[{"data":1,"prerenderedAt":260},["ShallowReactive",2],{"repo-pdfminer-pdfminer.six-en":3,"i18n-pdfminer-pdfminer.six-en":257},{"mirrorPool":4,"detail":13,"relatedProjects":160},[5,9],{"key":6,"label":7,"base":8,"type":6},"github","mirror.github","https:\u002F\u002Fgithub.com\u002F",{"key":10,"label":11,"base":12,"type":10},"auto-proxy","mirror.autoProxy","https:\u002F\u002Fgithub.xxlab.tech\u002F",{"owner":14,"repo":15,"repoId":16,"repoUrl":17,"starCount":18,"language":19,"description":20,"languages":21,"screenshots":25,"homepage":26,"pushedAt":27,"ownerAvatar":28,"ownerName":14,"ownerBio":29,"lastSyncTime":30,"lastReleaseTime":31,"tags":32,"license":36,"category":37,"subgroup":38,"releases":39},"pdfminer","pdfminer.six",23465887,"https:\u002F\u002Fgithub.com\u002Fpdfminer\u002Fpdfminer.six",7039,"Python","Community maintained fork of pdfminer - we fathom PDF",{"Python":22,"Makefile":23,"Shell":24},99.6,0.4,0,[],"https:\u002F\u002Fpdfminersix.readthedocs.io","2026-03-13","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F22586632?v=4","we maintain pdfminer.six","2026-10-20T10:25:45.796776+00:00","2026-01-07T13:29:15Z",[33,34,35],"parser","pdf","python","MIT","development","PDF工具",[40,57,72,88,104,118,134,148],{"tag":41,"publishAt":31,"semVer":42,"prerelease":43,"assets":44},"20260107",[24,24,24],false,[45,51],{"fileName":46,"sizeMb":47,"sha256":48,"downloadCount":49,"originUrl":50},"pdfminer_six-20260107-py3-none-any.whl",6.29,"366585ba97e80dffa8f00cebe303d2f381884d8637af4ce422f1df3ef38111a9",352,"https:\u002F\u002Fgithub.com\u002Fpdfminer\u002Fpdfminer.six\u002Freleases\u002Fdownload\u002F20260107\u002Fpdfminer_six-20260107-py3-none-any.whl",{"fileName":52,"sizeMb":53,"sha256":54,"downloadCount":55,"originUrl":56},"pdfminer_six-20260107.tar.gz",8.12,"96bfd431e3577a55a0efd25676968ca4ce8fd5b53f14565f85716ff363889602",190,"https:\u002F\u002Fgithub.com\u002Fpdfminer\u002Fpdfminer.six\u002Freleases\u002Fdownload\u002F20260107\u002Fpdfminer_six-20260107.tar.gz",{"tag":58,"publishAt":59,"semVer":60,"prerelease":43,"assets":61},"20251230","2025-12-30T15:49:15Z",[24,24,24],[62,67],{"fileName":63,"sizeMb":47,"sha256":64,"downloadCount":65,"originUrl":66},"pdfminer_six-20251230-py3-none-any.whl","9ff2e3466a7dfc6de6fd779478850b6b7c2d9e9405aa2a5869376a822771f485",132,"https:\u002F\u002Fgithub.com\u002Fpdfminer\u002Fpdfminer.six\u002Freleases\u002Fdownload\u002F20251230\u002Fpdfminer_six-20251230-py3-none-any.whl",{"fileName":68,"sizeMb":53,"sha256":69,"downloadCount":70,"originUrl":71},"pdfminer_six-20251230.tar.gz","e8f68a14c57e00c2d7276d26519ea64be1b48f91db1cdc776faa80528ca06c1e",19,"https:\u002F\u002Fgithub.com\u002Fpdfminer\u002Fpdfminer.six\u002Freleases\u002Fdownload\u002F20251230\u002Fpdfminer_six-20251230.tar.gz",{"tag":73,"publishAt":74,"semVer":75,"prerelease":43,"assets":76},"20251229","2025-12-29T20:16:06Z",[24,24,24],[77,83],{"fileName":78,"sizeMb":79,"sha256":80,"downloadCount":81,"originUrl":82},"pdfminer_six-20251229-py3-none-any.whl",5.36,"3d1856f8d013ad733dc4e55c8c68553eaf5e17ced3d3e2122a2f59a2a3e9c675",12,"https:\u002F\u002Fgithub.com\u002Fpdfminer\u002Fpdfminer.six\u002Freleases\u002Fdownload\u002F20251229\u002Fpdfminer_six-20251229-py3-none-any.whl",{"fileName":84,"sizeMb":85,"sha256":86,"downloadCount":70,"originUrl":87},"pdfminer_six-20251229.tar.gz",7.12,"60c6d8745de92e02a06cff7edc82125aed70b88f139cde72c3a22a45d044c6c6","https:\u002F\u002Fgithub.com\u002Fpdfminer\u002Fpdfminer.six\u002Freleases\u002Fdownload\u002F20251229\u002Fpdfminer_six-20251229.tar.gz",{"tag":89,"publishAt":90,"semVer":91,"prerelease":43,"assets":92},"20251228","2025-12-28T14:32:28Z",[24,24,24],[93,98],{"fileName":94,"sizeMb":79,"sha256":95,"downloadCount":96,"originUrl":97},"pdfminer_six-20251228-py3-none-any.whl","d365fb6dc41c5b8d04bd63622a3f468be24f3fecf54107e36e2451cf1bde870a",67,"https:\u002F\u002Fgithub.com\u002Fpdfminer\u002Fpdfminer.six\u002Freleases\u002Fdownload\u002F20251228\u002Fpdfminer_six-20251228-py3-none-any.whl",{"fileName":99,"sizeMb":100,"sha256":101,"downloadCount":102,"originUrl":103},"pdfminer_six-20251228.tar.gz",7.05,"5972b2babc5dd576a58634023b47e41ee827b505e36793cbfe37ac899000a1fb",6,"https:\u002F\u002Fgithub.com\u002Fpdfminer\u002Fpdfminer.six\u002Freleases\u002Fdownload\u002F20251228\u002Fpdfminer_six-20251228.tar.gz",{"tag":105,"publishAt":106,"semVer":107,"prerelease":43,"assets":108},"20251227","2025-12-27T20:16:25Z",[24,24,24],[109,114],{"fileName":110,"sizeMb":79,"sha256":111,"downloadCount":112,"originUrl":113},"pdfminer_six-20251227-py3-none-any.whl","7a41f668a74fdde9e3a6c9265e400992a8312224fb6dbc13ee8861111e330d36",7,"https:\u002F\u002Fgithub.com\u002Fpdfminer\u002Fpdfminer.six\u002Freleases\u002Fdownload\u002F20251227\u002Fpdfminer_six-20251227-py3-none-any.whl",{"fileName":115,"sizeMb":100,"sha256":116,"downloadCount":102,"originUrl":117},"pdfminer_six-20251227.tar.gz","1d98781cf884d7274c694e742a94ffe6326ee11ee7ea79e73e1e75c4c74d91eb","https:\u002F\u002Fgithub.com\u002Fpdfminer\u002Fpdfminer.six\u002Freleases\u002Fdownload\u002F20251227\u002Fpdfminer_six-20251227.tar.gz",{"tag":119,"publishAt":120,"semVer":121,"prerelease":43,"assets":122},"20251107","2025-11-07T20:01:12Z",[24,24,24],[123,128],{"fileName":124,"sizeMb":79,"sha256":125,"downloadCount":126,"originUrl":127},"pdfminer_six-20251107-py3-none-any.whl","c09df33e4cbe6b26b2a79248a4ffcccafaa5c5d39c9fff0e6e81567f165b5401",124,"https:\u002F\u002Fgithub.com\u002Fpdfminer\u002Fpdfminer.six\u002Freleases\u002Fdownload\u002F20251107\u002Fpdfminer_six-20251107-py3-none-any.whl",{"fileName":129,"sizeMb":130,"sha256":131,"downloadCount":132,"originUrl":133},"pdfminer_six-20251107.tar.gz",7.04,"5fb0c553799c591777f22c0c72b77fc2522d7d10c70654e25f4c5f1fd996e008",31,"https:\u002F\u002Fgithub.com\u002Fpdfminer\u002Fpdfminer.six\u002Freleases\u002Fdownload\u002F20251107\u002Fpdfminer_six-20251107.tar.gz",{"tag":135,"publishAt":136,"semVer":137,"prerelease":43,"assets":138},"20250506","2025-05-06T16:17:03Z",[24,24,24],[139,144],{"fileName":140,"sizeMb":79,"sha256":141,"downloadCount":142,"originUrl":143},"pdfminer_six-20250506-py3-none-any.whl","",227,"https:\u002F\u002Fgithub.com\u002Fpdfminer\u002Fpdfminer.six\u002Freleases\u002Fdownload\u002F20250506\u002Fpdfminer_six-20250506-py3-none-any.whl",{"fileName":145,"sizeMb":100,"sha256":141,"downloadCount":146,"originUrl":147},"pdfminer_six-20250506.tar.gz",96,"https:\u002F\u002Fgithub.com\u002Fpdfminer\u002Fpdfminer.six\u002Freleases\u002Fdownload\u002F20250506\u002Fpdfminer_six-20250506.tar.gz",{"tag":149,"publishAt":150,"semVer":151,"prerelease":43,"assets":152},"20250416","2025-04-16T09:43:44Z",[24,24,24],[153,157],{"fileName":154,"sizeMb":79,"sha256":141,"downloadCount":155,"originUrl":156},"pdfminer_six-20250416-py3-none-any.whl",139,"https:\u002F\u002Fgithub.com\u002Fpdfminer\u002Fpdfminer.six\u002Freleases\u002Fdownload\u002F20250416\u002Fpdfminer_six-20250416-py3-none-any.whl",{"fileName":158,"sizeMb":130,"sha256":141,"downloadCount":70,"originUrl":159},"pdfminer_six-20250416.tar.gz","https:\u002F\u002Fgithub.com\u002Fpdfminer\u002Fpdfminer.six\u002Freleases\u002Fdownload\u002F20250416\u002Fpdfminer_six-20250416.tar.gz",[161,186,202,219,231,244],{"owner":162,"repo":163,"repoId":164,"category":165,"subgroup":38,"language":166,"tags":167,"starCount":175,"ownerUid":176,"latestTag":177,"platforms":178,"lastReleaseTime":183,"downloadCount":184,"description":185},"storytold","pdfcraft",1398086162,"tools","Rust",[168,169,34,170,171,172,173,174],"document-processing","documents","pdf-generation","pdf-processing","pdf-tools","pdf-viewer","rust",17952,76897702,"v0.14.0",[179,180,181,182],"windows","mac","linux","other","2026-10-25T13:56:05Z",96532,"PdfCraft is an open-source PDF reader and editor rewritten from scratch in pure Rust, following the Acrobat workflow with reading, organizing, merging, splitting and securing PDFs, threaded comments, no account and no telemetry across desktop and the browser.",{"owner":187,"repo":188,"repoId":189,"category":37,"subgroup":38,"language":19,"tags":190,"starCount":195,"ownerUid":196,"latestTag":197,"platforms":198,"lastReleaseTime":199,"downloadCount":200,"description":201},"Kozea","WeasyPrint",2179572,[191,192,193,34,35,194],"converter","css","html","weasyprint",9709,870325,"v70.0",[179],"2026-09-08T12:31:06Z",5713,"WeasyPrint is a Python visual rendering engine that turns HTML and CSS into PDF, ideal for producing reports, invoices, and tickets, with a CSS layout engine designed for pagination and no browser engine dependency.",{"owner":203,"repo":203,"repoId":204,"category":165,"subgroup":38,"language":205,"tags":206,"starCount":212,"ownerUid":213,"latestTag":214,"platforms":215,"lastReleaseTime":216,"downloadCount":217,"description":218},"pdfcpu",94702367,"Go",[207,208,209,210,34,211,172],"cli","go","golang","golang-library","pdf-files",8887,53127365,"v0.16.4",[179,180,181,182],"2026-10-27T21:17:38Z",200,"A PDF processing library and command-line tool written in Go, supporting validation, optimization, encryption, signing, document assembly, and content extraction.",{"owner":220,"repo":221,"repoId":222,"category":165,"subgroup":38,"language":19,"tags":223,"starCount":224,"ownerUid":225,"latestTag":226,"platforms":227,"lastReleaseTime":228,"downloadCount":229,"description":230},"happycola233","tchMaterial-parser",676833692,[35],6968,91878264,"v4.4",[179,180],"2026-10-07T06:21:11Z",56,"tchMaterial-parser is a Python-based downloader with a cross-platform GUI for the National Smart Education Platform of China, letting users batch-parse and download PDF textbooks with automatic naming and bookmarking.",{"owner":232,"repo":232,"repoId":233,"category":37,"subgroup":38,"language":234,"tags":235,"starCount":237,"ownerUid":238,"latestTag":239,"platforms":240,"lastReleaseTime":241,"downloadCount":242,"description":243},"qpdf",4539167,"C++",[34,236],"pdf-document-processor",5459,1812112,"v12.4.2",[179,180,181,182],"2026-09-27T00:01:39Z",20175,"A content-preserving PDF document transformer and C++ library, supporting linearization, encryption, splitting, and merging of PDF files.",{"owner":245,"repo":246,"repoId":247,"category":165,"subgroup":38,"language":248,"tags":249,"starCount":250,"ownerUid":251,"latestTag":252,"platforms":253,"lastReleaseTime":254,"downloadCount":255,"description":256},"wuwangzhang1216","congcong-school",1208023113,"TypeScript",[],1103,60851473,"v1.7.3-ios-resources",[182],"2026-10-26T16:38:46Z",391,"Congcong School is a free, open-source learning platform for grades 1-6 covering math, Chinese, English, and science, playable in the browser with full TTS narration and AI-graded stories.",{"description":258,"readmeHtml":259},"pdfminer.six is a pure Python tool for extracting information from PDF documents, focused on text data analysis — it recovers text plus its position, font, and color, and can also pull images, forms, and outlines.","\u003Ch2 id=\"project-overview\">Project Overview\u003C\u002Fh2>\u003Cp>pdfminer.six is a community maintained fork of the original PDFMiner for extracting information from PDF documents, with a focus on getting and analyzing text data. It pulls page text directly from the PDF's internal structure and can also recover exact position, font, and color of each string; the codebase is modular so every component can be swapped for custom pipelines.\u003C\u002Fp>\n\u003Ctable>\n\u003Cthead>\n\u003Ctr>\n\u003Cth>Item\u003C\u002Fth>\n\u003Cth>Value\u003C\u002Fth>\n\u003C\u002Ftr>\n\u003C\u002Fthead>\n\u003Ctbody>\u003Ctr>\n\u003Ctd>Platform\u003C\u002Ftd>\n\u003Ctd>cross-platform (pure Python)\u003C\u002Ftd>\n\u003C\u002Ftr>\n\u003Ctr>\n\u003Ctd>Language\u003C\u002Ftd>\n\u003Ctd>Python 3.10+\u003C\u002Ftd>\n\u003C\u002Ftr>\n\u003Ctr>\n\u003Ctd>License\u003C\u002Ftd>\n\u003Ctd>MIT\u003C\u002Ftd>\n\u003C\u002Ftr>\n\u003Ctr>\n\u003Ctd>CLI tool\u003C\u002Ftd>\n\u003Ctd>pdf2txt.py\u003C\u002Ftd>\n\u003C\u002Ftr>\n\u003C\u002Ftbody>\u003C\u002Ftable>\n\u003Cblockquote>\n\u003Cp>Mine text, positions, fonts, and colors out of PDFs in pure Python.\u003C\u002Fp>\n\u003C\u002Fblockquote>\n\u003Ch2 id=\"key-features\">Key Features\u003C\u002Fh2>\u003Cul>\n\u003Cli>\u003Cstrong>Text extraction\u003C\u002Fstrong>: parses the PDF internals to pull text straight off pages\u003C\u002Fli>\n\u003Cli>\u003Cstrong>Layout analysis\u003C\u002Fstrong>: automatically analyzes layout, reporting position, font, and color\u003C\u002Fli>\n\u003Cli>\u003Cstrong>Multiple outputs\u003C\u002Fstrong>: export content as text, HTML, or hOCR\u003C\u002Fli>\n\u003Cli>\u003Cstrong>Image extraction\u003C\u002Fstrong>: pulls embedded JPG, PNG, TIFF, and JBIG2 images\u003C\u002Fli>\n\u003Cli>\u003Cstrong>CJK and vertical writing\u003C\u002Fstrong>: supports Chinese, Japanese, Korean, and vertical text\u003C\u002Fli>\n\u003Cli>\u003Cstrong>Encrypted documents\u003C\u002Fstrong>: decrypts PDFs protected with RC4 or AES\u003C\u002Fli>\n\u003Cli>\u003Cstrong>Form extraction\u003C\u002Fstrong>: reads AcroForm interactive form data\u003C\u002Fli>\n\u003Cli>\u003Cstrong>Outline extraction\u003C\u002Fstrong>: recovers the table of contents and tagged contents\u003C\u002Fli>\n\u003C\u002Ful>\n\u003Ch2 id=\"target-audience\">Target Audience\u003C\u002Fh2>\u003Cul>\n\u003Cli>Document automation and RPA developers\u003C\u002Fli>\n\u003Cli>Engineering teams digitizing archives and analytics data\u003C\u002Fli>\n\u003Cli>Internationalization projects handling multilingual PDFs\u003C\u002Fli>\n\u003Cli>Developers building their own PDF parsing components\u003C\u002Fli>\n\u003C\u002Ful>\n\u003Ch2 id=\"quick-start\">Quick Start\u003C\u002Fh2>\u003Col>\n\u003Cli>Install\u003C\u002Fli>\n\u003C\u002Fol>\n\u003Cdiv class=\"code-block\">\u003Cpre>\u003Ccode class=\"hljs language-bash\">pip install pdfminer.six\u003C\u002Fcode>\u003C\u002Fpre>\u003C\u002Fdiv>\u003Col start=\"2\">\n\u003Cli>Extract text from the command line\u003C\u002Fli>\n\u003C\u002Fol>\n\u003Cdiv class=\"code-block\">\u003Cpre>\u003Ccode class=\"hljs language-bash\">pdf2txt.py example.pdf\u003C\u002Fcode>\u003C\u002Fpre>\u003C\u002Fdiv>\u003Col start=\"3\">\n\u003Cli>Call the high-level API in code\u003C\u002Fli>\n\u003C\u002Fol>\n\u003Cdiv class=\"code-block\">\u003Cpre>\u003Ccode class=\"hljs language-python\">from pdfminer.high_level import extract_text\n\ntext = extract_text('example.pdf')\nprint(text)\u003C\u002Fcode>\u003C\u002Fpre>\u003C\u002Fdiv>\u003Col start=\"4\">\n\u003Cli>Install the extra dependency when images are needed\u003C\u002Fli>\n\u003C\u002Fol>\n\u003Cdiv class=\"code-block\">\u003Cpre>\u003Ccode class=\"hljs language-bash\">pip install 'pdfminer.six[image]'\u003C\u002Fcode>\u003C\u002Fpre>\u003C\u002Fdiv>\u003Ch2 id=\"core-advantages\">Core Advantages\u003C\u002Fh2>\u003Cul>\n\u003Cli>\u003Cstrong>Pure Python\u003C\u002Fstrong>: no system-level PDF library needed, deployment stays simple\u003C\u002Fli>\n\u003Cli>\u003Cstrong>Deep detail\u003C\u002Fstrong>: beyond raw text, positions, fonts, and colors are available\u003C\u002Fli>\n\u003Cli>\u003Cstrong>Modular design\u003C\u002Fstrong>: parsing, interpretation, and rendering components are independently replaceable\u003C\u002Fli>\n\u003C\u002Ful>\n\u003Ch2 id=\"system-requirements\">System Requirements\u003C\u002Fh2>\u003Ctable>\n\u003Cthead>\n\u003Ctr>\n\u003Cth>Item\u003C\u002Fth>\n\u003Cth>Requirement\u003C\u002Fth>\n\u003C\u002Ftr>\n\u003C\u002Fthead>\n\u003Ctbody>\u003Ctr>\n\u003Ctd>Language\u003C\u002Ftd>\n\u003Ctd>Python 3.10 or newer\u003C\u002Ftd>\n\u003C\u002Ftr>\n\u003Ctr>\n\u003Ctd>OS\u003C\u002Ftd>\n\u003Ctd>cross-platform\u003C\u002Ftd>\n\u003C\u002Ftr>\n\u003Ctr>\n\u003Ctd>Optional deps\u003C\u002Ftd>\n\u003Ctd>image extra required for picture extraction\u003C\u002Ftd>\n\u003C\u002Ftr>\n\u003C\u002Ftbody>\u003C\u002Ftable>\n\u003Ch2 id=\"notes\">Notes\u003C\u002Fh2>\u003Cul>\n\u003Cli>\u003Cstrong>Scans do not work\u003C\u002Fstrong>: image-only scanned PDFs have no text layer and need OCR alongside\u003C\u002Fli>\n\u003Cli>\u003Cstrong>Complex layouts need tuning\u003C\u002Fstrong>: tables and multi-column pages may require custom layout analysis\u003C\u002Fli>\n\u003C\u002Ful>\n",1793197923155]