{"id":26619,"name":"pdf-extractor","description":"NLP-powered tool designed to extract data from PDF documents. Using Optical Character Recognition (OCR) technology and GPT language model, this tool offers the capability to read, interpret, and convert unstructured data in PDFs into structured, usable data formats and provides the output in an Excel sheet. ","url":"https://github.com/kaufmannb/pdf-extractor","last_synced_at":"2025-09-05T03:17:40.662Z","repository":{"id":183041409,"uuid":"653798846","full_name":"kaufmannb/PDF-Extractor","owner":"kaufmannb","description":"NLP-powered tool designed to extract data from PDF documents. Using Optical Character Recognition (OCR) technology and GPT language model, this tool offers the capability to read, interpret, and convert unstructured data in PDFs into structured, usable data formats and provides the output in an Excel sheet. ","archived":false,"fork":false,"pushed_at":"2023-10-04T16:50:11.000Z","size":385,"stargazers_count":7,"open_issues_count":0,"forks_count":1,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-04-13T13:23:27.516Z","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":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/kaufmannb.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"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":"2023-06-14T19:00:00.000Z","updated_at":"2024-12-30T20:28:08.000Z","dependencies_parsed_at":"2025-04-13T13:33:43.905Z","dependency_job_id":null,"html_url":"https://github.com/kaufmannb/PDF-Extractor","commit_stats":null,"previous_names":["kaufmannb/pdf-extractor"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/kaufmannb/PDF-Extractor","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kaufmannb%2FPDF-Extractor","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kaufmannb%2FPDF-Extractor/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kaufmannb%2FPDF-Extractor/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kaufmannb%2FPDF-Extractor/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/kaufmannb","download_url":"https://codeload.github.com/kaufmannb/PDF-Extractor/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kaufmannb%2FPDF-Extractor/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":273704689,"owners_count":25153204,"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":"kaufmannb","name":"Basil Kaufmann","uuid":"123345478","kind":"user","description":"Urologist and tech enthusiast. ","email":"","website":null,"location":"New York","twitter":"BasilKaufmann","company":"Icahn School of Medicine at Mount Sinai","icon_url":"https://avatars.githubusercontent.com/u/123345478?v=4","repositories_count":1,"last_synced_at":"2023-07-22T15:31:02.356Z","metadata":{"has_sponsors_listing":false},"html_url":"https://github.com/kaufmannb","funding_links":[],"total_stars":null,"followers":null,"following":null,"created_at":"2023-05-04T20:37:26.316Z","updated_at":"2023-07-22T15:31:02.368Z","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/kaufmannb","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/kaufmannb/repositories"},"packages":[],"commits":{"message":"Repository syncing started."},"issues_stats":{"full_name":"kaufmannb/pdf-extractor","html_url":"https://github.com/kaufmannb/pdf-extractor","last_synced_at":null,"status":null,"issues_count":null,"pull_requests_count":null,"avg_time_to_close_issue":null,"avg_time_to_close_pull_request":null,"issues_closed_count":null,"pull_requests_closed_count":null,"pull_request_authors_count":null,"issue_authors_count":null,"avg_comments_per_issue":null,"avg_comments_per_pull_request":null,"merged_pull_requests_count":null,"bot_issues_count":null,"bot_pull_requests_count":null,"past_year_issues_count":null,"past_year_pull_requests_count":null,"past_year_avg_time_to_close_issue":null,"past_year_avg_time_to_close_pull_request":null,"past_year_issues_closed_count":null,"past_year_pull_requests_closed_count":null,"past_year_pull_request_authors_count":null,"past_year_issue_authors_count":null,"past_year_avg_comments_per_issue":null,"past_year_avg_comments_per_pull_request":null,"past_year_bot_issues_count":null,"past_year_bot_pull_requests_count":null,"past_year_merged_pull_requests_count":null,"created_at":"2025-09-05T03:17:13.084Z","updated_at":"2025-09-05T03:17:13.084Z","repository_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/repositories/kaufmannb%2Fpdf-extractor","issues_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/repositories/kaufmannb%2Fpdf-extractor/issues","issue_labels_count":{},"pull_request_labels_count":{},"issue_author_associations_count":{},"pull_request_author_associations_count":{},"issue_authors":{},"pull_request_authors":{},"host":{"name":"GitHub","url":"https://github.com","kind":"github","last_synced_at":"2025-09-05T00:00:10.444Z","repositories_count":10083752,"issues_count":31254324,"pull_requests_count":96222393,"authors_count":10694625,"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},"last_year":{"WatchEvent":3}},"keywords":[],"dependencies":[{"ecosystem":"pypi","filepath":"requirements.txt","sha":null,"kind":"manifest","created_at":"2023-10-02T19:39:04.262Z","updated_at":"2023-10-02T19:39:04.262Z","repository_link":"https://github.com/kaufmannb/PDF-Extractor/blob/main/requirements.txt","dependencies":[{"id":14061680438,"package_name":"fitz","ecosystem":"pypi","requirements":"==0.0.1.dev2","direct":true,"kind":"runtime","optional":false},{"id":14061680439,"package_name":"flatten_json","ecosystem":"pypi","requirements":"==0.1.13","direct":true,"kind":"runtime","optional":false},{"id":14061680440,"package_name":"jsonlines","ecosystem":"pypi","requirements":"==3.1.0","direct":true,"kind":"runtime","optional":false},{"id":14061680441,"package_name":"nltk","ecosystem":"pypi","requirements":"==3.8.1","direct":true,"kind":"runtime","optional":false},{"id":14061680442,"package_name":"numpy","ecosystem":"pypi","requirements":"==1.23.5","direct":true,"kind":"runtime","optional":false},{"id":14061680443,"package_name":"openai","ecosystem":"pypi","requirements":"==0.27.8","direct":true,"kind":"runtime","optional":false},{"id":14061680444,"package_name":"openpyxl","ecosystem":"pypi","requirements":"==3.1.2","direct":true,"kind":"runtime","optional":false},{"id":14061680445,"package_name":"pandas","ecosystem":"pypi","requirements":"==2.0.3","direct":true,"kind":"runtime","optional":false},{"id":14061680446,"package_name":"pdfminer","ecosystem":"pypi","requirements":"==20191125","direct":true,"kind":"runtime","optional":false},{"id":14061680447,"package_name":"PyInstaller","ecosystem":"pypi","requirements":"==5.13.0","direct":true,"kind":"runtime","optional":false},{"id":14061680448,"package_name":"PyMuPDF","ecosystem":"pypi","requirements":"==1.22.5","direct":true,"kind":"runtime","optional":false},{"id":14061680449,"package_name":"Requests","ecosystem":"pypi","requirements":"==2.31.0","direct":true,"kind":"runtime","optional":false},{"id":14061680450,"package_name":"scikit_learn","ecosystem":"pypi","requirements":"==1.3.0","direct":true,"kind":"runtime","optional":false},{"id":14061680451,"package_name":"selenium","ecosystem":"pypi","requirements":"==4.10.0","direct":true,"kind":"runtime","optional":false},{"id":14061680452,"package_name":"tensorflow_hub","ecosystem":"pypi","requirements":"==0.13.0","direct":true,"kind":"runtime","optional":false},{"id":14061680453,"package_name":"transformers","ecosystem":"pypi","requirements":"==4.30.2","direct":true,"kind":"runtime","optional":false}]}],"score":null,"created_at":"2025-09-04T15:50:58.821Z","updated_at":"2025-10-07T08:11:56.755Z","avatar_url":"https://github.com/kaufmannb.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/26619","html_url":"https://science.ecosyste.ms/projects/26619","bibtex_url":"https://science.ecosyste.ms/projects/26619/export.bibtex","apalike_url":"https://science.ecosyste.ms/projects/26619/export.apalike"}