{"id":19758972,"url":"https://github.com/majd-kontar/pdf-highlight-extractor","last_synced_at":"2026-04-17T19:32:27.720Z","repository":{"id":132535253,"uuid":"482201809","full_name":"majd-kontar/pdf-highlight-extractor","owner":"majd-kontar","description":null,"archived":false,"fork":false,"pushed_at":"2022-04-16T10:08:56.000Z","size":31,"stargazers_count":3,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-02-28T09:32:40.749Z","etag":null,"topics":["extract-text","highlight","pdf","python"],"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/majd-kontar.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":"2022-04-16T08:43:58.000Z","updated_at":"2023-10-26T07:55:23.000Z","dependencies_parsed_at":"2023-06-08T13:00:15.322Z","dependency_job_id":null,"html_url":"https://github.com/majd-kontar/pdf-highlight-extractor","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/majd-kontar/pdf-highlight-extractor","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/majd-kontar%2Fpdf-highlight-extractor","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/majd-kontar%2Fpdf-highlight-extractor/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/majd-kontar%2Fpdf-highlight-extractor/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/majd-kontar%2Fpdf-highlight-extractor/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/majd-kontar","download_url":"https://codeload.github.com/majd-kontar/pdf-highlight-extractor/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/majd-kontar%2Fpdf-highlight-extractor/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":31943354,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-17T17:29:20.459Z","status":"ssl_error","status_checked_at":"2026-04-17T17:28:47.801Z","response_time":62,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.6:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"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":["extract-text","highlight","pdf","python"],"created_at":"2024-11-12T03:26:58.301Z","updated_at":"2026-04-17T19:32:27.697Z","avatar_url":"https://github.com/majd-kontar.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# PDF-Highlight-Extractor\n\n![img.png](img.png)\n\n## Description\n\nThis repo allows researchers to easily extract the text they highlight in multiple articles and writes them to a docx file as bullet points under the\nname of the pdf where they were highlighted as a header.\n\n## Getting Started\nInstall requirements\n\u003cbr/\u003e\n`pip install -r requirements.txt`\n\n## Usage\n\nRun `main.py` \n\u003cbr/\u003eEnter the path to the folder containing the pdfs you have highlighted (make sure that all the pdfs are in the same\nfolder). \n\u003cbr/\u003eEnter the output file name (the name of the docx file to be generated)\n\u003cbr/\u003eexample: `output`\nwill save the output docx file in the directory of the pdfs as `output.docx`\n\n## References\n\nhttps://stackoverflow.com/a/63686095","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmajd-kontar%2Fpdf-highlight-extractor","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fmajd-kontar%2Fpdf-highlight-extractor","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmajd-kontar%2Fpdf-highlight-extractor/lists"}