{"id":16976300,"url":"https://github.com/ferbcn/pytextractor","last_synced_at":"2025-09-10T12:35:16.148Z","repository":{"id":149198485,"uuid":"218735542","full_name":"ferbcn/PyTextractor","owner":"ferbcn","description":"Extract text with OCR from images and pdf-image files","archived":false,"fork":false,"pushed_at":"2019-10-31T13:05:07.000Z","size":19,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-06-09T20:38:06.461Z","etag":null,"topics":["pyqt5","python","tesseract","tesseract-ocr"],"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/ferbcn.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":"2019-10-31T10:00:15.000Z","updated_at":"2019-11-01T10:36:33.000Z","dependencies_parsed_at":null,"dependency_job_id":"6b3d270c-351f-462f-b4a5-683962ad1fdf","html_url":"https://github.com/ferbcn/PyTextractor","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/ferbcn/PyTextractor","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ferbcn%2FPyTextractor","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ferbcn%2FPyTextractor/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ferbcn%2FPyTextractor/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ferbcn%2FPyTextractor/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ferbcn","download_url":"https://codeload.github.com/ferbcn/PyTextractor/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ferbcn%2FPyTextractor/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":274463065,"owners_count":25290112,"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"}},"keywords":["pyqt5","python","tesseract","tesseract-ocr"],"created_at":"2024-10-14T01:25:39.774Z","updated_at":"2025-09-10T12:35:16.140Z","avatar_url":"https://github.com/ferbcn.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Installation \n\npip install -r requirements.txt\n\ntesseract-ocr binaries (and maybe PATH)\n\nTesseract language packages. (and maybe add  PATH to tessdata parent directory)\n\nWindows requires poppler for windows (included in most linux distros). You'll need to add binaries folder to PATH\n\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fferbcn%2Fpytextractor","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fferbcn%2Fpytextractor","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fferbcn%2Fpytextractor/lists"}