{"id":41855901,"url":"https://github.com/reezuleanu/pdf_deconstructor","last_synced_at":"2026-01-25T10:38:04.505Z","repository":{"id":291159337,"uuid":"976765910","full_name":"reezuleanu/pdf_deconstructor","owner":"reezuleanu","description":"Decompose a PDF file based on its headers for RAG ingestion.","archived":false,"fork":false,"pushed_at":"2025-05-02T18:49:23.000Z","size":14,"stargazers_count":0,"open_issues_count":3,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-05-02T19:37:43.388Z","etag":null,"topics":["pdf-document-processor","rag"],"latest_commit_sha":null,"homepage":"","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/reezuleanu.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,"zenodo":null}},"created_at":"2025-05-02T17:55:29.000Z","updated_at":"2025-05-02T18:50:23.000Z","dependencies_parsed_at":"2025-05-02T19:48:22.765Z","dependency_job_id":null,"html_url":"https://github.com/reezuleanu/pdf_deconstructor","commit_stats":null,"previous_names":["reezuleanu/pdf_deconstructor"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/reezuleanu/pdf_deconstructor","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/reezuleanu%2Fpdf_deconstructor","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/reezuleanu%2Fpdf_deconstructor/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/reezuleanu%2Fpdf_deconstructor/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/reezuleanu%2Fpdf_deconstructor/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/reezuleanu","download_url":"https://codeload.github.com/reezuleanu/pdf_deconstructor/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/reezuleanu%2Fpdf_deconstructor/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":28751816,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-01-25T10:25:12.305Z","status":"ssl_error","status_checked_at":"2026-01-25T10:25:11.933Z","response_time":113,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.5:443 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":["pdf-document-processor","rag"],"created_at":"2026-01-25T10:38:04.418Z","updated_at":"2026-01-25T10:38:04.492Z","avatar_url":"https://github.com/reezuleanu.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# PDF Deconstructor\nDecompose a PDF file based on its headers for RAG ingestion.\n\n## What it does\nIt takes a PDF file and converts it into a hierarchy of sections and subsections based on the headers inside the file, as well as extract all the links.\n\n## Main use\nThe intended use is to be part of a larger ingestion pipeline of unstructured data for RAG purposes.\n\n## How to use\n```py\nfrom pdf_deconstructor import Deconstructor as PDFDeconstructor\n\noutput = PDFDeconstructor.parse(\"file.pdf\", start_page=1)\n\n# to see extracted tree\nfor header in output.content:\n    print(header.tree())\n```\n\nEach header contains the raw text, markdown syntax text, and extracted links, as well as sub headers","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Freezuleanu%2Fpdf_deconstructor","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Freezuleanu%2Fpdf_deconstructor","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Freezuleanu%2Fpdf_deconstructor/lists"}