{"id":57452,"name":"commoncrawl-creativecommons","description":"Software to create C5, Common Crawl crawls, annotated with potential Creative Commons license information","url":"https://github.com/bramvanroy/commoncrawl-creativecommons","last_synced_at":"2025-09-05T14:48:39.680Z","repository":{"id":275589097,"uuid":"913892842","full_name":"BramVanroy/CommonCrawl-CreativeCommons","owner":"BramVanroy","description":"Software to create C5, Common Crawl crawls, annotated with potential Creative Commons license information","archived":false,"fork":false,"pushed_at":"2025-08-28T09:25:40.000Z","size":349,"stargazers_count":6,"open_issues_count":0,"forks_count":1,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-08-30T07:27:28.720Z","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":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/BramVanroy.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":"CITATION.cff","codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2025-01-08T14:55:59.000Z","updated_at":"2025-08-28T09:25:44.000Z","dependencies_parsed_at":"2025-02-03T14:23:05.301Z","dependency_job_id":"91a384d4-1130-4da3-8a90-5bd1990a62ca","html_url":"https://github.com/BramVanroy/CommonCrawl-CreativeCommons","commit_stats":null,"previous_names":["bramvanroy/commoncrawl-creativecommons"],"tags_count":7,"template":false,"template_full_name":null,"purl":"pkg:github/BramVanroy/CommonCrawl-CreativeCommons","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/BramVanroy%2FCommonCrawl-CreativeCommons","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/BramVanroy%2FCommonCrawl-CreativeCommons/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/BramVanroy%2FCommonCrawl-CreativeCommons/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/BramVanroy%2FCommonCrawl-CreativeCommons/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/BramVanroy","download_url":"https://codeload.github.com/BramVanroy/CommonCrawl-CreativeCommons/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/BramVanroy%2FCommonCrawl-CreativeCommons/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":273772117,"owners_count":25165327,"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":"2025-09-05T02:00:09.113Z","response_time":402,"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":"BramVanroy","name":"Bram Vanroy","uuid":"2779410","kind":"user","description":"👋  My name is Bram and I work on natural language processing and machine translation (evaluation) but I also spend a lot of time in this open-source world 🌍","email":"","website":"https://bramvanroy.github.io/","location":"Belgium","twitter":null,"company":"@CCL-KULeuven @instituutnederlandsetaal","icon_url":"https://avatars.githubusercontent.com/u/2779410?u=acab3262cb2b0c02b0e6986e9194e809a801324f\u0026v=4","repositories_count":29,"last_synced_at":"2025-08-30T07:22:57.196Z","metadata":{"has_sponsors_listing":false},"html_url":"https://github.com/BramVanroy","funding_links":[],"total_stars":null,"followers":151,"following":26,"created_at":"2023-02-15T00:31:31.716Z","updated_at":"2025-08-30T07:22:57.196Z","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/BramVanroy","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/BramVanroy/repositories"},"packages":[],"commits":{"id":8865862,"full_name":"bramvanroy/commoncrawl-creativecommons","default_branch":"master","committers":null,"total_commits":null,"total_committers":null,"total_bot_commits":null,"total_bot_committers":null,"mean_commits":null,"dds":null,"past_year_committers":null,"past_year_total_commits":null,"past_year_total_committers":null,"past_year_total_bot_commits":null,"past_year_total_bot_committers":null,"past_year_mean_commits":null,"past_year_dds":null,"last_synced_at":null,"last_synced_commit":null,"created_at":"2025-02-21T19:19:05.466Z","updated_at":"2025-02-21T19:19:05.466Z","commits_url":"https://commits.ecosyste.ms/api/v1/hosts/GitHub/repositories/bramvanroy%2Fcommoncrawl-creativecommons/commits","host":{"name":"GitHub","url":"https://github.com","kind":"github","last_synced_at":"2025-09-05T00:00:10.343Z","repositories_count":5480019,"commits_count":853389012,"contributors_count":31098138,"owners_count":906558,"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":"bramvanroy/commoncrawl-creativecommons","html_url":"https://github.com/bramvanroy/commoncrawl-creativecommons","last_synced_at":"2025-04-13T11:51:10.946Z","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":"2025-02-21T19:19:05.561Z","updated_at":"2025-08-29T12:59:30.899Z","repository_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/repositories/bramvanroy%2Fcommoncrawl-creativecommons","issues_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/repositories/bramvanroy%2Fcommoncrawl-creativecommons/issues","issue_labels_count":{},"pull_request_labels_count":{},"issue_author_associations_count":{"NONE":1},"pull_request_author_associations_count":{},"issue_authors":{"KennethEnevoldsen":1},"pull_request_authors":{},"host":{"name":"GitHub","url":"https://github.com","kind":"github","last_synced_at":"2025-09-05T00:00:10.444Z","repositories_count":10101874,"issues_count":31502423,"pull_requests_count":97598050,"authors_count":10703170,"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":{"KennethEnevoldsen":1},"past_year_pull_request_authors":{},"maintainers":[],"active_maintainers":[]},"events":{"total":{"IssuesEvent":1,"WatchEvent":4,"PushEvent":61,"PublicEvent":1,"CreateEvent":4},"last_year":{"IssuesEvent":1,"WatchEvent":4,"PushEvent":61,"PublicEvent":1,"CreateEvent":4}},"keywords":[],"dependencies":[{"ecosystem":"pypi","filepath":"pyproject.toml","sha":null,"kind":"manifest","created_at":"2025-02-03T14:23:03.199Z","updated_at":"2025-02-03T14:23:03.199Z","repository_link":"https://github.com/BramVanroy/CommonCrawl-CreativeCommons/blob/main/pyproject.toml","dependencies":[{"id":21722734632,"package_name":"beautifulsoup4","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":21722734633,"package_name":"datasets","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":21722734634,"package_name":"datatrove","ecosystem":"pypi","requirements":"[io,s3,processing,multilingual,cli]@git+https://github.com/BramVanroy/datatrove","direct":true,"kind":"runtime","optional":false},{"id":21722735051,"package_name":"duckdb","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":21722735054,"package_name":"hf_transfer","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":21722735534,"package_name":"html5lib","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":21722735535,"package_name":"huggingface_hub","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":21722735536,"package_name":"lxml","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":21722735537,"package_name":"lxml_html_clean","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":21722735541,"package_name":"pip","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":21722735542,"package_name":"pydantic","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false}]}],"score":null,"created_at":"2025-09-04T15:51:33.826Z","updated_at":"2025-10-07T08:22:38.784Z","avatar_url":"https://github.com/BramVanroy.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/57452","html_url":"https://science.ecosyste.ms/projects/57452"}