null,"avg_comments_per_pull_request":null,"merged_pull_requests_count":0,"bot_issues_count":0,"bot_pull_requests_count":0,"past_year_issues_count":0,"past_year_pull_requests_count":0,"past_year_avg_time_to_close_issue":null,"past_year_avg_time_to_close_pull_request":null,"past_year_issues_closed_count":0,"past_year_pull_requests_closed_count":0,"past_year_pull_request_authors_count":0,"past_year_issue_authors_count":0,"past_year_avg_comments_per_issue":null,"past_year_avg_comments_per_pull_request":null,"past_year_bot_issues_count":0,"past_year_bot_pull_requests_count":0,"past_year_merged_pull_requests_count":0,"created_at":"2025-06-12T08:40:53.680Z","updated_at":"2025-06-12T08:41:00.986Z","repository_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/repositories/commoncrawl%2Fcc-warcinfo-index-builder","issues_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/repositories/commoncrawl%2Fcc-warcinfo-index-builder/issues","issue_labels_count":{},"pull_request_labels_count":{},"issue_author_associations_count":{},"pull_request_author_associations_count":{},"issue_authors":{},"pull_request_authors":{},"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":{},"past_year_issue_authors":{},"past_year_pull_request_authors":{},"maintainers":[],"active_maintainers":[]},"events":{"total":{"PushEvent":1,"CreateEvent":1},"last_year":{"PushEvent":1,"CreateEvent":1}},"keywords":[],"dependencies":[{"ecosystem":"pypi","filepath":"requirements.txt","sha":null,"kind":"manifest","created_at":"2025-05-27T06:35:46.215Z","updated_at":"2025-05-27T06:35:46.215Z","repository_link":"https://github.com/commoncrawl/cc-warcinfo-index-builder/blob/main/requirements.txt","dependencies":[{"id":23322242244,"package_name":"boto3","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":23322242245,"package_name":"warcio","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":23322242246,"package_name":"pandas","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":23322242247,"package_name":"numpy","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":23322242248,"package_name":"pyarrow","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":23322242249,"package_name":"duckdb","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":23322242250,"package_name":"pytest","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false}]}],"score":null,"created_at":"2025-09-09T02:58:07.688Z","updated_at":"2025-10-07T08:42:12.698Z","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/189271","html_url":"https://science.ecosyste.ms/projects/189271"}