https://channel.nostses.icuhttps://channel.nostses.icu/posts/1394https://channel.nostses.icu/posts/1394Tue, 19 Aug 2025 18:12:26 GMT<div class="tgme_widget_message_forwarded_from accent_color">Forwarded from <a class="tgme_widget_message_forwarded_from_name" href="https://t.me/iokhk/6580" target="_blank" rel="noopener"><span>OKHK <i class="emoji" style="background-image:url('//telegram.org/img/emoji/40/F09F9180.png')"><b>👀</b></i></span></a></div><b><u>Marker - 将 PDF 快速转换为 Markdown / JSON / HTML</u></b><br /><br /><a href="https://github.com/datalab-to/marker" target="_blank" rel="noopener" title="https://github.com/datalab-to/marker">https://github.com/datalab-to/marker</a><br /><br />API 版本： <a href="https://github.com/adithya-s-k/marker-api" target="_blank" rel="noopener" title="https://github.com/adithya-s-k/marker-api">https://github.com/adithya-s-k/marker-api</a><br /><br />Marker 是一个将 PDF 文档转换为 Markdown、JSON 和 HTML 的工具，快速准确。<br /><br /><b>● </b>支持多种文件格式（PDF、图像、PPTX、DOCX、XLSX、HTML、EPUB）和多种语言的转换<br /><b>● </b>格式化表格、公式、内联数学、链接、引用和代码块<br /><b>● </b>提取和保存图像，移除页眉 / 页脚等<br /><b>● </b>可通过 LLM 提高转换准确度<br /><br /><a href="/search/result?q=%23PDF" title="#PDF">#PDF</a> <a href="/search/result?q=%23Tool" title="#Tool">#Tool</a> <a href="/search/result?q=%23GitHub" title="#GitHub">#GitHub</a><a class="tgme_widget_message_link_preview" href="https://github.com/datalab-to/marker" target="_blank" rel="noopener" title="Convert PDF to markdown + JSON quickly with high accuracy - datalab-to/marker"> <div class="link_preview_site_name accent_color">GitHub</div> <img class="link_preview_image" alt="GitHub - datalab-to/marker: Convert PDF to markdown + JSON quickly with high accuracy" src="/static/https://cdn4.telesco.pe/file/brQqsw23YLBzx_JfjzSDXUsHUZxZ4Z4GGTU9U7fZRYArsjjKI_pIB8U8WSNDc8wYEvLFPYBMwB1M3hBZa_a9xcVsccpmDVfXXf_j2K9BLEBpkb1yPwc094-gaJf6EuXF8oleoLUZcdXgq95a6xKYPEXNnI0jF0rfB9yZ3qUpzZ2bpHJwbpDlE2tnAdfVaHJ7c8EE2IEXF7HjJnA-50zagOP1N9R1-LSdpeuV15qSZUuuMwGyMn97is-nRf-G10dHuSf0Ts-q_RbgzdZnryvfXfcW_H8QwfPzArXVeZ3_YjOhNI6xWwceek-XftCblXX5JupjNegfZQSur06LzykZKQ.jpg" width="1200" height="630" loading="eager" /> <div class="link_preview_title">GitHub - datalab-to/marker: Convert PDF to markdown + JSON quickly with high accuracy</div> <div class="link_preview_description">Convert PDF to markdown + JSON quickly with high accuracy - datalab-to/marker</div> </a>https://channel.nostses.icu/posts/1218https://channel.nostses.icu/posts/1218Wed, 30 Jul 2025 17:42:22 GMT<div class="tgme_widget_message_forwarded_from accent_color">Forwarded from <a class="tgme_widget_message_forwarded_from_name" href="https://t.me/HardcoreOpenAI/680" target="_blank" rel="noopener"><span>硬核开源智库</span></a></div><a href="https://github.com/docling-project/docling-parse" target="_blank" rel="noopener" title="Docling Parse">Docling Parse</a>：专注于从程序化 PDF 中高效提取文本、路径及位图资源的轻量级工具包。 <br /><br />• 支持字符、单词及行级别文本坐标输出，精准定位文本内容，方便深度版面分析与可视化<br />• 同时提取路径和位图图像，满足复杂文档结构解析需求 <br />• 内置可交互式可视化脚本，便于快速验证与展示解析效果 <br />• 性能显著提升，最新版本解析速度较初版快 5-10 倍，适合大规模文档处理 <br />• Python 包即装即用，支持命令行和编程接口，灵活集成到多种工作流 <br />• 完全开源，MIT 许可，社区活跃，持续更新与优化，便于二次开发和创新 <br />• 适合科研、文档数字化、信息抽取等多场景应用，助力文档数据智能化转型 <br /><br />基于程序化 PDF 结构，精细提取多层级文本单元与图形元素，融合性能优化与可视化，推动 PDF 内容的结构化理解与应用扩展。<br /><a href="/search/result?q=%23%E8%B5%84%E6%BA%90%E5%8F%82%E8%80%83" title="#资源参考">#资源参考</a> <a href="/search/result?q=%23%E5%B7%A5%E5%85%B7" title="#工具">#工具</a> <a href="/search/result?q=%23AI" title="#AI">#AI</a> <a href="/search/result?q=%23PDF%E6%8F%90%E5%8F%96%E6%96%87%E6%9C%AC%E5%9B%BE%E5%83%8F" title="#PDF提取文本图像">#PDF提取文本图像</a><a class="tgme_widget_message_link_preview" href="https://github.com/docling-project/docling-parse" target="_blank" rel="noopener" title="Simple package to extract text with coordinates from programmatic PDFs - docling-project/docling-parse"> <div class="link_preview_site_name accent_color">GitHub</div> <img class="link_preview_image" alt="GitHub - docling-project/docling-parse: Simple package to extract text with coordinates from programmatic PDFs" src="/static/https://cdn4.telesco.pe/file/apPvRvyocBiZMf2oeUtY5bL0Sg67RiKB0JnxiIs4D6ITvBfUkgZ9hTQ5egMoe1cp2-8QKSD4cuRraTi902yiBJDGTTiiHkz_jv3FfbGb_M6BQLbuUMfPr0LNovwyyDv2RZ2gxtAHrvp3On9w1Es1LQovF8thiDlwhW9OW2SINnm_Y0pLJnah59xqueMO1TZ1Zx9eA4TKehaxOhgIUjzchnJepPhRWKcncEEsr91--Bss5Kaw55XP9pdfdxosogPgI48ZW9nXrJ0J4sBh3KzUWjYJLMGPwFxxEqfJn7qs5v3_P4B1jLrjmKrY_89ANY7ohR451vnGX0D2-dWWIPfviA.jpg" width="1200" height="630" loading="eager" /> <div class="link_preview_title">GitHub - docling-project/docling-parse: Simple package to extract text with coordinates from programmatic PDFs</div> <div class="link_preview_description">Simple package to extract text with coordinates from programmatic PDFs - docling-project/docling-parse</div> </a>