{"id":22166309,"url":"https://github.com/alextanhongpin/pdf-parser","last_synced_at":"2025-10-17T05:28:32.733Z","repository":{"id":79115154,"uuid":"190553245","full_name":"alextanhongpin/pdf-parser","owner":"alextanhongpin","description":"Sample pipeline for parsing PDF and performing text processing","archived":false,"fork":false,"pushed_at":"2019-06-06T09:22:36.000Z","size":1,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-07-19T03:35:22.813Z","etag":null,"topics":["nlp","python","resume-parser","text-processing","tika"],"latest_commit_sha":null,"homepage":null,"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/alextanhongpin.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}},"created_at":"2019-06-06T09:22:20.000Z","updated_at":"2019-06-06T09:24:19.000Z","dependencies_parsed_at":null,"dependency_job_id":"94e7a75c-a1f7-4fd4-b153-f6194d52947d","html_url":"https://github.com/alextanhongpin/pdf-parser","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/alextanhongpin/pdf-parser","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/alextanhongpin%2Fpdf-parser","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/alextanhongpin%2Fpdf-parser/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/alextanhongpin%2Fpdf-parser/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/alextanhongpin%2Fpdf-parser/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/alextanhongpin","download_url":"https://codeload.github.com/alextanhongpin/pdf-parser/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/alextanhongpin%2Fpdf-parser/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":279289926,"owners_count":26141131,"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":"2025-10-17T02:00:07.504Z","response_time":56,"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":["nlp","python","resume-parser","text-processing","tika"],"created_at":"2024-12-02T05:19:04.543Z","updated_at":"2025-10-17T05:28:32.687Z","avatar_url":"https://github.com/alextanhongpin.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# PDF Parser with Tika\n\nSample pipeline for pdf parsing and NLP.\n\n```bash\n$ pip3 install tika\n$ pip install tika\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Falextanhongpin%2Fpdf-parser","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Falextanhongpin%2Fpdf-parser","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Falextanhongpin%2Fpdf-parser/lists"}