{"id":189254,"name":null,"description":"Tools to construct and process Common Crawl webgraphs","url":"https://github.com/commoncrawl/cc-webgraph","last_synced_at":"2025-09-10T03:38:46.534Z","repository":{"id":47653513,"uuid":"110439950","full_name":"commoncrawl/cc-webgraph","owner":"commoncrawl","description":"Tools to construct and process Common Crawl webgraphs","archived":false,"fork":false,"pushed_at":"2025-07-01T11:31:49.000Z","size":158,"stargazers_count":92,"open_issues_count":2,"forks_count":5,"subscribers_count":12,"default_branch":"main","last_synced_at":"2025-07-01T12:32:07.412Z","etag":null,"topics":["centrality-measures","common-crawl","commoncrawl","pagerank","webgraph","webgraph-framework"],"latest_commit_sha":null,"homepage":"https://commoncrawl.org/web-graphs","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":"2017-11-12T14:38:16.000Z","updated_at":"2025-07-01T11:30:40.000Z","dependencies_parsed_at":"2024-06-03T23:36:25.638Z","dependency_job_id":"7d29995c-85ca-416e-9e77-d47aae7305ab","html_url":"https://github.com/commoncrawl/cc-webgraph","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/commoncrawl/cc-webgraph","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/commoncrawl%2Fcc-webgraph","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/commoncrawl%2Fcc-webgraph/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/commoncrawl%2Fcc-webgraph/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/commoncrawl%2Fcc-webgraph/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/commoncrawl","download_url":"https://codeload.github.com/commoncrawl/cc-webgraph/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/commoncrawl%2Fcc-webgraph/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":10323847,"full_name":"commoncrawl/cc-webgraph","default_branch":"main","committers":[{"name":"Sebastian Nagel","email":"sebastian@commoncrawl.org","login":"sebastian-nagel","count":105},{"name":"Thom Vaughan","email":"thom@commoncrawl.org","login":"thunderpoot","count":13},{"name":"Julien Nioche","email":"julien@digitalpebble.com","login":"jnioche","count":2},{"name":"dependabot[bot]","email":"49699333+dependabot[bot]","login":"dependabot[bot]","count":1},{"name":"Ubuntu","email":"ubuntu@ip-10-42-42-7.ec2.internal","login":null,"count":1}],"total_commits":122,"total_committers":5,"total_bot_commits":1,"total_bot_committers":1,"mean_commits":24.4,"dds":0.139344262295082,"past_year_committers":[{"name":"Sebastian Nagel","email":"sebastian@commoncrawl.org","login":"sebastian-nagel","count":20},{"name":"Thom Vaughan","email":"thom@commoncrawl.org","login":"thunderpoot","count":8},{"name":"Ubuntu","email":"ubuntu@ip-10-42-42-7.ec2.internal","login":null,"count":1}],"past_year_total_commits":29,"past_year_total_committers":3,"past_year_total_bot_commits":0,"past_year_total_bot_committers":0,"past_year_mean_commits":9.666666666666666,"past_year_dds":0.31034482758620685,"last_synced_at":"2025-06-12T20:02:28.649Z","last_synced_commit":"23a4aed91110b71623373970d65f798acdf01ade","created_at":"2025-06-12T08:40:52.863Z","updated_at":"2025-06-12T20:02:33.473Z","commits_url":"https://commits.ecosyste.ms/api/v1/hosts/GitHub/repositories/commoncrawl%2Fcc-webgraph/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-webgraph","html_url":"https://github.com/commoncrawl/cc-webgraph","last_synced_at":"2025-06-12T08:41:12.521Z","status":null,"issues_count":14,"pull_requests_count":7,"avg_time_to_close_issue":14669827.0,"avg_time_to_close_pull_request":3369935.4285714286,"issues_closed_count":12,"pull_requests_closed_count":7,"pull_request_authors_count":2,"issue_authors_count":9,"avg_comments_per_issue":3.0,"avg_comments_per_pull_request":0.2857142857142857,"merged_pull_requests_count":7,"bot_issues_count":0,"bot_pull_requests_count":2,"past_year_issues_count":4,"past_year_pull_requests_count":1,"past_year_avg_time_to_close_issue":1817296.0,"past_year_avg_time_to_close_pull_request":5371997.0,"past_year_issues_closed_count":3,"past_year_pull_requests_closed_count":1,"past_year_pull_request_authors_count":1,"past_year_issue_authors_count":4,"past_year_avg_comments_per_issue":1.25,"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":1,"created_at":"2025-06-12T08:40:54.434Z","updated_at":"2025-09-02T13:19:07.718Z","repository_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/repositories/commoncrawl%2Fcc-webgraph","issues_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/repositories/commoncrawl%2Fcc-webgraph/issues","issue_labels_count":{"enhancement":2,"bug":2,"help wanted":1,"question":1},"pull_request_labels_count":{"dependencies":3},"issue_author_associations_count":{"NONE":8,"CONTRIBUTOR":5,"MEMBER":1},"pull_request_author_associations_count":{"CONTRIBUTOR":10,"NONE":1},"issue_authors":{"sebastian-nagel":5,"akul-goyal":2,"scd31":1,"julesearl":1,"wumpus":1,"PeterCarragher":1,"liyucheng09":1,"AbraGanz":1,"covuworie":1},"pull_request_authors":{"sebastian-nagel":8,"dependabot[bot]":3},"host":{"name":"GitHub","url":"https://github.com","kind":"github","last_synced_at":"2025-09-03T00:00:08.273Z","repositories_count":10061379,"issues_count":31059648,"pull_requests_count":94180017,"authors_count":10686068,"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":{"NONE":1},"past_year_pull_request_author_associations_count":{},"past_year_issue_authors":{"scd31":1},"past_year_pull_request_authors":{},"maintainers":[{"login":"wumpus","count":1,"url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/authors/wumpus"}],"active_maintainers":[]},"events":{"total":{"IssuesEvent":2,"WatchEvent":17,"DeleteEvent":3,"IssueCommentEvent":7,"PushEvent":26,"ForkEvent":1},"last_year":{"IssuesEvent":2,"WatchEvent":17,"DeleteEvent":3,"IssueCommentEvent":7,"PushEvent":26,"ForkEvent":1}},"keywords":["centrality-measures","common-crawl","commoncrawl","pagerank","webgraph","webgraph-framework"],"dependencies":[{"ecosystem":"maven","filepath":"pom.xml","sha":null,"kind":"manifest","created_at":"2022-09-23T15:51:42.582Z","updated_at":"2022-09-23T15:51:42.582Z","repository_link":"https://github.com/commoncrawl/cc-webgraph/blob/main/pom.xml","dependencies":[{"id":5971653304,"package_name":"org.slf4j:slf4j-api","ecosystem":"maven","requirements":"2.0.0","direct":true,"kind":"runtime","optional":false},{"id":5971653305,"package_name":"com.github.crawler-commons:crawler-commons","ecosystem":"maven","requirements":"1.3","direct":true,"kind":"runtime","optional":false},{"id":5971653306,"package_name":"it.unimi.dsi:fastutil-core","ecosystem":"maven","requirements":"8.5.7","direct":true,"kind":"runtime","optional":false},{"id":5971653307,"package_name":"commons-cli:commons-cli","ecosystem":"maven","requirements":"1.5.0","direct":true,"kind":"runtime","optional":false},{"id":5971653308,"package_name":"it.unimi.dsi:webgraph","ecosystem":"maven","requirements":"3.6.10","direct":true,"kind":"runtime","optional":false},{"id":5971653309,"package_name":"it.unimi.dsi:webgraph-big","ecosystem":"maven","requirements":"3.7.0","direct":true,"kind":"runtime","optional":false},{"id":5971653310,"package_name":"it.unimi.dsi:law","ecosystem":"maven","requirements":"2.7.2","direct":true,"kind":"runtime","optional":false},{"id":5971653311,"package_name":"org.apache.commons:commons-configuration2","ecosystem":"maven","requirements":"2.8.0","direct":true,"kind":"runtime","optional":false},{"id":5971653312,"package_name":"org.junit.jupiter:junit-jupiter","ecosystem":"maven","requirements":null,"direct":true,"kind":"test","optional":false},{"id":5971653313,"package_name":"org.slf4j:slf4j-simple","ecosystem":"maven","requirements":"2.0.0","direct":true,"kind":"test","optional":false},{"id":5971653314,"package_name":"org.junit:junit-bom","ecosystem":"maven","requirements":"5.9.0","direct":true,"kind":"import","optional":false}]},{"ecosystem":"actions","filepath":".github/workflows/build.yml","sha":null,"kind":"manifest","created_at":"2024-06-03T23:36:24.314Z","updated_at":"2024-06-03T23:36:24.314Z","repository_link":"https://github.com/commoncrawl/cc-webgraph/blob/main/.github/workflows/build.yml","dependencies":[{"id":18393540706,"package_name":"actions/checkout","ecosystem":"actions","requirements":"v4","direct":true,"kind":"composite","optional":false},{"id":18393540770,"package_name":"actions/setup-java","ecosystem":"actions","requirements":"v4","direct":true,"kind":"composite","optional":false}]}],"score":6.152732694704104,"created_at":"2025-09-09T02:58:07.643Z","updated_at":"2025-10-07T08:42:12.328Z","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":["archival","projection","profiles","interactive","sequences","generic","observability","autograding","hacking","shellcodes"],"project_url":"https://science.ecosyste.ms/api/v1/projects/189254","html_url":"https://science.ecosyste.ms/projects/189254"}