{"id":207390,"name":null,"description":"Docker Container for a Make-based, PDF extraction using OCR","url":"https://github.com/datamade/pdf-textextract","last_synced_at":"2025-09-11T08:59:38.296Z","repository":{"id":146796504,"uuid":"552194464","full_name":"datamade/pdf-textextract","owner":"datamade","description":"Docker Container for a Make-based, PDF extraction using OCR","archived":false,"fork":false,"pushed_at":"2024-07-31T15:15:04.000Z","size":151,"stargazers_count":12,"open_issues_count":0,"forks_count":4,"subscribers_count":2,"default_branch":"main","last_synced_at":"2025-04-10T19:11:34.134Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"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/datamade.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}},"created_at":"2022-10-16T03:05:26.000Z","updated_at":"2025-01-12T01:45:26.000Z","dependencies_parsed_at":"2024-07-31T18:55:34.061Z","dependency_job_id":null,"html_url":"https://github.com/datamade/pdf-textextract","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/datamade/pdf-textextract","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/datamade%2Fpdf-textextract","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/datamade%2Fpdf-textextract/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/datamade%2Fpdf-textextract/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/datamade%2Fpdf-textextract/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/datamade","download_url":"https://codeload.github.com/datamade/pdf-textextract/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/datamade%2Fpdf-textextract/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":274608198,"owners_count":25316608,"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":"2025-09-11T02:00:13.660Z","response_time":74,"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":"datamade","name":"datamade","uuid":"3723931","kind":"organization","description":"We build open source technology using open data to empower journalists, researchers, governments and advocacy organizations.","email":"info@datamade.us","website":"http://datamade.us","location":"Chicago, IL","twitter":"datamadeco","company":null,"icon_url":"https://avatars.githubusercontent.com/u/3723931?v=4","repositories_count":123,"last_synced_at":"2023-03-24T07:52:38.361Z","metadata":{"has_sponsors_listing":false},"html_url":"https://github.com/datamade","funding_links":[],"total_stars":null,"followers":null,"following":null,"created_at":"2022-11-03T20:55:15.091Z","updated_at":"2023-03-24T07:52:39.283Z","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/datamade","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/datamade/repositories"},"packages":[],"commits":{"id":5639130,"full_name":"datamade/pdf-textextract","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":"2024-11-14T08:12:53.732Z","updated_at":"2024-11-14T08:12:53.732Z","commits_url":"https://commits.ecosyste.ms/api/v1/hosts/GitHub/repositories/datamade%2Fpdf-textextract/commits","host":{"name":"GitHub","url":"https://github.com","kind":"github","last_synced_at":"2025-09-11T02:23:18.710Z","repositories_count":5579221,"commits_count":890438433,"contributors_count":33166812,"owners_count":922982,"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":"datamade/pdf-textextract","html_url":"https://github.com/datamade/pdf-textextract","last_synced_at":"2025-04-10T18:51:08.717Z","status":null,"issues_count":0,"pull_requests_count":1,"avg_time_to_close_issue":null,"avg_time_to_close_pull_request":928607.0,"issues_closed_count":0,"pull_requests_closed_count":1,"pull_request_authors_count":1,"issue_authors_count":0,"avg_comments_per_issue":null,"avg_comments_per_pull_request":0.0,"merged_pull_requests_count":1,"bot_issues_count":0,"bot_pull_requests_count":0,"past_year_issues_count":0,"past_year_pull_requests_count":1,"past_year_avg_time_to_close_issue":null,"past_year_avg_time_to_close_pull_request":928607.0,"past_year_issues_closed_count":0,"past_year_pull_requests_closed_count":1,"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":1,"created_at":"2024-11-14T08:12:58.586Z","updated_at":"2025-09-02T00:58:53.524Z","repository_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/repositories/datamade%2Fpdf-textextract","issues_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/repositories/datamade%2Fpdf-textextract/issues","issue_labels_count":{},"pull_request_labels_count":{},"issue_author_associations_count":{},"pull_request_author_associations_count":{"NONE":1,"CONTRIBUTOR":1},"issue_authors":{},"pull_request_authors":{"alison985":2},"host":{"name":"GitHub","url":"https://github.com","kind":"github","last_synced_at":"2025-09-11T00:00:09.407Z","repositories_count":10236798,"issues_count":32590528,"pull_requests_count":103260691,"authors_count":10756528,"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":{"WatchEvent":3,"ForkEvent":2},"last_year":{"WatchEvent":3,"ForkEvent":2}},"keywords":[],"dependencies":[{"ecosystem":"actions","filepath":".github/workflows/main.yml","sha":null,"kind":"manifest","created_at":"2024-07-31T18:55:33.158Z","updated_at":"2024-07-31T18:55:33.158Z","repository_link":"https://github.com/datamade/pdf-textextract/blob/main/.github/workflows/main.yml","dependencies":[{"id":19438007139,"package_name":"docker/login-action","ecosystem":"actions","requirements":"v1","direct":true,"kind":"composite","optional":false},{"id":19438007140,"package_name":"docker/build-push-action","ecosystem":"actions","requirements":"v2","direct":true,"kind":"composite","optional":false}]},{"ecosystem":"docker","filepath":"Dockerfile","sha":null,"kind":"manifest","created_at":"2024-07-31T18:55:33.255Z","updated_at":"2024-07-31T18:55:33.255Z","repository_link":"https://github.com/datamade/pdf-textextract/blob/main/Dockerfile","dependencies":[{"id":19438007141,"package_name":"python","ecosystem":"docker","requirements":"3.10-slim-bullseye","direct":true,"kind":"build","optional":false}]},{"ecosystem":"docker","filepath":"docker-compose.yml","sha":null,"kind":"manifest","created_at":"2024-07-31T18:55:33.411Z","updated_at":"2024-07-31T18:55:33.411Z","repository_link":"https://github.com/datamade/pdf-textextract/blob/main/docker-compose.yml","dependencies":[{"id":19438007142,"package_name":"ghcr.io/datamade/pdf-textextract","ecosystem":"docker","requirements":"latest","direct":true,"kind":"runtime","optional":false}]},{"ecosystem":"pypi","filepath":"requirements.txt","sha":null,"kind":"manifest","created_at":"2024-07-31T18:55:33.830Z","updated_at":"2024-07-31T18:55:33.830Z","repository_link":"https://github.com/datamade/pdf-textextract/blob/main/requirements.txt","dependencies":[{"id":19438007143,"package_name":"numpy","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":19438007144,"package_name":"opencv-python-headless","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false}]}],"score":null,"created_at":"2025-09-09T04:23:27.743Z","updated_at":"2025-10-07T08:44:17.714Z","avatar_url":"https://github.com/datamade.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/207390","html_url":"https://science.ecosyste.ms/projects/207390"}