{"id":189269,"name":null,"description":"Process Common Crawl data with Python and Spark","url":"https://github.com/commoncrawl/cc-pyspark","last_synced_at":"2025-09-10T03:38:49.774Z","repository":{"id":22135455,"uuid":"88059195","full_name":"commoncrawl/cc-pyspark","owner":"commoncrawl","description":"Process Common Crawl data with Python and Spark","archived":false,"fork":false,"pushed_at":"2025-05-27T11:49:13.000Z","size":173,"stargazers_count":432,"open_issues_count":5,"forks_count":89,"subscribers_count":21,"default_branch":"main","last_synced_at":"2025-06-12T08:49:08.093Z","etag":null,"topics":["common-crawl","commoncrawl","pyspark","spark","sparksql","warc-files","wat-files","wet"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","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":"2017-04-12T14:09:44.000Z","updated_at":"2025-06-05T12:32:18.000Z","dependencies_parsed_at":"2024-08-03T03:56:54.611Z","dependency_job_id":"edf4d2f4-8baf-49db-976b-f62d6b2f85be","html_url":"https://github.com/commoncrawl/cc-pyspark","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/commoncrawl/cc-pyspark","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/commoncrawl%2Fcc-pyspark","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/commoncrawl%2Fcc-pyspark/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/commoncrawl%2Fcc-pyspark/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/commoncrawl%2Fcc-pyspark/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/commoncrawl","download_url":"https://codeload.github.com/commoncrawl/cc-pyspark/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/commoncrawl%2Fcc-pyspark/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":10323861,"full_name":"commoncrawl/cc-pyspark","default_branch":"main","committers":[{"name":"Sebastian Nagel","email":"sebastian@commoncrawl.org","login":"sebastian-nagel","count":100},{"name":"silentninja","email":"mmukesh95@hotmail.com","login":"silentninja","count":7},{"name":"cronoik","email":"johannes.schaffrath@mail.de","login":"cronoik","count":1},{"name":"Jae Ro","email":"jaero@google.com","login":"jaehunro","count":1},{"name":"Alex Xue","email":"alexxue2001@gmail.com","login":"Xue-Alex","count":1},{"name":"Praveen R","email":"praveen.rachabattuni@icloud.com","login":"praveenr019","count":1}],"total_commits":111,"total_committers":6,"total_bot_commits":0,"total_bot_committers":0,"mean_commits":18.5,"dds":0.09909909909909909,"past_year_committers":[{"name":"Sebastian Nagel","email":"sebastian@commoncrawl.org","login":"sebastian-nagel","count":9},{"name":"silentninja","email":"mmukesh95@hotmail.com","login":"silentninja","count":7}],"past_year_total_commits":16,"past_year_total_committers":2,"past_year_total_bot_commits":0,"past_year_total_bot_committers":0,"past_year_mean_commits":8.0,"past_year_dds":0.4375,"last_synced_at":"2025-06-12T20:02:16.039Z","last_synced_commit":"dc23ca9ec9ae9cd27c36e0cfefe744ed3cc05335","created_at":"2025-06-12T08:40:54.473Z","updated_at":"2025-06-12T20:02:29.701Z","commits_url":"https://commits.ecosyste.ms/api/v1/hosts/GitHub/repositories/commoncrawl%2Fcc-pyspark/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-pyspark","html_url":"https://github.com/commoncrawl/cc-pyspark","last_synced_at":"2025-08-31T16:48:11.411Z","status":null,"issues_count":28,"pull_requests_count":26,"avg_time_to_close_issue":16163713.5,"avg_time_to_close_pull_request":20361333.0,"issues_closed_count":24,"pull_requests_closed_count":23,"pull_request_authors_count":11,"issue_authors_count":15,"avg_comments_per_issue":2.0357142857142856,"avg_comments_per_pull_request":1.0384615384615385,"merged_pull_requests_count":14,"bot_issues_count":0,"bot_pull_requests_count":0,"past_year_issues_count":3,"past_year_pull_requests_count":6,"past_year_avg_time_to_close_issue":1584184.0,"past_year_avg_time_to_close_pull_request":2146388.25,"past_year_issues_closed_count":1,"past_year_pull_requests_closed_count":4,"past_year_pull_request_authors_count":2,"past_year_issue_authors_count":3,"past_year_avg_comments_per_issue":1.0,"past_year_avg_comments_per_pull_request":1.0,"past_year_bot_issues_count":0,"past_year_bot_pull_requests_count":0,"past_year_merged_pull_requests_count":4,"created_at":"2025-06-12T08:40:56.109Z","updated_at":"2025-09-03T06:45:51.957Z","repository_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/repositories/commoncrawl%2Fcc-pyspark","issues_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/repositories/commoncrawl%2Fcc-pyspark/issues","issue_labels_count":{"enhancement":8,"question":5,"bug":1},"pull_request_labels_count":{"enhancement":1},"issue_author_associations_count":{"CONTRIBUTOR":15,"NONE":13},"pull_request_author_associations_count":{"CONTRIBUTOR":21,"NONE":7,"COLLABORATOR":1},"issue_authors":{"sebastian-nagel":13,"swetepete":2,"brand17":1,"silentninja":1,"praveenr019":1,"BrownXing":1,"calee88":1,"chk2817":1,"Thanchanokk-p":1,"gamtiq":1,"GenuineReader":1,"lgov":1,"aliebrahiiimi":1,"hussien":1,"jaehunro":1},"pull_request_authors":{"sebastian-nagel":15,"silentninja":4,"jt55401":2,"tylerkovacs":1,"lauraedelson":1,"rdowd003":1,"praveenr019":1,"cronoik":1,"Xue-Alex":1,"layedra":1,"jaehunro":1},"host":{"name":"GitHub","url":"https://github.com","kind":"github","last_synced_at":"2025-09-06T00:00:15.144Z","repositories_count":10117187,"issues_count":31659705,"pull_requests_count":98542721,"authors_count":10708861,"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":{"NONE":3},"past_year_pull_request_author_associations_count":{"CONTRIBUTOR":6,"NONE":1},"past_year_issue_authors":{"hussien":1,"silentninja":1,"Thanchanokk-p":1},"past_year_pull_request_authors":{"silentninja":4,"sebastian-nagel":3},"maintainers":[{"login":"Xue-Alex","count":1,"url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/authors/Xue-Alex"}],"active_maintainers":[]},"events":{"total":{"IssuesEvent":5,"WatchEvent":39,"DeleteEvent":6,"IssueCommentEvent":13,"PushEvent":6,"PullRequestReviewCommentEvent":3,"PullRequestReviewEvent":7,"PullRequestEvent":5,"ForkEvent":4,"CreateEvent":2},"last_year":{"IssuesEvent":5,"WatchEvent":39,"DeleteEvent":6,"IssueCommentEvent":13,"PushEvent":6,"PullRequestReviewCommentEvent":3,"PullRequestReviewEvent":7,"PullRequestEvent":5,"ForkEvent":4,"CreateEvent":2}},"keywords":["common-crawl","commoncrawl","pyspark","spark","sparksql","warc-files","wat-files","wet"],"dependencies":[{"ecosystem":"pypi","filepath":"requirements.txt","sha":null,"kind":"manifest","created_at":"2022-07-04T11:42:02.887Z","updated_at":"2022-07-04T11:42:02.887Z","repository_link":"https://github.com/commoncrawl/cc-pyspark/blob/main/requirements.txt","dependencies":[{"id":105270278,"package_name":"botocore","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":105270279,"package_name":"boto3","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":105270280,"package_name":"requests","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":105270281,"package_name":"ujson","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":105270282,"package_name":"warcio","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":105270283,"package_name":"idna","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":105270284,"package_name":"beautifulsoup4","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":105270285,"package_name":"lxml","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false}]}],"score":7.8716926643236445,"created_at":"2025-09-09T02:58:07.683Z","updated_at":"2025-10-07T08:42:12.624Z","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/189269","html_url":"https://science.ecosyste.ms/projects/189269"}