{"id":103843,"date":"2026-09-11T12:49:12","date_gmt":"2026-09-11T04:49:12","guid":{"rendered":"https:\/\/www.wsisp.com\/helps\/103843.html"},"modified":"2026-09-11T12:49:12","modified_gmt":"2026-09-11T04:49:12","slug":"mineru-%e6%96%87%e6%a1%a3%e8%a7%a3%e6%9e%90%e6%9c%8d%e5%8a%a1","status":"publish","type":"post","link":"https:\/\/www.wsisp.com\/helps\/103843.html","title":{"rendered":"MinerU \u6587\u6863\u89e3\u6790\u670d\u52a1"},"content":{"rendered":"<h3>\u6458\u8981<\/h3>\n<p>\u672c\u6587\u7cfb\u7edf\u62c6\u89e3 MinerU \u6280\u672f\u6808\u7684\u5b8c\u6574\u67b6\u6784&#xff0c;\u6df1\u5165\u8bb2\u89e3\u5176\u6838\u5fc3\u5b9a\u4f4d\u3001\u5de5\u4f5c\u539f\u7406\u4e0e\u5404\u6a21\u5757\u7684\u534f\u4f5c\u65b9\u5f0f\u3002\u6587\u7ae0\u4ece\u5e95\u5c42\u539f\u7406\u51fa\u53d1&#xff0c;\u901a\u8fc7\u5b8c\u6574\u7684\u5b9e\u6218\u6848\u4f8b&#xff0c;\u6f14\u793a\u6587\u6863\u89e3\u6790\u3001\u5185\u5bb9\u63d0\u53d6\u3001\u6570\u636e\u6d41\u8f6c\u4e0e\u5e38\u89c1\u95ee\u9898\u6392\u67e5&#xff0c;\u5e76\u8fdb\u4e00\u6b65\u63a2\u8ba8 API \u96c6\u6210\u3001Docker \u5bb9\u5668\u5316\u3001\u6027\u80fd\u4f18\u5316\u7b49\u8fdb\u9636\u6269\u5c55\u3002\u65e0\u8bba\u4f60\u662f\u521d\u5b66\u8005\u8fd8\u662f\u6709\u4e00\u5b9a\u7ecf\u9a8c\u7684\u5f00\u53d1\u8005&#xff0c;\u90fd\u80fd\u4ece\u4e2d\u5efa\u7acb\u5bf9 MinerU \u7684\u6df1\u5ea6\u8ba4\u77e5\u3002<\/p>\n<p>\u5173\u952e\u8bcd&#xff1a;MinerU&#xff1b;\u6587\u6863\u89e3\u6790&#xff1b;PDF \u63d0\u53d6&#xff1b;OCR&#xff1b;\u6df1\u5ea6\u5b66\u4e60&#xff1b;\u5927\u6a21\u578b<\/p>\n<h3>\u76ee\u5f55<\/h3>\n<ul>\n<li>1. \u5f15\u8a00<\/li>\n<li>2. MinerU \u6280\u672f\u6808\u5168\u666f\n<ul>\n<li>2.1 \u4ec0\u4e48\u662f MinerU<\/li>\n<li>2.2 \u6838\u5fc3\u7ec4\u4ef6\u7684\u5b9a\u4f4d<\/li>\n<li>2.3 \u4e3a\u4ec0\u4e48\u9009\u62e9 MinerU<\/li>\n<\/ul>\n<\/li>\n<li>3. \u6df1\u5165\u6587\u6863\u89e3\u6790\u5f15\u64ce\n<ul>\n<li>3.1 \u89e3\u6790\u6d41\u7a0b\u7684\u6838\u5fc3\u601d\u60f3<\/li>\n<li>3.2 \u4e0e\u4f20\u7edf\u89e3\u6790\u5de5\u5177\u7684\u5bf9\u6bd4<\/li>\n<li>3.3 \u6838\u5fc3\u64cd\u4f5c<\/li>\n<li>3.4 \u6a21\u578b\u4f53\u7cfb\u7684\u4f5c\u7528<\/li>\n<\/ul>\n<\/li>\n<li>4. \u6df1\u5165\u5185\u5bb9\u63d0\u53d6\u6a21\u5757\n<ul>\n<li>4.1 \u63d0\u53d6\u6a21\u5757\u662f\u4ec0\u4e48<\/li>\n<li>4.2 \u7248\u9762\u5206\u6790\u673a\u5236<\/li>\n<li>4.3 \u8868\u683c\u4e0e\u516c\u5f0f\u8bc6\u522b<\/li>\n<li>4.4 \u4e0e\u4e0b\u6e38\u4efb\u52a1\u7684\u6570\u636e\u4ea4\u4e92<\/li>\n<\/ul>\n<\/li>\n<li>5. \u6df1\u5165 OCR \u8bc6\u522b\n<ul>\n<li>5.1 OCR \u7684\u6838\u5fc3\u601d\u60f3<\/li>\n<li>5.2 \u6587\u672c\u68c0\u6d4b\u4e0e\u8bc6\u522b<\/li>\n<li>5.3 \u4e0e\u6df1\u5ea6\u5b66\u4e60\u6846\u67b6\u7684\u96c6\u6210<\/li>\n<li>5.4 \u9002\u7528\u4e0e\u4e0d\u9002\u7528\u573a\u666f<\/li>\n<\/ul>\n<\/li>\n<li>6. \u6df1\u5165\u8f93\u51fa\u4e0e\u5e8f\u5217\u5316\n<ul>\n<li>6.1 \u591a\u683c\u5f0f\u8f93\u51fa\u7684\u8bbe\u8ba1<\/li>\n<li>6.2 \u7ed3\u6784\u5316\u6570\u636e\u6d41\u8f6c<\/li>\n<li>6.3 \u73af\u5883\u53d8\u91cf\u4e0e\u914d\u7f6e<\/li>\n<\/ul>\n<\/li>\n<li>7. MinerU \u5168\u6d41\u7a0b\u6570\u636e\u6d41\u8f6c\n<ul>\n<li>7.1 \u4e00\u6b21\u5b8c\u6574\u89e3\u6790\u7684\u751f\u547d\u5468\u671f<\/li>\n<li>7.2 \u76ee\u5f55\u7ed3\u6784\u89c4\u8303<\/li>\n<li>7.3 \u914d\u7f6e\u7ba1\u7406<\/li>\n<\/ul>\n<\/li>\n<li>8. MinerU \u5b9e\u6218&#xff1a;\u6784\u5efa\u4e00\u4e2a\u6587\u6863\u89e3\u6790\u670d\u52a1\n<ul>\n<li>8.1 \u540e\u7aef\u5b9e\u73b0<\/li>\n<li>8.2 \u524d\u7aef\u5b9e\u73b0<\/li>\n<li>8.3 \u542f\u52a8\u4e0e\u8054\u8c03<\/li>\n<li>8.4 \u5e38\u89c1\u95ee\u9898\u4e0e\u6392\u67e5<\/li>\n<\/ul>\n<\/li>\n<li>9. MinerU \u7684\u8fdb\u9636\u4e0e\u6269\u5c55\n<ul>\n<li>9.1 \u4e0e LLM \u96c6\u6210<\/li>\n<li>9.2 API \u670d\u52a1\u5316<\/li>\n<li>9.3 \u90e8\u7f72\u4e0e\u8fd0\u7ef4<\/li>\n<\/ul>\n<\/li>\n<li>10. \u603b\u7ed3\u4e0e\u5c55\u671b\n<ul>\n<li>10.1 \u6838\u5fc3\u4f18\u52bf\u56de\u987e<\/li>\n<li>10.2 MinerU \u7684\u5c40\u9650\u6027<\/li>\n<li>10.3 \u672a\u6765\u53d1\u5c55\u65b9\u5411<\/li>\n<li>10.4 \u5b66\u4e60\u8def\u7ebf\u5efa\u8bae<\/li>\n<li>10.5 \u8fdb\u4e00\u6b65\u5b66\u4e60\u8d44\u6e90\u63a8\u8350<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<h3>1. \u5f15\u8a00<\/h3>\n<p>\u5728\u4eba\u5de5\u667a\u80fd\u4e0e\u5927\u6a21\u578b\u65f6\u4ee3&#xff0c;\u6d77\u91cf\u7684 PDF\u3001\u626b\u63cf\u4ef6\u3001\u7f51\u9875\u7b49\u975e\u7ed3\u6784\u5316\u6587\u6863\u4e2d\u8574\u542b\u7740\u5de8\u5927\u7684\u77e5\u8bc6\u4ef7\u503c\u3002\u7136\u800c&#xff0c;\u5982\u4f55\u9ad8\u6548\u3001\u51c6\u786e\u5730\u5c06\u8fd9\u4e9b\u6587\u6863\u8f6c\u5316\u4e3a\u7ed3\u6784\u5316\u7684 Markdown\u3001JSON \u6570\u636e&#xff0c;\u4e00\u76f4\u662f RAG&#xff08;\u68c0\u7d22\u589e\u5f3a\u751f\u6210&#xff09;\u3001\u77e5\u8bc6\u5e93\u6784\u5efa\u3001\u6587\u6863\u667a\u80fd\u5904\u7406\u7b49\u573a\u666f\u7684\u6838\u5fc3\u75db\u70b9\u3002<\/p>\n<p>MinerU \u6b63\u662f\u4e3a\u89e3\u51b3\u8fd9\u4e00\u75db\u70b9\u800c\u751f\u7684\u5f00\u6e90\u6587\u6863\u89e3\u6790\u5de5\u5177\u3002\u5b83\u7531 OpenDataLab \u56e2\u961f\u5f00\u53d1&#xff0c;\u57fa\u4e8e\u6df1\u5ea6\u5b66\u4e60\u6a21\u578b&#xff0c;\u80fd\u591f\u5c06\u590d\u6742\u7684 PDF \u6587\u6863&#xff08;\u5305\u62ec\u626b\u63cf\u4ef6\u3001\u516c\u5f0f\u3001\u8868\u683c\u3001\u591a\u680f\u6392\u7248&#xff09;\u9ad8\u8d28\u91cf\u5730\u8f6c\u6362\u4e3a Markdown \u548c JSON \u683c\u5f0f\u3002\u672c\u6587\u5c06\u4ece\u6700\u5e95\u5c42\u8bb2\u8d77&#xff0c;\u7cfb\u7edf\u62c6\u89e3 MinerU \u6280\u672f\u6808\u7684\u6bcf\u4e2a\u73af\u8282&#xff0c;\u5e76\u7ed9\u51fa\u5b8c\u6574\u7684\u5b9e\u6218\u793a\u4f8b&#xff0c;\u5e2e\u52a9\u4f60\u5efa\u7acb\u5bf9 MinerU \u7684\u6df1\u5ea6\u8ba4\u77e5\u3002<\/p>\n<h3>2. MinerU \u6280\u672f\u6808\u5168\u666f<\/h3>\n<h4>2.1 \u4ec0\u4e48\u662f MinerU<\/h4>\n<p>MinerU \u662f\u4e00\u5957\u57fa\u4e8e\u6df1\u5ea6\u5b66\u4e60\u7684\u6587\u6863\u89e3\u6790\u89e3\u51b3\u65b9\u6848&#xff0c;\u6838\u5fc3\u76ee\u6807\u662f\u5c06 PDF \u7b49\u975e\u7ed3\u6784\u5316\u6587\u6863\u8f6c\u6362\u4e3a\u7ed3\u6784\u5316\u7684 Markdown \u548c JSON\u3002\u5b83\u6574\u5408\u4e86\u7248\u9762\u5206\u6790\u3001OCR \u8bc6\u522b\u3001\u516c\u5f0f\u68c0\u6d4b\u3001\u8868\u683c\u8bc6\u522b\u3001\u9605\u8bfb\u987a\u5e8f\u8fd8\u539f\u7b49\u591a\u4e2a AI \u6a21\u578b&#xff0c;\u5f62\u6210\u4e00\u6761\u5b8c\u6574\u7684\u89e3\u6790\u6d41\u6c34\u7ebf\u3002<\/p>\n<p>  #mermaid-svg-X6QQ7MGLeFnVWVWP{font-family:\\&#8221;trebuchet ms\\&#8221;,verdana,arial,sans-serif;font-size:16px;fill:#333;}@keyframes edge-animation-frame{from{stroke-dashoffset:0;}}@keyframes dash{to{stroke-dashoffset:0;}}#mermaid-svg-X6QQ7MGLeFnVWVWP .edge-animation-slow{stroke-dasharray:9,5!important;stroke-dashoffset:900;animation:dash 50s linear infinite;stroke-linecap:round;}#mermaid-svg-X6QQ7MGLeFnVWVWP .edge-animation-fast{stroke-dasharray:9,5!important;stroke-dashoffset:900;animation:dash 20s linear infinite;stroke-linecap:round;}#mermaid-svg-X6QQ7MGLeFnVWVWP .error-icon{fill:#552222;}#mermaid-svg-X6QQ7MGLeFnVWVWP .error-text{fill:#552222;stroke:#552222;}#mermaid-svg-X6QQ7MGLeFnVWVWP .edge-thickness-normal{stroke-width:1px;}#mermaid-svg-X6QQ7MGLeFnVWVWP .edge-thickness-thick{stroke-width:3.5px;}#mermaid-svg-X6QQ7MGLeFnVWVWP .edge-pattern-solid{stroke-dasharray:0;}#mermaid-svg-X6QQ7MGLeFnVWVWP .edge-thickness-invisible{stroke-width:0;fill:none;}#mermaid-svg-X6QQ7MGLeFnVWVWP .edge-pattern-dashed{stroke-dasharray:3;}#mermaid-svg-X6QQ7MGLeFnVWVWP .edge-pattern-dotted{stroke-dasharray:2;}#mermaid-svg-X6QQ7MGLeFnVWVWP .marker{fill:#333333;stroke:#333333;}#mermaid-svg-X6QQ7MGLeFnVWVWP .marker.cross{stroke:#333333;}#mermaid-svg-X6QQ7MGLeFnVWVWP svg{font-family:\\&#8221;trebuchet ms\\&#8221;,verdana,arial,sans-serif;font-size:16px;}#mermaid-svg-X6QQ7MGLeFnVWVWP p{margin:0;}#mermaid-svg-X6QQ7MGLeFnVWVWP .label{font-family:\\&#8221;trebuchet ms\\&#8221;,verdana,arial,sans-serif;color:#333;}#mermaid-svg-X6QQ7MGLeFnVWVWP .cluster-label text{fill:#333;}#mermaid-svg-X6QQ7MGLeFnVWVWP .cluster-label span{color:#333;}#mermaid-svg-X6QQ7MGLeFnVWVWP .cluster-label span p{background-color:transparent;}#mermaid-svg-X6QQ7MGLeFnVWVWP .label text,#mermaid-svg-X6QQ7MGLeFnVWVWP span{fill:#333;color:#333;}#mermaid-svg-X6QQ7MGLeFnVWVWP .node rect,#mermaid-svg-X6QQ7MGLeFnVWVWP .node circle,#mermaid-svg-X6QQ7MGLeFnVWVWP .node ellipse,#mermaid-svg-X6QQ7MGLeFnVWVWP .node polygon,#mermaid-svg-X6QQ7MGLeFnVWVWP .node path{fill:#ECECFF;stroke:#9370DB;stroke-width:1px;}#mermaid-svg-X6QQ7MGLeFnVWVWP .rough-node .label text,#mermaid-svg-X6QQ7MGLeFnVWVWP .node .label text,#mermaid-svg-X6QQ7MGLeFnVWVWP .image-shape .label,#mermaid-svg-X6QQ7MGLeFnVWVWP .icon-shape .label{text-anchor:middle;}#mermaid-svg-X6QQ7MGLeFnVWVWP .node .katex path{fill:#000;stroke:#000;stroke-width:1px;}#mermaid-svg-X6QQ7MGLeFnVWVWP .rough-node .label,#mermaid-svg-X6QQ7MGLeFnVWVWP .node .label,#mermaid-svg-X6QQ7MGLeFnVWVWP .image-shape .label,#mermaid-svg-X6QQ7MGLeFnVWVWP .icon-shape .label{text-align:center;}#mermaid-svg-X6QQ7MGLeFnVWVWP .node.clickable{cursor:pointer;}#mermaid-svg-X6QQ7MGLeFnVWVWP .root .anchor path{fill:#333333!important;stroke-width:0;stroke:#333333;}#mermaid-svg-X6QQ7MGLeFnVWVWP .arrowheadPath{fill:#333333;}#mermaid-svg-X6QQ7MGLeFnVWVWP .edgePath .path{stroke:#333333;stroke-width:2.0px;}#mermaid-svg-X6QQ7MGLeFnVWVWP .flowchart-link{stroke:#333333;fill:none;}#mermaid-svg-X6QQ7MGLeFnVWVWP .edgeLabel{background-color:rgba(232,232,232, 0.8);text-align:center;}#mermaid-svg-X6QQ7MGLeFnVWVWP .edgeLabel p{background-color:rgba(232,232,232, 0.8);}#mermaid-svg-X6QQ7MGLeFnVWVWP .edgeLabel rect{opacity:0.5;background-color:rgba(232,232,232, 0.8);fill:rgba(232,232,232, 0.8);}#mermaid-svg-X6QQ7MGLeFnVWVWP .labelBkg{background-color:rgba(232, 232, 232, 0.5);}#mermaid-svg-X6QQ7MGLeFnVWVWP .cluster rect{fill:#ffffde;stroke:#aaaa33;stroke-width:1px;}#mermaid-svg-X6QQ7MGLeFnVWVWP .cluster text{fill:#333;}#mermaid-svg-X6QQ7MGLeFnVWVWP .cluster span{color:#333;}#mermaid-svg-X6QQ7MGLeFnVWVWP div.mermaidTooltip{position:absolute;text-align:center;max-width:200px;padding:2px;font-family:\\&#8221;trebuchet ms\\&#8221;,verdana,arial,sans-serif;font-size:12px;background:hsl(80, 100%, 96.2745098039%);border:1px solid #aaaa33;border-radius:2px;pointer-events:none;z-index:100;}#mermaid-svg-X6QQ7MGLeFnVWVWP .flowchartTitleText{text-anchor:middle;font-size:18px;fill:#333;}#mermaid-svg-X6QQ7MGLeFnVWVWP rect.text{fill:none;stroke-width:0;}#mermaid-svg-X6QQ7MGLeFnVWVWP .icon-shape,#mermaid-svg-X6QQ7MGLeFnVWVWP .image-shape{background-color:rgba(232,232,232, 0.8);text-align:center;}#mermaid-svg-X6QQ7MGLeFnVWVWP .icon-shape p,#mermaid-svg-X6QQ7MGLeFnVWVWP .image-shape p{background-color:rgba(232,232,232, 0.8);padding:2px;}#mermaid-svg-X6QQ7MGLeFnVWVWP .icon-shape .label rect,#mermaid-svg-X6QQ7MGLeFnVWVWP .image-shape .label rect{opacity:0.5;background-color:rgba(232,232,232, 0.8);fill:rgba(232,232,232, 0.8);}#mermaid-svg-X6QQ7MGLeFnVWVWP .label-icon{display:inline-block;height:1em;overflow:visible;vertical-align:-0.125em;}#mermaid-svg-X6QQ7MGLeFnVWVWP .node .label-icon path{fill:currentColor;stroke:revert;stroke-width:revert;}#mermaid-svg-X6QQ7MGLeFnVWVWP :root{&#8211;mermaid-font-family:\\&#8221;trebuchet ms\\&#8221;,verdana,arial,sans-serif;}<\/p>\n<p>         <span class=\"edgeLabel\"><\/span><\/p>\n<p>         <span class=\"edgeLabel\"><\/span><\/p>\n<p>         <span class=\"edgeLabel\"><\/span><\/p>\n<p>         <span class=\"edgeLabel\"><\/span><\/p>\n<p>         <span class=\"edgeLabel\"><\/span><\/p>\n<p>         <span class=\"nodeLabel\"><\/p>\n<p>PDF \u6587\u6863\u8f93\u5165<\/p>\n<p><\/span><\/p>\n<p>         <span class=\"nodeLabel\"><\/p>\n<p>\u7248\u9762\u5206\u6790<\/p>\n<p><\/span><\/p>\n<p>         <span class=\"nodeLabel\"><\/p>\n<p>OCR \u8bc6\u522b<\/p>\n<p><\/span><\/p>\n<p>         <span class=\"nodeLabel\"><\/p>\n<p>\u516c\u5f0f \/ \u8868\u683c\u8bc6\u522b<\/p>\n<p><\/span><\/p>\n<p>         <span class=\"nodeLabel\"><\/p>\n<p>\u9605\u8bfb\u987a\u5e8f\u8fd8\u539f<\/p>\n<p><\/span><\/p>\n<p>         <span class=\"nodeLabel\"><\/p>\n<p>Markdown \/ JSON \u8f93\u51fa<\/p>\n<p><\/span><\/p>\n<h4>2.2 \u6838\u5fc3\u7ec4\u4ef6\u7684\u5b9a\u4f4d<\/h4>\n<table>\n<tr>\u7ec4\u4ef6\u5168\u79f0\u5b9a\u4f4d\u7c7b\u6bd4<\/tr>\n<tbody>\n<tr>\n<td>\u7248\u9762\u5206\u6790<\/td>\n<td>Layout Analysis<\/td>\n<td>\u8bc6\u522b\u6587\u6863\u4e2d\u7684\u6807\u9898\u3001\u6bb5\u843d\u3001\u56fe\u7247\u3001\u8868\u683c\u7b49\u533a\u57df<\/td>\n<td>\u5730\u56fe&#xff0c;\u6807\u6ce8\u6bcf\u4e2a\u533a\u57df<\/td>\n<\/tr>\n<tr>\n<td>OCR \u8bc6\u522b<\/td>\n<td>Optical Character Recognition<\/td>\n<td>\u8bc6\u522b\u626b\u63cf\u4ef6\u4e2d\u7684\u6587\u5b57<\/td>\n<td>\u773c\u775b&#xff0c;\u8bfb\u53d6\u56fe\u50cf\u4e2d\u7684\u6587\u5b57<\/td>\n<\/tr>\n<tr>\n<td>\u516c\u5f0f\u8bc6\u522b<\/td>\n<td>Formula Recognition<\/td>\n<td>\u5c06\u6570\u5b66\u516c\u5f0f\u8f6c\u4e3a LaTeX<\/td>\n<td>\u7ffb\u8bd1\u5b98&#xff0c;\u628a\u516c\u5f0f\u8f6c\u4e3a\u6807\u51c6\u8bed\u8a00<\/td>\n<\/tr>\n<tr>\n<td>\u8868\u683c\u8bc6\u522b<\/td>\n<td>Table Recognition<\/td>\n<td>\u5c06\u8868\u683c\u8f6c\u4e3a\u7ed3\u6784\u5316\u6570\u636e<\/td>\n<td>\u8bb0\u8d26\u5458&#xff0c;\u6574\u7406\u8868\u683c\u7ed3\u6784<\/td>\n<\/tr>\n<tr>\n<td>\u9605\u8bfb\u987a\u5e8f<\/td>\n<td>Reading Order<\/td>\n<td>\u8fd8\u539f\u6587\u6863\u7684\u903b\u8f91\u9605\u8bfb\u987a\u5e8f<\/td>\n<td>\u5bfc\u822a&#xff0c;\u51b3\u5b9a\u5148\u8bfb\u4ec0\u4e48\u540e\u8bfb\u4ec0\u4e48<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<h4>2.3 \u4e3a\u4ec0\u4e48\u9009\u62e9 MinerU<\/h4>\n<ul>\n<li>\u89e3\u6790\u8d28\u91cf\u9ad8&#xff1a;\u57fa\u4e8e\u6df1\u5ea6\u5b66\u4e60\u6a21\u578b&#xff0c;\u5bf9\u590d\u6742\u7248\u9762\u3001\u516c\u5f0f\u3001\u8868\u683c\u7684\u89e3\u6790\u6548\u679c\u8fdc\u8d85\u4f20\u7edf\u89c4\u5219\u5de5\u5177<\/li>\n<li>\u8f93\u51fa\u7ed3\u6784\u5316&#xff1a;\u76f4\u63a5\u8f93\u51fa Markdown \u548c JSON&#xff0c;\u5929\u7136\u9002\u914d RAG\u3001\u77e5\u8bc6\u5e93\u7b49\u4e0b\u6e38\u4efb\u52a1<\/li>\n<li>\u5f00\u6e90\u514d\u8d39&#xff1a;Apache 2.0 \u534f\u8bae&#xff0c;\u53ef\u81ea\u7531\u5546\u7528&#xff0c;\u793e\u533a\u6d3b\u8dc3<\/li>\n<li>\u591a\u8bed\u8a00\u652f\u6301&#xff1a;\u5185\u7f6e\u591a\u8bed\u8a00 OCR \u6a21\u578b&#xff0c;\u652f\u6301\u4e2d\u82f1\u6587\u6df7\u6392\u6587\u6863<\/li>\n<li>GPU \/ CPU \u53cc\u652f\u6301&#xff1a;\u65e2\u53ef\u5728 GPU \u4e0a\u9ad8\u901f\u89e3\u6790&#xff0c;\u4e5f\u53ef\u5728 CPU \u4e0a\u79bb\u7ebf\u8fd0\u884c<\/li>\n<\/ul>\n<h3>3. \u6df1\u5165\u6587\u6863\u89e3\u6790\u5f15\u64ce<\/h3>\n<h4>3.1 \u89e3\u6790\u6d41\u7a0b\u7684\u6838\u5fc3\u601d\u60f3<\/h4>\n<p>MinerU \u7684\u89e3\u6790\u5f15\u64ce\u91c7\u7528\u6d41\u6c34\u7ebf&#xff08;Pipeline&#xff09; \u67b6\u6784&#xff0c;\u5c06\u6587\u6863\u89e3\u6790\u62c6\u5206\u4e3a\u591a\u4e2a\u72ec\u7acb\u9636\u6bb5\u3002\u6bcf\u4e2a\u9636\u6bb5\u7531\u4e00\u4e2a\u6216\u591a\u4e2a\u6df1\u5ea6\u5b66\u4e60\u6a21\u578b\u8d1f\u8d23&#xff0c;\u524d\u4e00\u9636\u6bb5\u7684\u8f93\u51fa\u4f5c\u4e3a\u540e\u4e00\u9636\u6bb5\u7684\u8f93\u5165&#xff0c;\u6700\u7ec8\u6c47\u805a\u4e3a\u7ed3\u6784\u5316\u7ed3\u679c\u3002<\/p>\n<p><span class=\"token comment\"># MinerU \u89e3\u6790\u6d41\u7a0b\u793a\u610f<\/span><br \/>\n<span class=\"token keyword\">from<\/span> magic_pdf<span class=\"token punctuation\">.<\/span>data<span class=\"token punctuation\">.<\/span>data_reader_writer <span class=\"token keyword\">import<\/span> FileBasedDataWriter<br \/>\n<span class=\"token keyword\">from<\/span> magic_pdf<span class=\"token punctuation\">.<\/span>data<span class=\"token punctuation\">.<\/span>dataset <span class=\"token keyword\">import<\/span> PymuDocDataset<\/p>\n<p><span class=\"token comment\"># \u8bfb\u53d6 PDF \u6587\u6863<\/span><br \/>\ndataset <span class=\"token operator\">&#061;<\/span> PymuDocDataset<span class=\"token punctuation\">(<\/span>pdf_bytes<span class=\"token punctuation\">)<\/span><\/p>\n<p><span class=\"token comment\"># \u6267\u884c\u5b8c\u6574\u89e3\u6790\u6d41\u6c34\u7ebf<\/span><br \/>\nresult <span class=\"token operator\">&#061;<\/span> dataset<span class=\"token punctuation\">.<\/span>pipe_txt_mode<span class=\"token punctuation\">(<\/span><br \/>\n    model_json<span class=\"token operator\">&#061;<\/span>model_json<span class=\"token punctuation\">,<\/span>          <span class=\"token comment\"># \u6a21\u578b\u914d\u7f6e<\/span><br \/>\n    parse_mode<span class=\"token operator\">&#061;<\/span><span class=\"token string\">&#034;auto&#034;<\/span><span class=\"token punctuation\">,<\/span>              <span class=\"token comment\"># \u81ea\u52a8\u6a21\u5f0f<\/span><br \/>\n    output_writer<span class=\"token operator\">&#061;<\/span>output_writer<br \/>\n<span class=\"token punctuation\">)<\/span><\/p>\n<h4>3.2 \u4e0e\u4f20\u7edf\u89e3\u6790\u5de5\u5177\u7684\u5bf9\u6bd4<\/h4>\n<table>\n<tr>\u7ef4\u5ea6MinerUPyPDF2 \/ pdfplumber\u4f20\u7edf OCR \u5de5\u5177<\/tr>\n<tbody>\n<tr>\n<td>\u7248\u9762\u5206\u6790<\/td>\n<td>\u2705 \u6df1\u5ea6\u5b66\u4e60\u6a21\u578b<\/td>\n<td>\u274c \u65e0<\/td>\n<td>\u274c \u65e0<\/td>\n<\/tr>\n<tr>\n<td>\u516c\u5f0f\u8bc6\u522b<\/td>\n<td>\u2705 LaTeX \u8f93\u51fa<\/td>\n<td>\u274c \u4e0d\u652f\u6301<\/td>\n<td>\u274c \u4e0d\u652f\u6301<\/td>\n<\/tr>\n<tr>\n<td>\u8868\u683c\u8fd8\u539f<\/td>\n<td>\u2705 \u7ed3\u6784\u5316\u8f93\u51fa<\/td>\n<td>\u26a0\ufe0f \u7b80\u5355\u8868\u683c<\/td>\n<td>\u26a0\ufe0f \u6709\u9650<\/td>\n<\/tr>\n<tr>\n<td>\u9605\u8bfb\u987a\u5e8f<\/td>\n<td>\u2705 \u81ea\u52a8\u8fd8\u539f<\/td>\n<td>\u274c \u6309\u7269\u7406\u987a\u5e8f<\/td>\n<td>\u274c \u6309\u7269\u7406\u987a\u5e8f<\/td>\n<\/tr>\n<tr>\n<td>\u626b\u63cf\u4ef6\u652f\u6301<\/td>\n<td>\u2705 \u5185\u7f6e OCR<\/td>\n<td>\u274c \u4e0d\u652f\u6301<\/td>\n<td>\u2705 \u652f\u6301<\/td>\n<\/tr>\n<tr>\n<td>\u8f93\u51fa\u683c\u5f0f<\/td>\n<td>Markdown \/ JSON<\/td>\n<td>\u7eaf\u6587\u672c<\/td>\n<td>\u7eaf\u6587\u672c<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<h4>3.3 \u6838\u5fc3\u64cd\u4f5c<\/h4>\n<p><span class=\"token comment\"># \u5b89\u88c5 MinerU<\/span><br \/>\n<span class=\"token comment\"># pip install magic-pdf[full]<\/span><\/p>\n<p><span class=\"token keyword\">from<\/span> magic_pdf<span class=\"token punctuation\">.<\/span>data<span class=\"token punctuation\">.<\/span>data_reader_writer <span class=\"token keyword\">import<\/span> FileBasedDataWriter<br \/>\n<span class=\"token keyword\">from<\/span> magic_pdf<span class=\"token punctuation\">.<\/span>data<span class=\"token punctuation\">.<\/span>dataset <span class=\"token keyword\">import<\/span> PymuDocDataset<\/p>\n<p><span class=\"token comment\"># \u8bfb\u53d6 PDF \u6587\u4ef6<\/span><br \/>\npdf_bytes <span class=\"token operator\">&#061;<\/span> <span class=\"token builtin\">open<\/span><span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;document.pdf&#034;<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token string\">&#034;rb&#034;<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">.<\/span>read<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p><span class=\"token comment\"># \u521b\u5efa\u6570\u636e\u96c6\u5bf9\u8c61<\/span><br \/>\ndataset <span class=\"token operator\">&#061;<\/span> PymuDocDataset<span class=\"token punctuation\">(<\/span>pdf_bytes<span class=\"token punctuation\">)<\/span><\/p>\n<p><span class=\"token comment\"># \u6267\u884c\u89e3\u6790&#xff08;\u6587\u672c\u6a21\u5f0f&#xff09;<\/span><br \/>\nresult <span class=\"token operator\">&#061;<\/span> dataset<span class=\"token punctuation\">.<\/span>pipe_txt_mode<span class=\"token punctuation\">(<\/span><br \/>\n    model_json<span class=\"token operator\">&#061;<\/span>model_json<span class=\"token punctuation\">,<\/span><br \/>\n    parse_mode<span class=\"token operator\">&#061;<\/span><span class=\"token string\">&#034;auto&#034;<\/span><br \/>\n<span class=\"token punctuation\">)<\/span><\/p>\n<p><span class=\"token comment\"># \u83b7\u53d6 Markdown \u8f93\u51fa<\/span><br \/>\nmarkdown_content <span class=\"token operator\">&#061;<\/span> result<span class=\"token punctuation\">.<\/span>get_markdown<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p><span class=\"token comment\"># \u83b7\u53d6 JSON \u8f93\u51fa<\/span><br \/>\njson_content <span class=\"token operator\">&#061;<\/span> result<span class=\"token punctuation\">.<\/span>get_content_list<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><\/p>\n<h4>3.4 \u6a21\u578b\u4f53\u7cfb\u7684\u4f5c\u7528<\/h4>\n<p>MinerU \u7684\u89e3\u6790\u8d28\u91cf\u4f9d\u8d56\u4e8e\u5176\u80cc\u540e\u7684\u6a21\u578b\u4f53\u7cfb&#xff1a;<\/p>\n<ul>\n<li>\u7248\u9762\u5206\u6790\u6a21\u578b&#xff1a;\u57fa\u4e8e LayoutLMv3 \u7b49\u9884\u8bad\u7ec3\u6a21\u578b&#xff0c;\u8bc6\u522b\u6587\u6863\u4e2d\u7684\u6807\u9898\u3001\u6bb5\u843d\u3001\u56fe\u7247\u3001\u8868\u683c\u7b49\u533a\u57df<\/li>\n<li>\u516c\u5f0f\u68c0\u6d4b\u6a21\u578b&#xff1a;\u57fa\u4e8e YOLO \u7cfb\u5217\u68c0\u6d4b\u6a21\u578b&#xff0c;\u5b9a\u4f4d\u6587\u6863\u4e2d\u7684\u884c\u5185\u516c\u5f0f\u548c\u72ec\u7acb\u516c\u5f0f<\/li>\n<li>\u516c\u5f0f\u8bc6\u522b\u6a21\u578b&#xff1a;\u57fa\u4e8e Pix2Text \u7b49\u6a21\u578b&#xff0c;\u5c06\u516c\u5f0f\u56fe\u50cf\u8f6c\u4e3a LaTeX \u4ee3\u7801<\/li>\n<li>\u8868\u683c\u8bc6\u522b\u6a21\u578b&#xff1a;\u57fa\u4e8e StructEqTable \u7b49\u6a21\u578b&#xff0c;\u8fd8\u539f\u8868\u683c\u7684\u884c\u5217\u7ed3\u6784<\/li>\n<li>OCR \u6a21\u578b&#xff1a;\u57fa\u4e8e PaddleOCR \u7b49\u6a21\u578b&#xff0c;\u8bc6\u522b\u626b\u63cf\u4ef6\u4e2d\u7684\u6587\u5b57<\/li>\n<\/ul>\n<h3>4. \u6df1\u5165\u5185\u5bb9\u63d0\u53d6\u6a21\u5757<\/h3>\n<h4>4.1 \u63d0\u53d6\u6a21\u5757\u662f\u4ec0\u4e48<\/h4>\n<p>\u5185\u5bb9\u63d0\u53d6\u6a21\u5757\u662f MinerU \u7684\u6838\u5fc3&#xff0c;\u8d1f\u8d23\u5c06\u7248\u9762\u5206\u6790\u5f97\u5230\u7684\u533a\u57df\u4fe1\u606f\u8f6c\u5316\u4e3a\u771f\u6b63\u7684\u7ed3\u6784\u5316\u5185\u5bb9\u3002\u5b83\u51b3\u5b9a\u4e86\u6700\u7ec8\u8f93\u51fa\u7684 Markdown \u548c JSON \u7684\u8d28\u91cf\u3002<\/p>\n<h4>4.2 \u7248\u9762\u5206\u6790\u673a\u5236<\/h4>\n<p>\u7248\u9762\u5206\u6790\u662f\u5185\u5bb9\u63d0\u53d6\u7684\u7b2c\u4e00\u6b65\u3002MinerU \u5c06\u6587\u6863\u9875\u9762\u5212\u5206\u4e3a\u591a\u4e2a\u533a\u57df&#xff0c;\u6bcf\u4e2a\u533a\u57df\u6807\u6ce8\u5176\u7c7b\u578b&#xff08;\u6807\u9898\u3001\u6b63\u6587\u3001\u56fe\u7247\u3001\u8868\u683c\u3001\u516c\u5f0f\u7b49&#xff09;\u548c\u4f4d\u7f6e\u4fe1\u606f\u3002<\/p>\n<p><span class=\"token comment\"># \u7248\u9762\u5206\u6790\u7ed3\u679c\u793a\u610f<\/span><br \/>\n<span class=\"token punctuation\">{<\/span><br \/>\n  <span class=\"token string\">&#034;layout_dets&#034;<\/span><span class=\"token punctuation\">:<\/span> <span class=\"token punctuation\">[<\/span><br \/>\n    <span class=\"token punctuation\">{<\/span><br \/>\n      <span class=\"token string\">&#034;category_id&#034;<\/span><span class=\"token punctuation\">:<\/span> <span class=\"token number\">0<\/span><span class=\"token punctuation\">,<\/span>          <span class=\"token comment\"># \u6807\u9898<\/span><br \/>\n      <span class=\"token string\">&#034;bbox&#034;<\/span><span class=\"token punctuation\">:<\/span> <span class=\"token punctuation\">[<\/span><span class=\"token number\">72<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token number\">72<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token number\">540<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token number\">108<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token comment\"># \u4f4d\u7f6e\u5750\u6807<\/span><br \/>\n      <span class=\"token string\">&#034;score&#034;<\/span><span class=\"token punctuation\">:<\/span> <span class=\"token number\">0.98<\/span>              <span class=\"token comment\"># \u7f6e\u4fe1\u5ea6<\/span><br \/>\n    <span class=\"token punctuation\">}<\/span><span class=\"token punctuation\">,<\/span><br \/>\n    <span class=\"token punctuation\">{<\/span><br \/>\n      <span class=\"token string\">&#034;category_id&#034;<\/span><span class=\"token punctuation\">:<\/span> <span class=\"token number\">13<\/span><span class=\"token punctuation\">,<\/span>         <span class=\"token comment\"># \u8868\u683c<\/span><br \/>\n      <span class=\"token string\">&#034;bbox&#034;<\/span><span class=\"token punctuation\">:<\/span> <span class=\"token punctuation\">[<\/span><span class=\"token number\">72<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token number\">150<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token number\">540<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token number\">400<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">,<\/span><br \/>\n      <span class=\"token string\">&#034;score&#034;<\/span><span class=\"token punctuation\">:<\/span> <span class=\"token number\">0.95<\/span><br \/>\n    <span class=\"token punctuation\">}<\/span><br \/>\n  <span class=\"token punctuation\">]<\/span><br \/>\n<span class=\"token punctuation\">}<\/span><\/p>\n<h4>4.3 \u8868\u683c\u4e0e\u516c\u5f0f\u8bc6\u522b<\/h4>\n<p>\u8868\u683c\u548c\u516c\u5f0f\u662f\u6587\u6863\u89e3\u6790\u4e2d\u6700\u5177\u6311\u6218\u6027\u7684\u90e8\u5206\u3002MinerU \u901a\u8fc7\u4e13\u95e8\u7684\u6a21\u578b\u6765\u5904\u7406\u8fd9\u4e24\u7c7b\u5185\u5bb9&#xff1a;<\/p>\n<p><span class=\"token comment\"># \u8868\u683c\u8bc6\u522b\u7ed3\u679c\u793a\u610f<\/span><br \/>\n<span class=\"token punctuation\">{<\/span><br \/>\n  <span class=\"token string\">&#034;type&#034;<\/span><span class=\"token punctuation\">:<\/span> <span class=\"token string\">&#034;table&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n  <span class=\"token string\">&#034;table_body&#034;<\/span><span class=\"token punctuation\">:<\/span> <span class=\"token punctuation\">[<\/span><br \/>\n    <span class=\"token punctuation\">[<\/span><span class=\"token string\">&#034;\u59d3\u540d&#034;<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token string\">&#034;\u5e74\u9f84&#034;<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token string\">&#034;\u57ce\u5e02&#034;<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">,<\/span><br \/>\n    <span class=\"token punctuation\">[<\/span><span class=\"token string\">&#034;\u5f20\u4e09&#034;<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token string\">&#034;28&#034;<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token string\">&#034;\u5317\u4eac&#034;<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">,<\/span><br \/>\n    <span class=\"token punctuation\">[<\/span><span class=\"token string\">&#034;\u674e\u56db&#034;<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token string\">&#034;25&#034;<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token string\">&#034;\u4e0a\u6d77&#034;<\/span><span class=\"token punctuation\">]<\/span><br \/>\n  <span class=\"token punctuation\">]<\/span><br \/>\n<span class=\"token punctuation\">}<\/span><\/p>\n<p><span class=\"token comment\"># \u516c\u5f0f\u8bc6\u522b\u7ed3\u679c\u793a\u610f<\/span><br \/>\n<span class=\"token punctuation\">{<\/span><br \/>\n  <span class=\"token string\">&#034;type&#034;<\/span><span class=\"token punctuation\">:<\/span> <span class=\"token string\">&#034;equation&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n  <span class=\"token string\">&#034;latex&#034;<\/span><span class=\"token punctuation\">:<\/span> <span class=\"token string\">&#034;E &#061; mc^2&#034;<\/span><br \/>\n<span class=\"token punctuation\">}<\/span><\/p>\n<h4>4.4 \u4e0e\u4e0b\u6e38\u4efb\u52a1\u7684\u6570\u636e\u4ea4\u4e92<\/h4>\n<p>MinerU \u8f93\u51fa\u7684\u7ed3\u6784\u5316\u6570\u636e\u53ef\u4ee5\u76f4\u63a5\u5bf9\u63a5\u4e0b\u6e38\u4efb\u52a1&#xff1a;<\/p>\n<ul>\n<li>RAG \u68c0\u7d22&#xff1a;\u5c06 Markdown \u5206\u5757\u540e\u5411\u91cf\u5316&#xff0c;\u6784\u5efa\u77e5\u8bc6\u5e93<\/li>\n<li>\u77e5\u8bc6\u56fe\u8c31&#xff1a;\u4ece JSON \u4e2d\u63d0\u53d6\u5b9e\u4f53\u548c\u5173\u7cfb<\/li>\n<li>\u6587\u6863\u95ee\u7b54&#xff1a;\u5c06\u7ed3\u6784\u5316\u5185\u5bb9\u4f5c\u4e3a\u4e0a\u4e0b\u6587\u8f93\u5165\u7ed9 LLM<\/li>\n<li>\u6570\u636e\u5165\u5e93&#xff1a;\u5c06\u8868\u683c\u6570\u636e\u76f4\u63a5\u5199\u5165\u6570\u636e\u5e93<\/li>\n<\/ul>\n<h3>5. \u6df1\u5165 OCR \u8bc6\u522b<\/h3>\n<h4>5.1 OCR \u7684\u6838\u5fc3\u601d\u60f3<\/h4>\n<p>OCR&#xff08;\u5149\u5b66\u5b57\u7b26\u8bc6\u522b&#xff09;\u662f MinerU \u5904\u7406\u626b\u63cf\u4ef6\u548c\u56fe\u7247\u578b PDF \u7684\u5173\u952e\u80fd\u529b\u3002\u5b83\u57fa\u4e8e\u6df1\u5ea6\u5b66\u4e60\u6a21\u578b&#xff0c;\u5c06\u56fe\u50cf\u4e2d\u7684\u6587\u5b57\u533a\u57df\u68c0\u6d4b\u51fa\u6765\u5e76\u8bc6\u522b\u4e3a\u53ef\u7f16\u8f91\u7684\u6587\u672c\u3002<\/p>\n<h4>5.2 \u6587\u672c\u68c0\u6d4b\u4e0e\u8bc6\u522b<\/h4>\n<p>MinerU \u7684 OCR \u6d41\u7a0b\u5206\u4e3a\u4e24\u4e2a\u9636\u6bb5&#xff1a;<\/p>\n<li>\u6587\u672c\u68c0\u6d4b&#xff1a;\u5b9a\u4f4d\u56fe\u50cf\u4e2d\u6240\u6709\u6587\u5b57\u533a\u57df\u7684\u4f4d\u7f6e<\/li>\n<li>\u6587\u672c\u8bc6\u522b&#xff1a;\u5c06\u68c0\u6d4b\u5230\u7684\u6587\u5b57\u533a\u57df\u8bc6\u522b\u4e3a\u6587\u672c\u5185\u5bb9<\/li>\n<p><span class=\"token comment\"># OCR \u6d41\u7a0b\u793a\u610f<\/span><br \/>\n<span class=\"token comment\"># \u68c0\u6d4b\u9636\u6bb5&#xff1a;\u627e\u5230\u6587\u5b57\u533a\u57df<\/span><br \/>\ntext_regions <span class=\"token operator\">&#061;<\/span> detector<span class=\"token punctuation\">.<\/span>detect<span class=\"token punctuation\">(<\/span>image<span class=\"token punctuation\">)<\/span><\/p>\n<p><span class=\"token comment\"># \u8bc6\u522b\u9636\u6bb5&#xff1a;\u8bc6\u522b\u6bcf\u4e2a\u533a\u57df\u7684\u6587\u5b57<\/span><br \/>\n<span class=\"token keyword\">for<\/span> region <span class=\"token keyword\">in<\/span> text_regions<span class=\"token punctuation\">:<\/span><br \/>\n    text <span class=\"token operator\">&#061;<\/span> recognizer<span class=\"token punctuation\">.<\/span>recognize<span class=\"token punctuation\">(<\/span>image<span class=\"token punctuation\">,<\/span> region<span class=\"token punctuation\">)<\/span><br \/>\n    <span class=\"token keyword\">print<\/span><span class=\"token punctuation\">(<\/span>text<span class=\"token punctuation\">)<\/span><\/p>\n<h4>5.3 \u4e0e\u6df1\u5ea6\u5b66\u4e60\u6846\u67b6\u7684\u96c6\u6210<\/h4>\n<p>MinerU \u7684 OCR \u80fd\u529b\u57fa\u4e8e PaddleOCR \u7b49\u6210\u719f\u6846\u67b6&#xff0c;\u5e76\u9488\u5bf9\u6587\u6863\u573a\u666f\u8fdb\u884c\u4e86\u4f18\u5316&#xff1a;<\/p>\n<ul>\n<li>\u591a\u8bed\u8a00\u652f\u6301&#xff1a;\u5185\u7f6e\u4e2d\u82f1\u6587\u7b49\u591a\u8bed\u8a00\u6a21\u578b<\/li>\n<li>\u7248\u9762\u611f\u77e5&#xff1a;\u7ed3\u5408\u7248\u9762\u5206\u6790\u7ed3\u679c&#xff0c;\u63d0\u5347\u590d\u6742\u7248\u9762\u7684\u8bc6\u522b\u51c6\u786e\u7387<\/li>\n<li>\u516c\u5f0f\u611f\u77e5&#xff1a;\u8bc6\u522b\u5230\u516c\u5f0f\u533a\u57df\u65f6&#xff0c;\u81ea\u52a8\u5207\u6362\u5230\u516c\u5f0f\u8bc6\u522b\u6a21\u578b<\/li>\n<\/ul>\n<h4>5.4 \u9002\u7528\u4e0e\u4e0d\u9002\u7528\u573a\u666f<\/h4>\n<table>\n<tr>\u573a\u666f\u662f\u5426\u9002\u5408\u539f\u56e0<\/tr>\n<tbody>\n<tr>\n<td>\u626b\u63cf\u7248 PDF<\/td>\n<td>\u2705 \u9002\u5408<\/td>\n<td>\u5185\u7f6e OCR&#xff0c;\u8bc6\u522b\u51c6\u786e\u7387\u9ad8<\/td>\n<\/tr>\n<tr>\n<td>\u56fe\u7247\u578b PDF<\/td>\n<td>\u2705 \u9002\u5408<\/td>\n<td>\u81ea\u52a8\u68c0\u6d4b\u5e76\u8bc6\u522b\u56fe\u7247\u4e2d\u7684\u6587\u5b57<\/td>\n<\/tr>\n<tr>\n<td>\u5370\u5237\u4f53\u6587\u6863<\/td>\n<td>\u2705 \u9002\u5408<\/td>\n<td>\u8bc6\u522b\u51c6\u786e\u7387\u6781\u9ad8<\/td>\n<\/tr>\n<tr>\n<td>\u624b\u5199\u6587\u6863<\/td>\n<td>\u26a0\ufe0f \u6709\u9650<\/td>\n<td>\u8bc6\u522b\u51c6\u786e\u7387\u53d6\u51b3\u4e8e\u624b\u5199\u8d28\u91cf<\/td>\n<\/tr>\n<tr>\n<td>\u4f4e\u5206\u8fa8\u7387\u626b\u63cf\u4ef6<\/td>\n<td>\u26a0\ufe0f \u6709\u9650<\/td>\n<td>\u5efa\u8bae\u5148\u505a\u56fe\u50cf\u589e\u5f3a<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<h3>6. \u6df1\u5165\u8f93\u51fa\u4e0e\u5e8f\u5217\u5316<\/h3>\n<h4>6.1 \u591a\u683c\u5f0f\u8f93\u51fa\u7684\u8bbe\u8ba1<\/h4>\n<p>MinerU \u652f\u6301\u591a\u79cd\u8f93\u51fa\u683c\u5f0f&#xff0c;\u6ee1\u8db3\u4e0d\u540c\u4e0b\u6e38\u4efb\u52a1\u7684\u9700\u6c42&#xff1a;<\/p>\n<ul>\n<li>Markdown&#xff1a;\u9002\u5408\u4eba\u7c7b\u9605\u8bfb\u548c RAG \u5206\u5757<\/li>\n<li>JSON&#xff1a;\u9002\u5408\u7a0b\u5e8f\u5316\u5904\u7406\u548c\u7ed3\u6784\u5316\u5b58\u50a8<\/li>\n<li>\u4e2d\u7ee7\u6587\u4ef6&#xff1a;\u4fdd\u7559\u5b8c\u6574\u7684\u4e2d\u95f4\u89e3\u6790\u7ed3\u679c&#xff0c;\u4fbf\u4e8e\u8c03\u8bd5\u548c\u4e8c\u6b21\u5f00\u53d1<\/li>\n<\/ul>\n<h4>6.2 \u7ed3\u6784\u5316\u6570\u636e\u6d41\u8f6c<\/h4>\n<p><span class=\"token comment\">\/\/ MinerU JSON \u8f93\u51fa\u793a\u4f8b<\/span><br \/>\n<span class=\"token punctuation\">{<\/span><br \/>\n  <span class=\"token string-property property\">&#034;pdf_info&#034;<\/span><span class=\"token operator\">:<\/span> <span class=\"token punctuation\">{<\/span><br \/>\n    <span class=\"token string-property property\">&#034;page_count&#034;<\/span><span class=\"token operator\">:<\/span> <span class=\"token number\">10<\/span><span class=\"token punctuation\">,<\/span><br \/>\n    <span class=\"token string-property property\">&#034;title&#034;<\/span><span class=\"token operator\">:<\/span> <span class=\"token string\">&#034;\u793a\u4f8b\u6587\u6863&#034;<\/span><br \/>\n  <span class=\"token punctuation\">}<\/span><span class=\"token punctuation\">,<\/span><br \/>\n  <span class=\"token string-property property\">&#034;content_list&#034;<\/span><span class=\"token operator\">:<\/span> <span class=\"token punctuation\">[<\/span><br \/>\n    <span class=\"token punctuation\">{<\/span><br \/>\n      <span class=\"token string-property property\">&#034;type&#034;<\/span><span class=\"token operator\">:<\/span> <span class=\"token string\">&#034;text&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n      <span class=\"token string-property property\">&#034;text&#034;<\/span><span class=\"token operator\">:<\/span> <span class=\"token string\">&#034;\u8fd9\u662f\u6b63\u6587\u5185\u5bb9&#034;<\/span><br \/>\n    <span class=\"token punctuation\">}<\/span><span class=\"token punctuation\">,<\/span><br \/>\n    <span class=\"token punctuation\">{<\/span><br \/>\n      <span class=\"token string-property property\">&#034;type&#034;<\/span><span class=\"token operator\">:<\/span> <span class=\"token string\">&#034;table&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n      <span class=\"token string-property property\">&#034;table_body&#034;<\/span><span class=\"token operator\">:<\/span> <span class=\"token punctuation\">[<\/span><br \/>\n        <span class=\"token punctuation\">[<\/span><span class=\"token string\">&#034;\u52171&#034;<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token string\">&#034;\u52172&#034;<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">,<\/span><br \/>\n        <span class=\"token punctuation\">[<\/span><span class=\"token string\">&#034;\u503c1&#034;<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token string\">&#034;\u503c2&#034;<\/span><span class=\"token punctuation\">]<\/span><br \/>\n      <span class=\"token punctuation\">]<\/span><br \/>\n    <span class=\"token punctuation\">}<\/span><span class=\"token punctuation\">,<\/span><br \/>\n    <span class=\"token punctuation\">{<\/span><br \/>\n      <span class=\"token string-property property\">&#034;type&#034;<\/span><span class=\"token operator\">:<\/span> <span class=\"token string\">&#034;equation&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n      <span class=\"token string-property property\">&#034;latex&#034;<\/span><span class=\"token operator\">:<\/span> <span class=\"token string\">&#034;x^2 &#043; y^2 &#061; z^2&#034;<\/span><br \/>\n    <span class=\"token punctuation\">}<\/span><br \/>\n  <span class=\"token punctuation\">]<\/span><br \/>\n<span class=\"token punctuation\">}<\/span><\/p>\n<h4>6.3 \u73af\u5883\u53d8\u91cf\u4e0e\u914d\u7f6e<\/h4>\n<p><span class=\"token comment\"># .env \u6587\u4ef6<\/span><br \/>\n<span class=\"token comment\"># \u6a21\u578b\u914d\u7f6e<\/span><br \/>\n<span class=\"token assign-left variable\">MINERU_MODEL_DIR<\/span><span class=\"token operator\">&#061;<\/span>\/path\/to\/models<br \/>\n<span class=\"token assign-left variable\">MINERU_DEVICE<\/span><span class=\"token operator\">&#061;<\/span>cuda          <span class=\"token comment\"># cuda \/ cpu<\/span><br \/>\n<span class=\"token assign-left variable\">MINERU_OCR_ENGINE<\/span><span class=\"token operator\">&#061;<\/span>paddle    <span class=\"token comment\"># paddle \/ tesseract<\/span><\/p>\n<p><span class=\"token comment\"># \u89e3\u6790\u914d\u7f6e<\/span><br \/>\n<span class=\"token assign-left variable\">MINERU_PARSE_MODE<\/span><span class=\"token operator\">&#061;<\/span>auto      <span class=\"token comment\"># auto \/ txt \/ ocr<\/span><br \/>\n<span class=\"token assign-left variable\">MINERU_LANG<\/span><span class=\"token operator\">&#061;<\/span>ch              <span class=\"token comment\"># \u6587\u6863\u8bed\u8a00<\/span><\/p>\n<h3>7. MinerU \u5168\u6d41\u7a0b\u6570\u636e\u6d41\u8f6c<\/h3>\n<h4>7.1 \u4e00\u6b21\u5b8c\u6574\u89e3\u6790\u7684\u751f\u547d\u5468\u671f<\/h4>\n<p>     OCR \/ \u8bc6\u522b\u6a21\u578b<\/p>\n<p>     \u7248\u9762\u5206\u6790\u6a21\u578b<\/p>\n<p>     MinerU<\/p>\n<p>     \u7528\u6237<\/p>\n<p>      OCR \/ \u8bc6\u522b\u6a21\u578b<\/p>\n<p>      \u7248\u9762\u5206\u6790\u6a21\u578b<\/p>\n<p>      MinerU<\/p>\n<p>      \u7528\u6237<\/p>\n<p>  #mermaid-svg-WRhoRrKY6ywWXKAA{font-family:\\&#8221;trebuchet ms\\&#8221;,verdana,arial,sans-serif;font-size:16px;fill:#333;}@keyframes edge-animation-frame{from{stroke-dashoffset:0;}}@keyframes dash{to{stroke-dashoffset:0;}}#mermaid-svg-WRhoRrKY6ywWXKAA .edge-animation-slow{stroke-dasharray:9,5!important;stroke-dashoffset:900;animation:dash 50s linear infinite;stroke-linecap:round;}#mermaid-svg-WRhoRrKY6ywWXKAA .edge-animation-fast{stroke-dasharray:9,5!important;stroke-dashoffset:900;animation:dash 20s linear infinite;stroke-linecap:round;}#mermaid-svg-WRhoRrKY6ywWXKAA .error-icon{fill:#552222;}#mermaid-svg-WRhoRrKY6ywWXKAA .error-text{fill:#552222;stroke:#552222;}#mermaid-svg-WRhoRrKY6ywWXKAA .edge-thickness-normal{stroke-width:1px;}#mermaid-svg-WRhoRrKY6ywWXKAA .edge-thickness-thick{stroke-width:3.5px;}#mermaid-svg-WRhoRrKY6ywWXKAA .edge-pattern-solid{stroke-dasharray:0;}#mermaid-svg-WRhoRrKY6ywWXKAA .edge-thickness-invisible{stroke-width:0;fill:none;}#mermaid-svg-WRhoRrKY6ywWXKAA .edge-pattern-dashed{stroke-dasharray:3;}#mermaid-svg-WRhoRrKY6ywWXKAA .edge-pattern-dotted{stroke-dasharray:2;}#mermaid-svg-WRhoRrKY6ywWXKAA .marker{fill:#333333;stroke:#333333;}#mermaid-svg-WRhoRrKY6ywWXKAA .marker.cross{stroke:#333333;}#mermaid-svg-WRhoRrKY6ywWXKAA svg{font-family:\\&#8221;trebuchet ms\\&#8221;,verdana,arial,sans-serif;font-size:16px;}#mermaid-svg-WRhoRrKY6ywWXKAA p{margin:0;}#mermaid-svg-WRhoRrKY6ywWXKAA .actor{stroke:hsl(259.6261682243, 59.7765363128%, 87.9019607843%);fill:#ECECFF;}#mermaid-svg-WRhoRrKY6ywWXKAA text.actor&gt;tspan{fill:black;stroke:none;}#mermaid-svg-WRhoRrKY6ywWXKAA .actor-line{stroke:hsl(259.6261682243, 59.7765363128%, 87.9019607843%);}#mermaid-svg-WRhoRrKY6ywWXKAA .innerArc{stroke-width:1.5;stroke-dasharray:none;}#mermaid-svg-WRhoRrKY6ywWXKAA .messageLine0{stroke-width:1.5;stroke-dasharray:none;stroke:#333;}#mermaid-svg-WRhoRrKY6ywWXKAA .messageLine1{stroke-width:1.5;stroke-dasharray:2,2;stroke:#333;}#mermaid-svg-WRhoRrKY6ywWXKAA #arrowhead path{fill:#333;stroke:#333;}#mermaid-svg-WRhoRrKY6ywWXKAA .sequenceNumber{fill:white;}#mermaid-svg-WRhoRrKY6ywWXKAA #sequencenumber{fill:#333;}#mermaid-svg-WRhoRrKY6ywWXKAA #crosshead path{fill:#333;stroke:#333;}#mermaid-svg-WRhoRrKY6ywWXKAA .messageText{fill:#333;stroke:none;}#mermaid-svg-WRhoRrKY6ywWXKAA .labelBox{stroke:hsl(259.6261682243, 59.7765363128%, 87.9019607843%);fill:#ECECFF;}#mermaid-svg-WRhoRrKY6ywWXKAA .labelText,#mermaid-svg-WRhoRrKY6ywWXKAA .labelText&gt;tspan{fill:black;stroke:none;}#mermaid-svg-WRhoRrKY6ywWXKAA .loopText,#mermaid-svg-WRhoRrKY6ywWXKAA .loopText&gt;tspan{fill:black;stroke:none;}#mermaid-svg-WRhoRrKY6ywWXKAA .loopLine{stroke-width:2px;stroke-dasharray:2,2;stroke:hsl(259.6261682243, 59.7765363128%, 87.9019607843%);fill:hsl(259.6261682243, 59.7765363128%, 87.9019607843%);}#mermaid-svg-WRhoRrKY6ywWXKAA .note{stroke:#aaaa33;fill:#fff5ad;}#mermaid-svg-WRhoRrKY6ywWXKAA .noteText,#mermaid-svg-WRhoRrKY6ywWXKAA .noteText&gt;tspan{fill:black;stroke:none;}#mermaid-svg-WRhoRrKY6ywWXKAA .activation0{fill:#f4f4f4;stroke:#666;}#mermaid-svg-WRhoRrKY6ywWXKAA .activation1{fill:#f4f4f4;stroke:#666;}#mermaid-svg-WRhoRrKY6ywWXKAA .activation2{fill:#f4f4f4;stroke:#666;}#mermaid-svg-WRhoRrKY6ywWXKAA .actorPopupMenu{position:absolute;}#mermaid-svg-WRhoRrKY6ywWXKAA .actorPopupMenuPanel{position:absolute;fill:#ECECFF;box-shadow:0px 8px 16px 0px rgba(0,0,0,0.2);filter:drop-shadow(3px 5px 2px rgb(0 0 0 \/ 0.4));}#mermaid-svg-WRhoRrKY6ywWXKAA .actor-man line{stroke:hsl(259.6261682243, 59.7765363128%, 87.9019607843%);fill:#ECECFF;}#mermaid-svg-WRhoRrKY6ywWXKAA .actor-man circle,#mermaid-svg-WRhoRrKY6ywWXKAA line{stroke:hsl(259.6261682243, 59.7765363128%, 87.9019607843%);fill:#ECECFF;stroke-width:2px;}#mermaid-svg-WRhoRrKY6ywWXKAA :root{&#8211;mermaid-font-family:\\&#8221;trebuchet ms\\&#8221;,verdana,arial,sans-serif;}<\/p>\n<p>   \u4e0a\u4f20 PDF \u6587\u6863<\/p>\n<p>   \u7248\u9762\u5206\u6790<\/p>\n<p>   \u533a\u57df\u6807\u6ce8\u7ed3\u679c<\/p>\n<p>   \u6587\u672c \/ \u516c\u5f0f \/ \u8868\u683c\u8bc6\u522b<\/p>\n<p>   \u8bc6\u522b\u7ed3\u679c<\/p>\n<p>   \u9605\u8bfb\u987a\u5e8f\u8fd8\u539f<\/p>\n<p>   Markdown \/ JSON \u8f93\u51fa<\/p>\n<h4>7.2 \u76ee\u5f55\u7ed3\u6784\u89c4\u8303<\/h4>\n<p>\u4e00\u4e2a\u5178\u578b\u7684 MinerU \u9879\u76ee\u7ed3\u6784&#xff1a;<\/p>\n<p>mineru-project\/<br \/>\n\u251c\u2500\u2500 input\/                  # \u8f93\u5165\u6587\u6863<br \/>\n\u2502   \u2514\u2500\u2500 document.pdf<br \/>\n\u251c\u2500\u2500 output\/                 # \u8f93\u51fa\u7ed3\u679c<br \/>\n\u2502   \u251c\u2500\u2500 document.md<br \/>\n\u2502   \u2514\u2500\u2500 document.json<br \/>\n\u251c\u2500\u2500 models\/                 # \u6a21\u578b\u6587\u4ef6<br \/>\n\u2502   \u251c\u2500\u2500 layout\/<br \/>\n\u2502   \u251c\u2500\u2500 formula\/<br \/>\n\u2502   \u2514\u2500\u2500 ocr\/<br \/>\n\u251c\u2500\u2500 scripts\/                # \u811a\u672c<br \/>\n\u2502   \u251c\u2500\u2500 parse.py<br \/>\n\u2502   \u2514\u2500\u2500 batch_parse.py<br \/>\n\u2514\u2500\u2500 config\/<br \/>\n    \u2514\u2500\u2500 mineru.yaml<\/p>\n<h4>7.3 \u914d\u7f6e\u7ba1\u7406<\/h4>\n<p><span class=\"token comment\"># config\/mineru.yaml<\/span><br \/>\n<span class=\"token key atrule\">device<\/span><span class=\"token punctuation\">:<\/span> cuda<br \/>\n<span class=\"token key atrule\">model_dir<\/span><span class=\"token punctuation\">:<\/span> .\/models<\/p>\n<p><span class=\"token key atrule\">parse<\/span><span class=\"token punctuation\">:<\/span><br \/>\n  <span class=\"token key atrule\">mode<\/span><span class=\"token punctuation\">:<\/span> auto          <span class=\"token comment\"># auto \/ txt \/ ocr<\/span><br \/>\n  <span class=\"token key atrule\">lang<\/span><span class=\"token punctuation\">:<\/span> ch<br \/>\n  <span class=\"token key atrule\">formula_enable<\/span><span class=\"token punctuation\">:<\/span> <span class=\"token boolean important\">true<\/span><br \/>\n  <span class=\"token key atrule\">table_enable<\/span><span class=\"token punctuation\">:<\/span> <span class=\"token boolean important\">true<\/span><\/p>\n<p><span class=\"token key atrule\">output<\/span><span class=\"token punctuation\">:<\/span><br \/>\n  <span class=\"token key atrule\">format<\/span><span class=\"token punctuation\">:<\/span> <span class=\"token punctuation\">[<\/span>markdown<span class=\"token punctuation\">,<\/span> json<span class=\"token punctuation\">]<\/span><br \/>\n  <span class=\"token key atrule\">save_dir<\/span><span class=\"token punctuation\">:<\/span> .\/output<\/p>\n<h3>8. MinerU \u5b9e\u6218&#xff1a;\u6784\u5efa\u4e00\u4e2a\u6587\u6863\u89e3\u6790\u670d\u52a1<\/h3>\n<h4>8.1 \u540e\u7aef\u5b9e\u73b0<\/h4>\n<p><span class=\"token comment\"># server\/app.py<\/span><br \/>\n<span class=\"token keyword\">from<\/span> flask <span class=\"token keyword\">import<\/span> Flask<span class=\"token punctuation\">,<\/span> request<span class=\"token punctuation\">,<\/span> jsonify<br \/>\n<span class=\"token keyword\">from<\/span> magic_pdf<span class=\"token punctuation\">.<\/span>data<span class=\"token punctuation\">.<\/span>data_reader_writer <span class=\"token keyword\">import<\/span> FileBasedDataWriter<br \/>\n<span class=\"token keyword\">from<\/span> magic_pdf<span class=\"token punctuation\">.<\/span>data<span class=\"token punctuation\">.<\/span>dataset <span class=\"token keyword\">import<\/span> PymuDocDataset<br \/>\n<span class=\"token keyword\">import<\/span> os<\/p>\n<p>app <span class=\"token operator\">&#061;<\/span> Flask<span class=\"token punctuation\">(<\/span>__name__<span class=\"token punctuation\">)<\/span><\/p>\n<p><span class=\"token decorator annotation punctuation\">&#064;app<span class=\"token punctuation\">.<\/span>route<\/span><span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;\/api\/parse&#034;<\/span><span class=\"token punctuation\">,<\/span> methods<span class=\"token operator\">&#061;<\/span><span class=\"token punctuation\">[<\/span><span class=\"token string\">&#034;POST&#034;<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">)<\/span><br \/>\n<span class=\"token keyword\">def<\/span> <span class=\"token function\">parse_document<\/span><span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">:<\/span><br \/>\n    <span class=\"token triple-quoted-string string\">&#034;&#034;&#034;\u89e3\u6790\u4e0a\u4f20\u7684 PDF \u6587\u6863&#034;&#034;&#034;<\/span><br \/>\n    <span class=\"token keyword\">if<\/span> <span class=\"token string\">&#034;file&#034;<\/span> <span class=\"token keyword\">not<\/span> <span class=\"token keyword\">in<\/span> request<span class=\"token punctuation\">.<\/span>files<span class=\"token punctuation\">:<\/span><br \/>\n        <span class=\"token keyword\">return<\/span> jsonify<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">{<\/span><span class=\"token string\">&#034;error&#034;<\/span><span class=\"token punctuation\">:<\/span> <span class=\"token string\">&#034;\u672a\u4e0a\u4f20\u6587\u4ef6&#034;<\/span><span class=\"token punctuation\">}<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token number\">400<\/span><\/p>\n<p>    <span class=\"token builtin\">file<\/span> <span class=\"token operator\">&#061;<\/span> request<span class=\"token punctuation\">.<\/span>files<span class=\"token punctuation\">[<\/span><span class=\"token string\">&#034;file&#034;<\/span><span class=\"token punctuation\">]<\/span><br \/>\n    <span class=\"token keyword\">if<\/span> <span class=\"token keyword\">not<\/span> <span class=\"token builtin\">file<\/span><span class=\"token punctuation\">.<\/span>filename<span class=\"token punctuation\">.<\/span>endswith<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;.pdf&#034;<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">:<\/span><br \/>\n        <span class=\"token keyword\">return<\/span> jsonify<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">{<\/span><span class=\"token string\">&#034;error&#034;<\/span><span class=\"token punctuation\">:<\/span> <span class=\"token string\">&#034;\u4ec5\u652f\u6301 PDF \u6587\u4ef6&#034;<\/span><span class=\"token punctuation\">}<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token number\">400<\/span><\/p>\n<p>    <span class=\"token keyword\">try<\/span><span class=\"token punctuation\">:<\/span><br \/>\n        <span class=\"token comment\"># \u8bfb\u53d6 PDF \u5185\u5bb9<\/span><br \/>\n        pdf_bytes <span class=\"token operator\">&#061;<\/span> <span class=\"token builtin\">file<\/span><span class=\"token punctuation\">.<\/span>read<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p>        <span class=\"token comment\"># \u521b\u5efa\u6570\u636e\u96c6<\/span><br \/>\n        dataset <span class=\"token operator\">&#061;<\/span> PymuDocDataset<span class=\"token punctuation\">(<\/span>pdf_bytes<span class=\"token punctuation\">)<\/span><\/p>\n<p>        <span class=\"token comment\"># \u6267\u884c\u89e3\u6790<\/span><br \/>\n        result <span class=\"token operator\">&#061;<\/span> dataset<span class=\"token punctuation\">.<\/span>pipe_txt_mode<span class=\"token punctuation\">(<\/span><br \/>\n            model_json<span class=\"token operator\">&#061;<\/span>model_json<span class=\"token punctuation\">,<\/span><br \/>\n            parse_mode<span class=\"token operator\">&#061;<\/span><span class=\"token string\">&#034;auto&#034;<\/span><br \/>\n        <span class=\"token punctuation\">)<\/span><\/p>\n<p>        <span class=\"token comment\"># \u8fd4\u56de\u7ed3\u679c<\/span><br \/>\n        <span class=\"token keyword\">return<\/span> jsonify<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">{<\/span><br \/>\n            <span class=\"token string\">&#034;markdown&#034;<\/span><span class=\"token punctuation\">:<\/span> result<span class=\"token punctuation\">.<\/span>get_markdown<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">,<\/span><br \/>\n            <span class=\"token string\">&#034;content_list&#034;<\/span><span class=\"token punctuation\">:<\/span> result<span class=\"token punctuation\">.<\/span>get_content_list<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><br \/>\n        <span class=\"token punctuation\">}<\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p>    <span class=\"token keyword\">except<\/span> Exception <span class=\"token keyword\">as<\/span> e<span class=\"token punctuation\">:<\/span><br \/>\n        <span class=\"token keyword\">return<\/span> jsonify<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">{<\/span><span class=\"token string\">&#034;error&#034;<\/span><span class=\"token punctuation\">:<\/span> <span class=\"token builtin\">str<\/span><span class=\"token punctuation\">(<\/span>e<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">}<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token number\">500<\/span><\/p>\n<p><span class=\"token keyword\">if<\/span> __name__ <span class=\"token operator\">&#061;&#061;<\/span> <span class=\"token string\">&#034;__main__&#034;<\/span><span class=\"token punctuation\">:<\/span><br \/>\n    app<\/p>\n<p><span class=\"token comment\">### 8.2 \u524d\u7aef\u5b9e\u73b0<\/span><\/p>\n<p>\u524d\u7aef\u4f7f\u7528\u539f\u751f HTML <span class=\"token operator\">&#043;<\/span> JavaScript \u6784\u5efa&#xff0c;\u5305\u542b\u6587\u4ef6\u4e0a\u4f20\u8868\u5355\u3001\u8c03\u7528\u540e\u7aef &#096;<span class=\"token operator\">\/<\/span>api<span class=\"token operator\">\/<\/span>parse&#096; \u63a5\u53e3\u7684 fetch \u903b\u8f91&#xff0c;\u4ee5\u53ca Markdown \u548c JSON \u7ed3\u679c\u7684\u5c55\u793a\u533a\u57df\u3002<\/p>\n<p>&#096;&#096;&#096;html<br \/>\n<span class=\"token operator\">&lt;<\/span>!<span class=\"token operator\">&#8211;<\/span><span class=\"token operator\">&#8211;<\/span> client<span class=\"token operator\">\/<\/span>index<span class=\"token punctuation\">.<\/span>html <span class=\"token operator\">&#8211;<\/span><span class=\"token operator\">&#8211;<\/span><span class=\"token operator\">&gt;<\/span><br \/>\n<span class=\"token operator\">&lt;<\/span>!DOCTYPE html<span class=\"token operator\">&gt;<\/span><br \/>\n<span class=\"token operator\">&lt;<\/span>html lang<span class=\"token operator\">&#061;<\/span><span class=\"token string\">&#034;zh-CN&#034;<\/span><span class=\"token operator\">&gt;<\/span><br \/>\n<span class=\"token operator\">&lt;<\/span>head<span class=\"token operator\">&gt;<\/span><br \/>\n  <span class=\"token operator\">&lt;<\/span>meta charset<span class=\"token operator\">&#061;<\/span><span class=\"token string\">&#034;UTF-8&#034;<\/span> <span class=\"token operator\">\/<\/span><span class=\"token operator\">&gt;<\/span><br \/>\n  <span class=\"token operator\">&lt;<\/span>meta name<span class=\"token operator\">&#061;<\/span><span class=\"token string\">&#034;viewport&#034;<\/span> content<span class=\"token operator\">&#061;<\/span><span class=\"token string\">&#034;width&#061;device-width, initial-scale&#061;1.0&#034;<\/span> <span class=\"token operator\">\/<\/span><span class=\"token operator\">&gt;<\/span><br \/>\n  <span class=\"token operator\">&lt;<\/span>title<span class=\"token operator\">&gt;<\/span>MinerU \u6587\u6863\u89e3\u6790\u670d\u52a1<span class=\"token operator\">&lt;<\/span><span class=\"token operator\">\/<\/span>title<span class=\"token operator\">&gt;<\/span><br \/>\n  <span class=\"token operator\">&lt;<\/span>style<span class=\"token operator\">&gt;<\/span><br \/>\n    <span class=\"token operator\">\/<\/span><span class=\"token operator\">*<\/span> \u57fa\u7840\u6837\u5f0f&#xff1a;\u5c45\u4e2d\u5e03\u5c40&#xff0c;\u5361\u7247\u5f0f\u8bbe\u8ba1 <span class=\"token operator\">*<\/span><span class=\"token operator\">\/<\/span><br \/>\n    body <span class=\"token punctuation\">{<\/span><br \/>\n      font<span class=\"token operator\">&#8211;<\/span>family<span class=\"token punctuation\">:<\/span> <span class=\"token string\">&#034;Microsoft YaHei&#034;<\/span><span class=\"token punctuation\">,<\/span> Arial<span class=\"token punctuation\">,<\/span> sans<span class=\"token operator\">&#8211;<\/span>serif<span class=\"token punctuation\">;<\/span><br \/>\n      <span class=\"token builtin\">max<\/span><span class=\"token operator\">&#8211;<\/span>width<span class=\"token punctuation\">:<\/span> 900px<span class=\"token punctuation\">;<\/span><br \/>\n      margin<span class=\"token punctuation\">:<\/span> 40px auto<span class=\"token punctuation\">;<\/span><br \/>\n      padding<span class=\"token punctuation\">:<\/span> <span class=\"token number\">0<\/span> 20px<span class=\"token punctuation\">;<\/span><br \/>\n      background<span class=\"token punctuation\">:<\/span> <span class=\"token comment\">#f5f7fa;<\/span><br \/>\n      color<span class=\"token punctuation\">:<\/span> <span class=\"token comment\">#333;<\/span><br \/>\n    <span class=\"token punctuation\">}<\/span><br \/>\n    h1 <span class=\"token punctuation\">{<\/span> text<span class=\"token operator\">&#8211;<\/span>align<span class=\"token punctuation\">:<\/span> center<span class=\"token punctuation\">;<\/span> color<span class=\"token punctuation\">:<\/span> <span class=\"token comment\">#2c3e50; }<\/span><br \/>\n    <span class=\"token punctuation\">.<\/span>card <span class=\"token punctuation\">{<\/span><br \/>\n      background<span class=\"token punctuation\">:<\/span> <span class=\"token comment\">#fff;<\/span><br \/>\n      border<span class=\"token operator\">&#8211;<\/span>radius<span class=\"token punctuation\">:<\/span> 8px<span class=\"token punctuation\">;<\/span><br \/>\n      padding<span class=\"token punctuation\">:<\/span> 24px<span class=\"token punctuation\">;<\/span><br \/>\n      margin<span class=\"token operator\">&#8211;<\/span>bottom<span class=\"token punctuation\">:<\/span> 20px<span class=\"token punctuation\">;<\/span><br \/>\n      box<span class=\"token operator\">&#8211;<\/span>shadow<span class=\"token punctuation\">:<\/span> <span class=\"token number\">0<\/span> 2px 8px rgba<span class=\"token punctuation\">(<\/span><span class=\"token number\">0<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token number\">0<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token number\">0<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token number\">0.1<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">;<\/span><br \/>\n    <span class=\"token punctuation\">}<\/span><br \/>\n    <span class=\"token operator\">\/<\/span><span class=\"token operator\">*<\/span> \u6587\u4ef6\u4e0a\u4f20\u533a\u57df\u6837\u5f0f <span class=\"token operator\">*<\/span><span class=\"token operator\">\/<\/span><br \/>\n    <span class=\"token punctuation\">.<\/span>upload<span class=\"token operator\">&#8211;<\/span>area <span class=\"token punctuation\">{<\/span><br \/>\n      display<span class=\"token punctuation\">:<\/span> flex<span class=\"token punctuation\">;<\/span><br \/>\n      align<span class=\"token operator\">&#8211;<\/span>items<span class=\"token punctuation\">:<\/span> center<span class=\"token punctuation\">;<\/span><br \/>\n      gap<span class=\"token punctuation\">:<\/span> 12px<span class=\"token punctuation\">;<\/span><br \/>\n      flex<span class=\"token operator\">&#8211;<\/span>wrap<span class=\"token punctuation\">:<\/span> wrap<span class=\"token punctuation\">;<\/span><br \/>\n    <span class=\"token punctuation\">}<\/span><br \/>\n    <span class=\"token builtin\">input<\/span><span class=\"token punctuation\">[<\/span><span class=\"token builtin\">type<\/span><span class=\"token operator\">&#061;<\/span><span class=\"token string\">&#034;file&#034;<\/span><span class=\"token punctuation\">]<\/span> <span class=\"token punctuation\">{<\/span><br \/>\n      padding<span class=\"token punctuation\">:<\/span> 8px<span class=\"token punctuation\">;<\/span><br \/>\n      border<span class=\"token punctuation\">:<\/span> 1px solid <span class=\"token comment\">#ccc;<\/span><br \/>\n      border<span class=\"token operator\">&#8211;<\/span>radius<span class=\"token punctuation\">:<\/span> 4px<span class=\"token punctuation\">;<\/span><br \/>\n      background<span class=\"token punctuation\">:<\/span> <span class=\"token comment\">#fff;<\/span><br \/>\n    <span class=\"token punctuation\">}<\/span><br \/>\n    button <span class=\"token punctuation\">{<\/span><br \/>\n      padding<span class=\"token punctuation\">:<\/span> 10px 24px<span class=\"token punctuation\">;<\/span><br \/>\n      background<span class=\"token punctuation\">:<\/span> <span class=\"token comment\">#3498db;<\/span><br \/>\n      color<span class=\"token punctuation\">:<\/span> <span class=\"token comment\">#fff;<\/span><br \/>\n      border<span class=\"token punctuation\">:<\/span> none<span class=\"token punctuation\">;<\/span><br \/>\n      border<span class=\"token operator\">&#8211;<\/span>radius<span class=\"token punctuation\">:<\/span> 4px<span class=\"token punctuation\">;<\/span><br \/>\n      cursor<span class=\"token punctuation\">:<\/span> pointer<span class=\"token punctuation\">;<\/span><br \/>\n      font<span class=\"token operator\">&#8211;<\/span>size<span class=\"token punctuation\">:<\/span> 14px<span class=\"token punctuation\">;<\/span><br \/>\n    <span class=\"token punctuation\">}<\/span><br \/>\n    button<span class=\"token punctuation\">:<\/span>hover <span class=\"token punctuation\">{<\/span> background<span class=\"token punctuation\">:<\/span> <span class=\"token comment\">#2980b9; }<\/span><br \/>\n    button<span class=\"token punctuation\">:<\/span>disabled <span class=\"token punctuation\">{<\/span> background<span class=\"token punctuation\">:<\/span> <span class=\"token comment\">#95a5a6; cursor: not-allowed; }<\/span><br \/>\n    <span class=\"token operator\">\/<\/span><span class=\"token operator\">*<\/span> \u72b6\u6001\u63d0\u793a\u6837\u5f0f <span class=\"token operator\">*<\/span><span class=\"token operator\">\/<\/span><br \/>\n    <span class=\"token comment\">#status {<\/span><br \/>\n      margin<span class=\"token operator\">&#8211;<\/span>top<span class=\"token punctuation\">:<\/span> 12px<span class=\"token punctuation\">;<\/span><br \/>\n      padding<span class=\"token punctuation\">:<\/span> 8px 12px<span class=\"token punctuation\">;<\/span><br \/>\n      border<span class=\"token operator\">&#8211;<\/span>radius<span class=\"token punctuation\">:<\/span> 4px<span class=\"token punctuation\">;<\/span><br \/>\n      display<span class=\"token punctuation\">:<\/span> none<span class=\"token punctuation\">;<\/span><br \/>\n    <span class=\"token punctuation\">}<\/span><br \/>\n    <span class=\"token comment\">#status.loading { background: #eaf2f8; color: #2c3e50; }<\/span><br \/>\n    <span class=\"token comment\">#status.error { background: #fdecea; color: #c0392b; }<\/span><br \/>\n    <span class=\"token comment\">#status.success { background: #e8f8f5; color: #27ae60; }<\/span><br \/>\n    <span class=\"token operator\">\/<\/span><span class=\"token operator\">*<\/span> \u7ed3\u679c\u5c55\u793a\u533a\u57df\u6837\u5f0f <span class=\"token operator\">*<\/span><span class=\"token operator\">\/<\/span><br \/>\n    <span class=\"token punctuation\">.<\/span>result<span class=\"token operator\">&#8211;<\/span>section <span class=\"token punctuation\">{<\/span> margin<span class=\"token operator\">&#8211;<\/span>top<span class=\"token punctuation\">:<\/span> 16px<span class=\"token punctuation\">;<\/span> <span class=\"token punctuation\">}<\/span><br \/>\n    <span class=\"token punctuation\">.<\/span>result<span class=\"token operator\">&#8211;<\/span>section h3 <span class=\"token punctuation\">{<\/span><br \/>\n      margin<span class=\"token operator\">&#8211;<\/span>bottom<span class=\"token punctuation\">:<\/span> 8px<span class=\"token punctuation\">;<\/span><br \/>\n      color<span class=\"token punctuation\">:<\/span> <span class=\"token comment\">#2c3e50;<\/span><br \/>\n      border<span class=\"token operator\">&#8211;<\/span>bottom<span class=\"token punctuation\">:<\/span> 2px solid <span class=\"token comment\">#ecf0f1;<\/span><br \/>\n      padding<span class=\"token operator\">&#8211;<\/span>bottom<span class=\"token punctuation\">:<\/span> 6px<span class=\"token punctuation\">;<\/span><br \/>\n    <span class=\"token punctuation\">}<\/span><br \/>\n    pre <span class=\"token punctuation\">{<\/span><br \/>\n      background<span class=\"token punctuation\">:<\/span> <span class=\"token comment\">#2d2d2d;<\/span><br \/>\n      color<span class=\"token punctuation\">:<\/span> <span class=\"token comment\">#f8f8f2;<\/span><br \/>\n      padding<span class=\"token punctuation\">:<\/span> 16px<span class=\"token punctuation\">;<\/span><br \/>\n      border<span class=\"token operator\">&#8211;<\/span>radius<span class=\"token punctuation\">:<\/span> 6px<span class=\"token punctuation\">;<\/span><br \/>\n      overflow<span class=\"token operator\">&#8211;<\/span>x<span class=\"token punctuation\">:<\/span> auto<span class=\"token punctuation\">;<\/span><br \/>\n      <span class=\"token builtin\">max<\/span><span class=\"token operator\">&#8211;<\/span>height<span class=\"token punctuation\">:<\/span> 400px<span class=\"token punctuation\">;<\/span><br \/>\n      overflow<span class=\"token operator\">&#8211;<\/span>y<span class=\"token punctuation\">:<\/span> auto<span class=\"token punctuation\">;<\/span><br \/>\n      font<span class=\"token operator\">&#8211;<\/span>size<span class=\"token punctuation\">:<\/span> 13px<span class=\"token punctuation\">;<\/span><br \/>\n      line<span class=\"token operator\">&#8211;<\/span>height<span class=\"token punctuation\">:<\/span> <span class=\"token number\">1.6<\/span><span class=\"token punctuation\">;<\/span><br \/>\n    <span class=\"token punctuation\">}<\/span><br \/>\n    <span class=\"token operator\">\/<\/span><span class=\"token operator\">*<\/span> Markdown \u6e32\u67d3\u533a\u57df\u6837\u5f0f <span class=\"token operator\">*<\/span><span class=\"token operator\">\/<\/span><br \/>\n    <span class=\"token comment\">#markdown-result {<\/span><br \/>\n      background<span class=\"token punctuation\">:<\/span> <span class=\"token comment\">#fff;<\/span><br \/>\n      border<span class=\"token punctuation\">:<\/span> 1px solid <span class=\"token comment\">#ddd;<\/span><br \/>\n      border<span class=\"token operator\">&#8211;<\/span>radius<span class=\"token punctuation\">:<\/span> 6px<span class=\"token punctuation\">;<\/span><br \/>\n      padding<span class=\"token punctuation\">:<\/span> 16px<span class=\"token punctuation\">;<\/span><br \/>\n      <span class=\"token builtin\">min<\/span><span class=\"token operator\">&#8211;<\/span>height<span class=\"token punctuation\">:<\/span> 200px<span class=\"token punctuation\">;<\/span><br \/>\n      <span class=\"token builtin\">max<\/span><span class=\"token operator\">&#8211;<\/span>height<span class=\"token punctuation\">:<\/span> 400px<span class=\"token punctuation\">;<\/span><br \/>\n      overflow<span class=\"token operator\">&#8211;<\/span>y<span class=\"token punctuation\">:<\/span> auto<span class=\"token punctuation\">;<\/span><br \/>\n    <span class=\"token punctuation\">}<\/span><br \/>\n    <span class=\"token comment\">#markdown-result h1, #markdown-result h2, #markdown-result h3 {<\/span><br \/>\n      margin<span class=\"token punctuation\">:<\/span> 12px <span class=\"token number\">0<\/span> 8px<span class=\"token punctuation\">;<\/span><br \/>\n    <span class=\"token punctuation\">}<\/span><br \/>\n    <span class=\"token comment\">#markdown-result table {<\/span><br \/>\n      border<span class=\"token operator\">&#8211;<\/span>collapse<span class=\"token punctuation\">:<\/span> collapse<span class=\"token punctuation\">;<\/span><br \/>\n      width<span class=\"token punctuation\">:<\/span> <span class=\"token number\">100<\/span><span class=\"token operator\">%<\/span><span class=\"token punctuation\">;<\/span><br \/>\n      margin<span class=\"token punctuation\">:<\/span> 8px <span class=\"token number\">0<\/span><span class=\"token punctuation\">;<\/span><br \/>\n    <span class=\"token punctuation\">}<\/span><br \/>\n    <span class=\"token comment\">#markdown-result th, #markdown-result td {<\/span><br \/>\n      border<span class=\"token punctuation\">:<\/span> 1px solid <span class=\"token comment\">#ddd;<\/span><br \/>\n      padding<span class=\"token punctuation\">:<\/span> 6px 10px<span class=\"token punctuation\">;<\/span><br \/>\n      text<span class=\"token operator\">&#8211;<\/span>align<span class=\"token punctuation\">:<\/span> left<span class=\"token punctuation\">;<\/span><br \/>\n    <span class=\"token punctuation\">}<\/span><br \/>\n    <span class=\"token comment\">#markdown-result code {<\/span><br \/>\n      background<span class=\"token punctuation\">:<\/span> <span class=\"token comment\">#f0f0f0;<\/span><br \/>\n      padding<span class=\"token punctuation\">:<\/span> 2px 4px<span class=\"token punctuation\">;<\/span><br \/>\n      border<span class=\"token operator\">&#8211;<\/span>radius<span class=\"token punctuation\">:<\/span> 3px<span class=\"token punctuation\">;<\/span><br \/>\n    <span class=\"token punctuation\">}<\/span><br \/>\n  <span class=\"token operator\">&lt;<\/span><span class=\"token operator\">\/<\/span>style<span class=\"token operator\">&gt;<\/span><br \/>\n<span class=\"token operator\">&lt;<\/span><span class=\"token operator\">\/<\/span>head<span class=\"token operator\">&gt;<\/span><br \/>\n<span class=\"token operator\">&lt;<\/span>body<span class=\"token operator\">&gt;<\/span><br \/>\n  <span class=\"token operator\">&lt;<\/span>h1<span class=\"token operator\">&gt;<\/span>&#x1f4c4; MinerU \u6587\u6863\u89e3\u6790\u670d\u52a1<span class=\"token operator\">&lt;<\/span><span class=\"token operator\">\/<\/span>h1<span class=\"token operator\">&gt;<\/span><\/p>\n<p>  <span class=\"token operator\">&lt;<\/span>!<span class=\"token operator\">&#8211;<\/span><span class=\"token operator\">&#8211;<\/span> \u6587\u4ef6\u4e0a\u4f20\u8868\u5355\u5361\u7247 <span class=\"token operator\">&#8211;<\/span><span class=\"token operator\">&#8211;<\/span><span class=\"token operator\">&gt;<\/span><br \/>\n  <span class=\"token operator\">&lt;<\/span>div <span class=\"token keyword\">class<\/span><span class=\"token operator\">&#061;<\/span><span class=\"token string\">&#034;card&#034;<\/span><span class=\"token operator\">&gt;<\/span><br \/>\n    <span class=\"token operator\">&lt;<\/span>h2<span class=\"token operator\">&gt;<\/span>\u4e0a\u4f20 PDF \u6587\u6863<span class=\"token operator\">&lt;<\/span><span class=\"token operator\">\/<\/span>h2<span class=\"token operator\">&gt;<\/span><br \/>\n    <span class=\"token operator\">&lt;<\/span>div <span class=\"token keyword\">class<\/span><span class=\"token operator\">&#061;<\/span><span class=\"token string\">&#034;upload-area&#034;<\/span><span class=\"token operator\">&gt;<\/span><br \/>\n      <span class=\"token operator\">&lt;<\/span>!<span class=\"token operator\">&#8211;<\/span><span class=\"token operator\">&#8211;<\/span> \u6587\u4ef6\u9009\u62e9\u6846&#xff1a;\u4ec5\u63a5\u53d7 PDF \u6587\u4ef6 <span class=\"token operator\">&#8211;<\/span><span class=\"token operator\">&#8211;<\/span><span class=\"token operator\">&gt;<\/span><br \/>\n      <span class=\"token operator\">&lt;<\/span><span class=\"token builtin\">input<\/span> <span class=\"token builtin\">type<\/span><span class=\"token operator\">&#061;<\/span><span class=\"token string\">&#034;file&#034;<\/span> <span class=\"token builtin\">id<\/span><span class=\"token operator\">&#061;<\/span><span class=\"token string\">&#034;file-input&#034;<\/span> accept<span class=\"token operator\">&#061;<\/span><span class=\"token string\">&#034;.pdf&#034;<\/span> <span class=\"token operator\">\/<\/span><span class=\"token operator\">&gt;<\/span><br \/>\n      <span class=\"token operator\">&lt;<\/span>!<span class=\"token operator\">&#8211;<\/span><span class=\"token operator\">&#8211;<\/span> \u89e3\u6790\u6309\u94ae&#xff1a;\u70b9\u51fb\u540e\u89e6\u53d1\u89e3\u6790 <span class=\"token operator\">&#8211;<\/span><span class=\"token operator\">&#8211;<\/span><span class=\"token operator\">&gt;<\/span><br \/>\n      <span class=\"token operator\">&lt;<\/span>button <span class=\"token builtin\">id<\/span><span class=\"token operator\">&#061;<\/span><span class=\"token string\">&#034;parse-btn&#034;<\/span> onclick<span class=\"token operator\">&#061;<\/span><span class=\"token string\">&#034;parseDocument()&#034;<\/span><span class=\"token operator\">&gt;<\/span>\u5f00\u59cb\u89e3\u6790<span class=\"token operator\">&lt;<\/span><span class=\"token operator\">\/<\/span>button<span class=\"token operator\">&gt;<\/span><br \/>\n    <span class=\"token operator\">&lt;<\/span><span class=\"token operator\">\/<\/span>div<span class=\"token operator\">&gt;<\/span><br \/>\n    <span class=\"token operator\">&lt;<\/span>!<span class=\"token operator\">&#8211;<\/span><span class=\"token operator\">&#8211;<\/span> \u72b6\u6001\u63d0\u793a\u533a\u57df&#xff1a;\u663e\u793a\u52a0\u8f7d\u4e2d <span class=\"token operator\">\/<\/span> \u6210\u529f <span class=\"token operator\">\/<\/span> \u9519\u8bef\u4fe1\u606f <span class=\"token operator\">&#8211;<\/span><span class=\"token operator\">&#8211;<\/span><span class=\"token operator\">&gt;<\/span><br \/>\n    <span class=\"token operator\">&lt;<\/span>div <span class=\"token builtin\">id<\/span><span class=\"token operator\">&#061;<\/span><span class=\"token string\">&#034;status&#034;<\/span><span class=\"token operator\">&gt;<\/span><span class=\"token operator\">&lt;<\/span><span class=\"token operator\">\/<\/span>div<span class=\"token operator\">&gt;<\/span><br \/>\n  <span class=\"token operator\">&lt;<\/span><span class=\"token operator\">\/<\/span>div<span class=\"token operator\">&gt;<\/span><\/p>\n<p>  <span class=\"token operator\">&lt;<\/span>!<span class=\"token operator\">&#8211;<\/span><span class=\"token operator\">&#8211;<\/span> Markdown \u7ed3\u679c\u5c55\u793a\u5361\u7247 <span class=\"token operator\">&#8211;<\/span><span class=\"token operator\">&#8211;<\/span><span class=\"token operator\">&gt;<\/span><br \/>\n  <span class=\"token operator\">&lt;<\/span>div <span class=\"token keyword\">class<\/span><span class=\"token operator\">&#061;<\/span><span class=\"token string\">&#034;card result-section&#034;<\/span><span class=\"token operator\">&gt;<\/span><br \/>\n    <span class=\"token operator\">&lt;<\/span>h3<span class=\"token operator\">&gt;<\/span>&#x1f4dd; Markdown \u7ed3\u679c<span class=\"token operator\">&lt;<\/span><span class=\"token operator\">\/<\/span>h3<span class=\"token operator\">&gt;<\/span><br \/>\n    <span class=\"token operator\">&lt;<\/span>!<span class=\"token operator\">&#8211;<\/span><span class=\"token operator\">&#8211;<\/span> \u6e32\u67d3\u540e\u7684 Markdown \u5185\u5bb9&#xff08;HTML \u5f62\u5f0f&#xff09; <span class=\"token operator\">&#8211;<\/span><span class=\"token operator\">&#8211;<\/span><span class=\"token operator\">&gt;<\/span><br \/>\n    <span class=\"token operator\">&lt;<\/span>div <span class=\"token builtin\">id<\/span><span class=\"token operator\">&#061;<\/span><span class=\"token string\">&#034;markdown-result&#034;<\/span><span class=\"token operator\">&gt;<\/span><br \/>\n      <span class=\"token operator\">&lt;<\/span>p style<span class=\"token operator\">&#061;<\/span><span class=\"token string\">&#034;color: #999;&#034;<\/span><span class=\"token operator\">&gt;<\/span>\u89e3\u6790\u5b8c\u6210\u540e&#xff0c;Markdown \u7ed3\u679c\u5c06\u663e\u793a\u5728\u8fd9\u91cc<span class=\"token punctuation\">.<\/span><span class=\"token punctuation\">.<\/span><span class=\"token punctuation\">.<\/span><span class=\"token operator\">&lt;<\/span><span class=\"token operator\">\/<\/span>p<span class=\"token operator\">&gt;<\/span><br \/>\n    <span class=\"token operator\">&lt;<\/span><span class=\"token operator\">\/<\/span>div<span class=\"token operator\">&gt;<\/span><br \/>\n  <span class=\"token operator\">&lt;<\/span><span class=\"token operator\">\/<\/span>div<span class=\"token operator\">&gt;<\/span><\/p>\n<p>  <span class=\"token operator\">&lt;<\/span>!<span class=\"token operator\">&#8211;<\/span><span class=\"token operator\">&#8211;<\/span> JSON \u7ed3\u679c\u5c55\u793a\u5361\u7247 <span class=\"token operator\">&#8211;<\/span><span class=\"token operator\">&#8211;<\/span><span class=\"token operator\">&gt;<\/span><br \/>\n  <span class=\"token operator\">&lt;<\/span>div <span class=\"token keyword\">class<\/span><span class=\"token operator\">&#061;<\/span><span class=\"token string\">&#034;card result-section&#034;<\/span><span class=\"token operator\">&gt;<\/span><br \/>\n    <span class=\"token operator\">&lt;<\/span>h3<span class=\"token operator\">&gt;<\/span>&#x1f50d; JSON \u7ed3\u679c<span class=\"token operator\">&lt;<\/span><span class=\"token operator\">\/<\/span>h3<span class=\"token operator\">&gt;<\/span><br \/>\n    <span class=\"token operator\">&lt;<\/span>!<span class=\"token operator\">&#8211;<\/span><span class=\"token operator\">&#8211;<\/span> \u539f\u59cb JSON \u5b57\u7b26\u4e32&#xff08;\u683c\u5f0f\u5316\u5c55\u793a&#xff09; <span class=\"token operator\">&#8211;<\/span><span class=\"token operator\">&#8211;<\/span><span class=\"token operator\">&gt;<\/span><br \/>\n    <span class=\"token operator\">&lt;<\/span>pre <span class=\"token builtin\">id<\/span><span class=\"token operator\">&#061;<\/span><span class=\"token string\">&#034;json-result&#034;<\/span><span class=\"token operator\">&gt;<\/span><span class=\"token operator\">\/\/<\/span> \u89e3\u6790\u5b8c\u6210\u540e&#xff0c;JSON \u7ed3\u679c\u5c06\u663e\u793a\u5728\u8fd9\u91cc<span class=\"token punctuation\">.<\/span><span class=\"token punctuation\">.<\/span><span class=\"token punctuation\">.<\/span><span class=\"token operator\">&lt;<\/span><span class=\"token operator\">\/<\/span>pre<span class=\"token operator\">&gt;<\/span><br \/>\n  <span class=\"token operator\">&lt;<\/span><span class=\"token operator\">\/<\/span>div<span class=\"token operator\">&gt;<\/span><\/p>\n<p>  <span class=\"token operator\">&lt;<\/span>!<span class=\"token operator\">&#8211;<\/span><span class=\"token operator\">&#8211;<\/span> \u5f15\u5165 marked<span class=\"token punctuation\">.<\/span>js \u7528\u4e8e\u5c06 Markdown \u6e32\u67d3\u4e3a HTML <span class=\"token operator\">&#8211;<\/span><span class=\"token operator\">&#8211;<\/span><span class=\"token operator\">&gt;<\/span><br \/>\n  <span class=\"token operator\">&lt;<\/span>script src<span class=\"token operator\">&#061;<\/span><span class=\"token string\">&#034;https:\/\/cdn.jsdelivr.net\/npm\/marked\/marked.min.js&#034;<\/span><span class=\"token operator\">&gt;<\/span><span class=\"token operator\">&lt;<\/span><span class=\"token operator\">\/<\/span>script<span class=\"token operator\">&gt;<\/span><br \/>\n  <span class=\"token operator\">&lt;<\/span>script<span class=\"token operator\">&gt;<\/span><br \/>\n    <span class=\"token operator\">\/\/<\/span> \u83b7\u53d6\u9875\u9762\u5143\u7d20\u5f15\u7528<br \/>\n    const fileInput <span class=\"token operator\">&#061;<\/span> document<span class=\"token punctuation\">.<\/span>getElementById<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;file-input&#034;<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">;<\/span><br \/>\n    const parseBtn <span class=\"token operator\">&#061;<\/span> document<span class=\"token punctuation\">.<\/span>getElementById<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;parse-btn&#034;<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">;<\/span><br \/>\n    const statusDiv <span class=\"token operator\">&#061;<\/span> document<span class=\"token punctuation\">.<\/span>getElementById<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;status&#034;<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">;<\/span><br \/>\n    const markdownResult <span class=\"token operator\">&#061;<\/span> document<span class=\"token punctuation\">.<\/span>getElementById<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;markdown-result&#034;<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">;<\/span><br \/>\n    const jsonResult <span class=\"token operator\">&#061;<\/span> document<span class=\"token punctuation\">.<\/span>getElementById<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;json-result&#034;<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">;<\/span><\/p>\n<p>    <span class=\"token operator\">\/<\/span><span class=\"token operator\">**<\/span><br \/>\n     <span class=\"token operator\">*<\/span> \u663e\u793a\u72b6\u6001\u63d0\u793a\u4fe1\u606f<br \/>\n     <span class=\"token operator\">*<\/span> &#064;param <span class=\"token punctuation\">{<\/span>string<span class=\"token punctuation\">}<\/span> message <span class=\"token operator\">&#8211;<\/span> \u63d0\u793a\u6587\u672c<br \/>\n     <span class=\"token operator\">*<\/span> &#064;param <span class=\"token punctuation\">{<\/span>string<span class=\"token punctuation\">}<\/span> <span class=\"token builtin\">type<\/span> <span class=\"token operator\">&#8211;<\/span> \u72b6\u6001\u7c7b\u578b&#xff1a;loading <span class=\"token operator\">\/<\/span> success <span class=\"token operator\">\/<\/span> error<br \/>\n     <span class=\"token operator\">*<\/span><span class=\"token operator\">\/<\/span><br \/>\n    function showStatus<span class=\"token punctuation\">(<\/span>message<span class=\"token punctuation\">,<\/span> <span class=\"token builtin\">type<\/span><span class=\"token punctuation\">)<\/span> <span class=\"token punctuation\">{<\/span><br \/>\n      statusDiv<span class=\"token punctuation\">.<\/span>textContent <span class=\"token operator\">&#061;<\/span> message<span class=\"token punctuation\">;<\/span><br \/>\n      statusDiv<span class=\"token punctuation\">.<\/span>className <span class=\"token operator\">&#061;<\/span> <span class=\"token builtin\">type<\/span><span class=\"token punctuation\">;<\/span> <span class=\"token operator\">\/\/<\/span> \u901a\u8fc7 CSS \u7c7b\u63a7\u5236\u989c\u8272<br \/>\n      statusDiv<span class=\"token punctuation\">.<\/span>style<span class=\"token punctuation\">.<\/span>display <span class=\"token operator\">&#061;<\/span> <span class=\"token string\">&#034;block&#034;<\/span><span class=\"token punctuation\">;<\/span><br \/>\n    <span class=\"token punctuation\">}<\/span><\/p>\n<p>    <span class=\"token operator\">\/<\/span><span class=\"token operator\">**<\/span><br \/>\n     <span class=\"token operator\">*<\/span> \u89e3\u6790\u6587\u6863\u7684\u4e3b\u51fd\u6570<br \/>\n     <span class=\"token operator\">*<\/span> \u8bfb\u53d6\u7528\u6237\u9009\u62e9\u7684 PDF \u6587\u4ef6&#xff0c;\u901a\u8fc7 fetch \u4e0a\u4f20\u5230\u540e\u7aef <span class=\"token operator\">\/<\/span>api<span class=\"token operator\">\/<\/span>parse \u63a5\u53e3&#xff0c;<br \/>\n     <span class=\"token operator\">*<\/span> \u5e76\u5c06\u8fd4\u56de\u7684 Markdown \u548c JSON \u7ed3\u679c\u5c55\u793a\u5230\u9875\u9762\u4e0a\u3002<br \/>\n     <span class=\"token operator\">*<\/span><span class=\"token operator\">\/<\/span><br \/>\n    <span class=\"token keyword\">async<\/span> function parseDocument<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span> <span class=\"token punctuation\">{<\/span><br \/>\n      <span class=\"token operator\">\/\/<\/span> <span class=\"token number\">1.<\/span> \u6821\u9a8c\u662f\u5426\u9009\u62e9\u4e86\u6587\u4ef6<br \/>\n      const <span class=\"token builtin\">file<\/span> <span class=\"token operator\">&#061;<\/span> fileInput<span class=\"token punctuation\">.<\/span>files<span class=\"token punctuation\">[<\/span><span class=\"token number\">0<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">;<\/span><br \/>\n      <span class=\"token keyword\">if<\/span> <span class=\"token punctuation\">(<\/span>!<span class=\"token builtin\">file<\/span><span class=\"token punctuation\">)<\/span> <span class=\"token punctuation\">{<\/span><br \/>\n        showStatus<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;\u8bf7\u5148\u9009\u62e9\u4e00\u4e2a PDF \u6587\u4ef6&#034;<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token string\">&#034;error&#034;<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">;<\/span><br \/>\n        <span class=\"token keyword\">return<\/span><span class=\"token punctuation\">;<\/span><br \/>\n      <span class=\"token punctuation\">}<\/span><\/p>\n<p>      <span class=\"token operator\">\/\/<\/span> <span class=\"token number\">2.<\/span> \u6821\u9a8c\u6587\u4ef6\u7c7b\u578b\u662f\u5426\u4e3a PDF<br \/>\n      <span class=\"token keyword\">if<\/span> <span class=\"token punctuation\">(<\/span>!<span class=\"token builtin\">file<\/span><span class=\"token punctuation\">.<\/span>name<span class=\"token punctuation\">.<\/span>toLowerCase<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">.<\/span>endsWith<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;.pdf&#034;<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">)<\/span> <span class=\"token punctuation\">{<\/span><br \/>\n        showStatus<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;\u4ec5\u652f\u6301 PDF \u6587\u4ef6&#034;<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token string\">&#034;error&#034;<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">;<\/span><br \/>\n        <span class=\"token keyword\">return<\/span><span class=\"token punctuation\">;<\/span><br \/>\n      <span class=\"token punctuation\">}<\/span><\/p>\n<p>      <span class=\"token operator\">\/\/<\/span> <span class=\"token number\">3.<\/span> \u6784\u5efa FormData&#xff0c;\u7528\u4e8e multipart<span class=\"token operator\">\/<\/span>form<span class=\"token operator\">&#8211;<\/span>data \u4e0a\u4f20<br \/>\n      const formData <span class=\"token operator\">&#061;<\/span> new FormData<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">;<\/span><br \/>\n      formData<span class=\"token punctuation\">.<\/span>append<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;file&#034;<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token builtin\">file<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">;<\/span> <span class=\"token operator\">\/\/<\/span> \u5b57\u6bb5\u540d\u5fc5\u987b\u4e0e\u540e\u7aef request<span class=\"token punctuation\">.<\/span>files<span class=\"token punctuation\">[<\/span><span class=\"token string\">&#034;file&#034;<\/span><span class=\"token punctuation\">]<\/span> \u4e00\u81f4<\/p>\n<p>      <span class=\"token operator\">\/\/<\/span> <span class=\"token number\">4.<\/span> \u7981\u7528\u6309\u94ae&#xff0c;\u9632\u6b62\u91cd\u590d\u63d0\u4ea4<br \/>\n      parseBtn<span class=\"token punctuation\">.<\/span>disabled <span class=\"token operator\">&#061;<\/span> true<span class=\"token punctuation\">;<\/span><br \/>\n      showStatus<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;\u6b63\u5728\u89e3\u6790\u6587\u6863&#xff0c;\u8bf7\u7a0d\u5019&#8230;&#034;<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token string\">&#034;loading&#034;<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">;<\/span><\/p>\n<p>      <span class=\"token keyword\">try<\/span> <span class=\"token punctuation\">{<\/span><br \/>\n        <span class=\"token operator\">\/\/<\/span> <span class=\"token number\">5.<\/span> \u8c03\u7528\u540e\u7aef\u89e3\u6790\u63a5\u53e3<br \/>\n        const response <span class=\"token operator\">&#061;<\/span> <span class=\"token keyword\">await<\/span> fetch<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;\/api\/parse&#034;<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token punctuation\">{<\/span><br \/>\n          method<span class=\"token punctuation\">:<\/span> <span class=\"token string\">&#034;POST&#034;<\/span><span class=\"token punctuation\">,<\/span><br \/>\n          body<span class=\"token punctuation\">:<\/span> formData <span class=\"token operator\">\/\/<\/span> \u6ce8\u610f&#xff1a;\u4e0d\u8981\u624b\u52a8\u8bbe\u7f6e Content<span class=\"token operator\">&#8211;<\/span>Type&#xff0c;\u6d4f\u89c8\u5668\u4f1a\u81ea\u52a8\u6dfb\u52a0 boundary<br \/>\n        <span class=\"token punctuation\">}<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">;<\/span><\/p>\n<p>        <span class=\"token operator\">\/\/<\/span> <span class=\"token number\">6.<\/span> \u89e3\u6790\u54cd\u5e94 JSON<br \/>\n        const data <span class=\"token operator\">&#061;<\/span> <span class=\"token keyword\">await<\/span> response<span class=\"token punctuation\">.<\/span>json<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">;<\/span><\/p>\n<p>        <span class=\"token operator\">\/\/<\/span> <span class=\"token number\">7.<\/span> \u5904\u7406\u540e\u7aef\u8fd4\u56de\u7684\u9519\u8bef<br \/>\n        <span class=\"token keyword\">if<\/span> <span class=\"token punctuation\">(<\/span>!response<span class=\"token punctuation\">.<\/span>ok<span class=\"token punctuation\">)<\/span> <span class=\"token punctuation\">{<\/span><br \/>\n          throw new Error<span class=\"token punctuation\">(<\/span>data<span class=\"token punctuation\">.<\/span>error <span class=\"token operator\">|<\/span><span class=\"token operator\">|<\/span> <span class=\"token string\">&#034;\u89e3\u6790\u5931\u8d25&#xff0c;\u8bf7\u7a0d\u540e\u91cd\u8bd5&#034;<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">;<\/span><br \/>\n        <span class=\"token punctuation\">}<\/span><\/p>\n<p>        <span class=\"token operator\">\/\/<\/span> <span class=\"token number\">8.<\/span> \u5c55\u793a Markdown \u7ed3\u679c&#xff08;\u4f7f\u7528 marked \u6e32\u67d3\u4e3a HTML&#xff09;<br \/>\n        markdownResult<span class=\"token punctuation\">.<\/span>innerHTML <span class=\"token operator\">&#061;<\/span> marked<span class=\"token punctuation\">.<\/span>parse<span class=\"token punctuation\">(<\/span>data<span class=\"token punctuation\">.<\/span>markdown <span class=\"token operator\">|<\/span><span class=\"token operator\">|<\/span> <span class=\"token string\">&#034;&#xff08;\u65e0 Markdown \u5185\u5bb9&#xff09;&#034;<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">;<\/span><\/p>\n<p>        <span class=\"token operator\">\/\/<\/span> <span class=\"token number\">9.<\/span> \u5c55\u793a JSON \u7ed3\u679c&#xff08;\u683c\u5f0f\u5316\u7f29\u8fdb&#xff0c;\u4fbf\u4e8e\u9605\u8bfb&#xff09;<br \/>\n        jsonResult<span class=\"token punctuation\">.<\/span>textContent <span class=\"token operator\">&#061;<\/span> JSON<span class=\"token punctuation\">.<\/span>stringify<span class=\"token punctuation\">(<\/span>data<span class=\"token punctuation\">.<\/span>content_list <span class=\"token operator\">|<\/span><span class=\"token operator\">|<\/span> <span class=\"token punctuation\">[<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">,<\/span> null<span class=\"token punctuation\">,<\/span> <span class=\"token number\">2<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">;<\/span><\/p>\n<p>        <span class=\"token operator\">\/\/<\/span> <span class=\"token number\">10.<\/span> \u66f4\u65b0\u72b6\u6001\u4e3a\u6210\u529f<br \/>\n        showStatus<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;\u2705 \u89e3\u6790\u6210\u529f&#xff01;&#034;<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token string\">&#034;success&#034;<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">;<\/span><br \/>\n      <span class=\"token punctuation\">}<\/span> catch <span class=\"token punctuation\">(<\/span>err<span class=\"token punctuation\">)<\/span> <span class=\"token punctuation\">{<\/span><br \/>\n        <span class=\"token operator\">\/\/<\/span> <span class=\"token number\">11.<\/span> \u6355\u83b7\u5e76\u5c55\u793a\u9519\u8bef\u4fe1\u606f<br \/>\n        showStatus<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;\u274c &#034;<\/span> <span class=\"token operator\">&#043;<\/span> err<span class=\"token punctuation\">.<\/span>message<span class=\"token punctuation\">,<\/span> <span class=\"token string\">&#034;error&#034;<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">;<\/span><br \/>\n        console<span class=\"token punctuation\">.<\/span>error<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;\u89e3\u6790\u51fa\u9519:&#034;<\/span><span class=\"token punctuation\">,<\/span> err<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">;<\/span><br \/>\n      <span class=\"token punctuation\">}<\/span> <span class=\"token keyword\">finally<\/span> <span class=\"token punctuation\">{<\/span><br \/>\n        <span class=\"token operator\">\/\/<\/span> <span class=\"token number\">12.<\/span> \u65e0\u8bba\u6210\u529f\u5931\u8d25&#xff0c;\u90fd\u6062\u590d\u6309\u94ae\u53ef\u7528\u72b6\u6001<br \/>\n        parseBtn<span class=\"token punctuation\">.<\/span>disabled <span class=\"token operator\">&#061;<\/span> false<span class=\"token punctuation\">;<\/span><br \/>\n      <span class=\"token punctuation\">}<\/span><br \/>\n    <span class=\"token punctuation\">}<\/span><br \/>\n  <span class=\"token operator\">&lt;<\/span><span class=\"token operator\">\/<\/span>script<span class=\"token operator\">&gt;<\/span><br \/>\n<span class=\"token operator\">&lt;<\/span><span class=\"token operator\">\/<\/span>body<span class=\"token operator\">&gt;<\/span><br \/>\n<span class=\"token operator\">&lt;<\/span><span class=\"token operator\">\/<\/span>html<span class=\"token operator\">&gt;<\/span><\/p>\n<p>\u4ee3\u7801\u8bf4\u660e&#xff1a;<\/p>\n<ul>\n<li>\u6587\u4ef6\u4e0a\u4f20\u8868\u5355&#xff1a;\u4f7f\u7528 &lt;input type&#061;&#034;file&#034; accept&#061;&#034;.pdf&#034;&gt; \u9650\u5236\u53ea\u80fd\u9009\u62e9 PDF \u6587\u4ef6&#xff0c;\u914d\u5408\u300c\u5f00\u59cb\u89e3\u6790\u300d\u6309\u94ae\u89e6\u53d1\u4e0a\u4f20\u3002<\/li>\n<li>fetch \u8c03\u7528\u903b\u8f91&#xff1a;\u901a\u8fc7 FormData \u5c01\u88c5\u6587\u4ef6&#xff0c;\u4ee5 multipart\/form-data \u65b9\u5f0f POST \u5230 \/api\/parse&#xff0c;\u5b57\u6bb5\u540d file \u4e0e\u540e\u7aef request.files[&#034;file&#034;] \u4e25\u683c\u5bf9\u5e94\u3002<\/li>\n<li>\u7ed3\u679c\u5c55\u793a&#xff1a;Markdown \u7ed3\u679c\u501f\u52a9 marked.js \u6e32\u67d3\u4e3a HTML \u5448\u73b0&#xff1b;JSON \u7ed3\u679c\u4ee5\u683c\u5f0f\u5316\u7f29\u8fdb\u7684\u65b9\u5f0f\u5c55\u793a\u5728 &lt;pre&gt; \u4e2d&#xff0c;\u4fbf\u4e8e\u67e5\u770b\u7ed3\u6784\u5316\u6570\u636e\u3002<\/li>\n<li>\u72b6\u6001\u53cd\u9988&#xff1a;\u901a\u8fc7 showStatus() \u51fd\u6570\u7edf\u4e00\u7ba1\u7406\u300c\u52a0\u8f7d\u4e2d \/ \u6210\u529f \/ \u9519\u8bef\u300d\u4e09\u79cd\u72b6\u6001&#xff0c;\u63d0\u5347\u7528\u6237\u4f53\u9a8c\u3002<\/li>\n<li>\u9519\u8bef\u5904\u7406&#xff1a;\u524d\u7aef\u540c\u65f6\u6821\u9a8c\u6587\u4ef6\u662f\u5426\u9009\u62e9\u3001\u662f\u5426\u4e3a PDF&#xff0c;\u5e76\u6355\u83b7\u540e\u7aef\u8fd4\u56de\u7684\u9519\u8bef\u4fe1\u606f&#xff0c;\u907f\u514d\u8bf7\u6c42\u5931\u8d25\u65f6\u9875\u9762\u65e0\u54cd\u5e94<\/li>\n<\/ul>\n<h4>10.6 \u5e38\u89c1\u95ee\u9898\u4e0e\u89e3\u51b3\u65b9\u6848<\/h4>\n<p>\u5728\u5b9e\u9645\u4f7f\u7528 MinerU \u7684\u8fc7\u7a0b\u4e2d&#xff0c;\u5f00\u53d1\u8005\u5e38\u4f1a\u9047\u5230\u6a21\u578b\u4e0b\u8f7d\u3001\u89e3\u6790\u6027\u80fd\u3001\u8bc6\u522b\u7cbe\u5ea6\u7b49\u65b9\u9762\u7684\u95ee\u9898\u3002\u4e0b\u9762\u6574\u7406 5 \u4e2a\u9ad8\u9891\u95ee\u9898&#xff0c;\u5e76\u7ed9\u51fa\u5177\u4f53\u7684\u6392\u67e5\u6b65\u9aa4\u4e0e\u89e3\u51b3\u4ee3\u7801\u3002<\/p>\n<h5>\u95ee\u9898\u4e00&#xff1a;\u6a21\u578b\u4e0b\u8f7d\u5931\u8d25\u6216\u8d85\u65f6<\/h5>\n<p>\u73b0\u8c61&#xff1a;\u9996\u6b21\u8fd0\u884c MinerU \u65f6&#xff0c;\u6a21\u578b\u6587\u4ef6\u65e0\u6cd5\u81ea\u52a8\u4e0b\u8f7d&#xff0c;\u6216\u4e0b\u8f7d\u4e2d\u9014\u4e2d\u65ad&#xff0c;\u5bfc\u81f4\u89e3\u6790\u62a5\u9519\u3002<\/p>\n<p>\u6392\u67e5\u6b65\u9aa4&#xff1a;<\/p>\n<li>\u68c0\u67e5\u7f51\u7edc\u662f\u5426\u80fd\u591f\u8bbf\u95ee Hugging Face \/ ModelScope \u7b49\u6a21\u578b\u4ed3\u5e93&#xff1b;<\/li>\n<li>\u67e5\u770b MINERU_MODEL_DIR \u6307\u5411\u7684\u76ee\u5f55\u662f\u5426\u5b58\u5728\u4e14\u53ef\u5199&#xff1b;<\/li>\n<li>\u786e\u8ba4\u78c1\u76d8\u5269\u4f59\u7a7a\u95f4\u662f\u5426\u5145\u8db3&#xff08;\u6a21\u578b\u603b\u91cf\u7ea6 2-4 GB&#xff09;\u3002<\/li>\n<p>\u89e3\u51b3\u65b9\u6848&#xff1a;\u63a8\u8350\u4f7f\u7528\u56fd\u5185\u955c\u50cf\u6e90\u624b\u52a8\u4e0b\u8f7d\u6a21\u578b&#xff0c;\u518d\u901a\u8fc7\u73af\u5883\u53d8\u91cf\u6307\u5b9a\u672c\u5730\u8def\u5f84\u3002<\/p>\n<p><span class=\"token comment\"># \u4f7f\u7528 ModelScope \u955c\u50cf\u4e0b\u8f7d\u6a21\u578b<\/span><br \/>\npip <span class=\"token function\">install<\/span> modelscope<\/p>\n<p><span class=\"token comment\"># \u624b\u52a8\u4e0b\u8f7d MinerU \u6240\u9700\u6a21\u578b\u5230\u672c\u5730\u76ee\u5f55<\/span><br \/>\npython <span class=\"token parameter variable\">-c<\/span> <span class=\"token string\">&#034;<br \/>\nfrom modelscope import snapshot_download<br \/>\nsnapshot_download(&#039;opendatalab\/PDF-Extract-Kit-1.0&#039;, local_dir&#061;&#039;.\/models&#039;)<br \/>\n&#034;<\/span><\/p>\n<p><span class=\"token comment\"># \u6307\u5b9a\u672c\u5730\u6a21\u578b\u76ee\u5f55\u540e\u8fd0\u884c<\/span><br \/>\n<span class=\"token builtin class-name\">export<\/span> <span class=\"token assign-left variable\">MINERU_MODEL_DIR<\/span><span class=\"token operator\">&#061;<\/span>.\/models<br \/>\npython parse.py<\/p>\n<h5>\u95ee\u9898\u4e8c&#xff1a;\u89e3\u6790\u901f\u5ea6\u6162&#xff0c;CPU \u4e0a\u8017\u65f6\u8fc7\u957f<\/h5>\n<p>\u73b0\u8c61&#xff1a;\u5728 CPU \u73af\u5883\u4e0b\u89e3\u6790\u4e00\u4efd\u51e0\u5341\u9875\u7684 PDF \u9700\u8981\u6570\u5206\u949f\u751a\u81f3\u66f4\u4e45\u3002<\/p>\n<p>\u6392\u67e5\u6b65\u9aa4&#xff1a;<\/p>\n<li>\u786e\u8ba4\u5f53\u524d\u4f7f\u7528\u7684\u8bbe\u5907\u662f CPU \u8fd8\u662f GPU&#xff08;MINERU_DEVICE \u914d\u7f6e&#xff09;&#xff1b;<\/li>\n<li>\u68c0\u67e5\u662f\u5426\u5f00\u542f\u4e86\u4e0d\u5fc5\u8981\u7684\u6a21\u5757&#xff08;\u5982\u516c\u5f0f\u3001\u8868\u683c\u8bc6\u522b&#xff09;&#xff1b;<\/li>\n<li>\u89c2\u5bdf\u662f\u5426\u5bf9\u6574\u4efd\u6587\u6863\u91cd\u590d\u6267\u884c\u4e86\u591a\u6b21\u89e3\u6790\u3002<\/li>\n<p>\u89e3\u51b3\u65b9\u6848&#xff1a;\u4f18\u5148\u4f7f\u7528 GPU \u52a0\u901f&#xff1b;\u82e5\u53ea\u80fd\u4f7f\u7528 CPU&#xff0c;\u53ef\u5173\u95ed\u975e\u5fc5\u8981\u6a21\u5757\u5e76\u9650\u5236\u89e3\u6790\u9875\u6570\u3002<\/p>\n<p><span class=\"token comment\"># \u5173\u95ed\u516c\u5f0f\u4e0e\u8868\u683c\u8bc6\u522b&#xff0c;\u4ec5\u63d0\u53d6\u6587\u672c&#xff0c;\u663e\u8457\u63d0\u5347\u901f\u5ea6<\/span><br \/>\nresult <span class=\"token operator\">&#061;<\/span> dataset<span class=\"token punctuation\">.<\/span>pipe_txt_mode<span class=\"token punctuation\">(<\/span><br \/>\n    model_json<span class=\"token operator\">&#061;<\/span>model_json<span class=\"token punctuation\">,<\/span><br \/>\n    parse_mode<span class=\"token operator\">&#061;<\/span><span class=\"token string\">&#034;txt&#034;<\/span><span class=\"token punctuation\">,<\/span>          <span class=\"token comment\"># \u7eaf\u6587\u672c\u6a21\u5f0f&#xff0c;\u8df3\u8fc7 OCR \u4e0e\u7248\u9762\u91cd\u6392<\/span><br \/>\n    formula_enable<span class=\"token operator\">&#061;<\/span><span class=\"token boolean\">False<\/span><span class=\"token punctuation\">,<\/span>      <span class=\"token comment\"># \u5173\u95ed\u516c\u5f0f\u8bc6\u522b<\/span><br \/>\n    table_enable<span class=\"token operator\">&#061;<\/span><span class=\"token boolean\">False<\/span>         <span class=\"token comment\"># \u5173\u95ed\u8868\u683c\u8bc6\u522b<\/span><br \/>\n<span class=\"token punctuation\">)<\/span><\/p>\n<p><span class=\"token comment\"># \u4ec5\u89e3\u6790\u524d 10 \u9875&#xff0c;\u7528\u4e8e\u5feb\u901f\u9a8c\u8bc1\u6d41\u7a0b<\/span><br \/>\npdf_bytes <span class=\"token operator\">&#061;<\/span> <span class=\"token builtin\">open<\/span><span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;document.pdf&#034;<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token string\">&#034;rb&#034;<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">.<\/span>read<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><br \/>\ndataset <span class=\"token operator\">&#061;<\/span> PymuDocDataset<span class=\"token punctuation\">(<\/span>pdf_bytes<span class=\"token punctuation\">)<\/span><br \/>\ndataset <span class=\"token operator\">&#061;<\/span> dataset<span class=\"token punctuation\">[<\/span><span class=\"token punctuation\">:<\/span><span class=\"token number\">10<\/span><span class=\"token punctuation\">]<\/span>         <span class=\"token comment\"># \u622a\u53d6\u524d 10 \u9875<\/span><\/p>\n<h5>\u95ee\u9898\u4e09&#xff1a;\u8868\u683c\u8bc6\u522b\u4e0d\u51c6\u786e&#xff0c;\u884c\u5217\u9519\u4e71<\/h5>\n<p>\u73b0\u8c61&#xff1a;\u590d\u6742\u8868\u683c&#xff08;\u5408\u5e76\u5355\u5143\u683c\u3001\u8de8\u9875\u8868\u683c\u3001\u65e0\u8fb9\u6846\u8868\u683c&#xff09;\u89e3\u6790\u540e\u7ed3\u6784\u9519\u4e71\u3002<\/p>\n<p>\u6392\u67e5\u6b65\u9aa4&#xff1a;<\/p>\n<li>\u786e\u8ba4\u539f PDF \u662f\u5426\u4e3a\u626b\u63cf\u4ef6&#xff0c;\u82e5\u662f\u5219\u5148\u786e\u8ba4 OCR \u662f\u5426\u5df2\u542f\u7528&#xff1b;<\/li>\n<li>\u68c0\u67e5\u8868\u683c\u533a\u57df\u662f\u5426\u88ab\u7248\u9762\u5206\u6790\u6b63\u786e\u8bc6\u522b&#xff08;\u67e5\u770b\u4e2d\u7ee7\u6587\u4ef6\u4e2d\u7684 layout_dets&#xff09;&#xff1b;<\/li>\n<li>\u5c1d\u8bd5\u63d0\u9ad8\u8f93\u5165\u56fe\u7247\u7684\u5206\u8fa8\u7387\u3002<\/li>\n<p>\u89e3\u51b3\u65b9\u6848&#xff1a;\u5bf9\u4f4e\u5206\u8fa8\u7387\u626b\u63cf\u4ef6\u5148\u505a\u56fe\u50cf\u589e\u5f3a&#xff0c;\u518d\u5f00\u542f\u8868\u683c\u8bc6\u522b&#xff1b;\u5fc5\u8981\u65f6\u5bf9\u8868\u683c\u533a\u57df\u5355\u72ec\u4e8c\u6b21\u89e3\u6790\u3002<\/p>\n<p><span class=\"token comment\"># \u4f7f\u7528 OpenCV \u5bf9\u626b\u63cf\u9875\u505a\u4e8c\u503c\u5316\u4e0e\u9510\u5316&#xff0c;\u63d0\u5347\u8868\u683c\u8bc6\u522b\u7cbe\u5ea6<\/span><br \/>\n<span class=\"token keyword\">import<\/span> cv2<br \/>\n<span class=\"token keyword\">import<\/span> numpy <span class=\"token keyword\">as<\/span> np<\/p>\n<p><span class=\"token keyword\">def<\/span> <span class=\"token function\">enhance_image<\/span><span class=\"token punctuation\">(<\/span>image_path<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">:<\/span><br \/>\n    img <span class=\"token operator\">&#061;<\/span> cv2<span class=\"token punctuation\">.<\/span>imread<span class=\"token punctuation\">(<\/span>image_path<span class=\"token punctuation\">,<\/span> cv2<span class=\"token punctuation\">.<\/span>IMREAD_GRAYSCALE<span class=\"token punctuation\">)<\/span><br \/>\n    <span class=\"token comment\"># \u4e8c\u503c\u5316&#xff0c;\u53bb\u9664\u566a\u70b9<\/span><br \/>\n    _<span class=\"token punctuation\">,<\/span> binary <span class=\"token operator\">&#061;<\/span> cv2<span class=\"token punctuation\">.<\/span>threshold<span class=\"token punctuation\">(<\/span>img<span class=\"token punctuation\">,<\/span> <span class=\"token number\">0<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token number\">255<\/span><span class=\"token punctuation\">,<\/span> cv2<span class=\"token punctuation\">.<\/span>THRESH_BINARY <span class=\"token operator\">&#043;<\/span> cv2<span class=\"token punctuation\">.<\/span>THRESH_OTSU<span class=\"token punctuation\">)<\/span><br \/>\n    <span class=\"token comment\"># \u9510\u5316&#xff0c;\u589e\u5f3a\u8868\u683c\u7ebf\u6761<\/span><br \/>\n    kernel <span class=\"token operator\">&#061;<\/span> np<span class=\"token punctuation\">.<\/span>array<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">[<\/span><span class=\"token punctuation\">[<\/span><span class=\"token number\">0<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token operator\">&#8211;<\/span><span class=\"token number\">1<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token number\">0<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token punctuation\">[<\/span><span class=\"token operator\">&#8211;<\/span><span class=\"token number\">1<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token number\">5<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token operator\">&#8211;<\/span><span class=\"token number\">1<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token punctuation\">[<\/span><span class=\"token number\">0<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token operator\">&#8211;<\/span><span class=\"token number\">1<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token number\">0<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">)<\/span><br \/>\n    sharpened <span class=\"token operator\">&#061;<\/span> cv2<span class=\"token punctuation\">.<\/span>filter2D<span class=\"token punctuation\">(<\/span>binary<span class=\"token punctuation\">,<\/span> <span class=\"token operator\">&#8211;<\/span><span class=\"token number\">1<\/span><span class=\"token punctuation\">,<\/span> kernel<span class=\"token punctuation\">)<\/span><br \/>\n    cv2<span class=\"token punctuation\">.<\/span>imwrite<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;enhanced.png&#034;<\/span><span class=\"token punctuation\">,<\/span> sharpened<span class=\"token punctuation\">)<\/span><br \/>\n    <span class=\"token keyword\">return<\/span> <span class=\"token string\">&#034;enhanced.png&#034;<\/span><\/p>\n<p><span class=\"token comment\"># \u5c06\u589e\u5f3a\u540e\u7684\u56fe\u7247\u91cd\u65b0\u5582\u7ed9 MinerU \u89e3\u6790<\/span><br \/>\nenhanced_path <span class=\"token operator\">&#061;<\/span> enhance_image<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;page_scan.png&#034;<\/span><span class=\"token punctuation\">)<\/span><\/p>\n<h5>\u95ee\u9898\u56db&#xff1a;OCR \u8bc6\u522b\u7ed3\u679c\u4e71\u7801\u6216\u6f0f\u5b57<\/h5>\n<p>\u73b0\u8c61&#xff1a;\u626b\u63cf\u4ef6\u4e2d\u7684\u4e2d\u6587\u3001\u516c\u5f0f\u6216\u7279\u6b8a\u7b26\u53f7\u8bc6\u522b\u4e3a\u4e71\u7801&#xff0c;\u6216\u90e8\u5206\u6587\u5b57\u7f3a\u5931\u3002<\/p>\n<p>\u6392\u67e5\u6b65\u9aa4&#xff1a;<\/p>\n<li>\u786e\u8ba4 MINERU_LANG \u662f\u5426\u8bbe\u7f6e\u4e3a ch&#xff08;\u4e2d\u6587&#xff09;&#xff1b;<\/li>\n<li>\u68c0\u67e5\u539f\u56fe\u5206\u8fa8\u7387\u662f\u5426\u8fc7\u4f4e&#xff08;\u5efa\u8bae 300 DPI \u4ee5\u4e0a&#xff09;&#xff1b;<\/li>\n<li>\u786e\u8ba4\u662f\u5426\u542f\u7528\u4e86\u516c\u5f0f\u611f\u77e5\u5207\u6362\u3002<\/li>\n<p>\u89e3\u51b3\u65b9\u6848&#xff1a;\u8bbe\u7f6e\u6b63\u786e\u7684\u8bed\u8a00\u53c2\u6570&#xff0c;\u5e76\u5bf9\u4f4e\u8d28\u91cf\u56fe\u7247\u505a\u9884\u5904\u7406\u540e\u518d\u89e3\u6790\u3002<\/p>\n<p><span class=\"token comment\"># \u8bbe\u7f6e\u6587\u6863\u8bed\u8a00\u4e3a\u4e2d\u6587<\/span><br \/>\n<span class=\"token builtin class-name\">export<\/span> <span class=\"token assign-left variable\">MINERU_LANG<\/span><span class=\"token operator\">&#061;<\/span>ch<\/p>\n<p><span class=\"token comment\"># \u5f00\u542f OCR \u5f15\u64ce\u4e3a PaddleOCR&#xff08;\u5bf9\u4e2d\u6587\u652f\u6301\u66f4\u597d&#xff09;<\/span><br \/>\n<span class=\"token builtin class-name\">export<\/span> <span class=\"token assign-left variable\">MINERU_OCR_ENGINE<\/span><span class=\"token operator\">&#061;<\/span>paddle<\/p>\n<p><span class=\"token comment\"># \u5728\u4ee3\u7801\u4e2d\u663e\u5f0f\u6307\u5b9a\u8bed\u8a00\u4e0e OCR \u5f15\u64ce<\/span><br \/>\nresult <span class=\"token operator\">&#061;<\/span> dataset<span class=\"token punctuation\">.<\/span>pipe_txt_mode<span class=\"token punctuation\">(<\/span><br \/>\n    model_json<span class=\"token operator\">&#061;<\/span>model_json<span class=\"token punctuation\">,<\/span><br \/>\n    parse_mode<span class=\"token operator\">&#061;<\/span><span class=\"token string\">&#034;ocr&#034;<\/span><span class=\"token punctuation\">,<\/span>          <span class=\"token comment\"># \u5f3a\u5236 OCR \u6a21\u5f0f<\/span><br \/>\n    lang<span class=\"token operator\">&#061;<\/span><span class=\"token string\">&#034;ch&#034;<\/span><span class=\"token punctuation\">,<\/span>                 <span class=\"token comment\"># \u4e2d\u6587<\/span><br \/>\n    ocr_engine<span class=\"token operator\">&#061;<\/span><span class=\"token string\">&#034;paddle&#034;<\/span>        <span class=\"token comment\"># \u4f7f\u7528 PaddleOCR<\/span><br \/>\n<span class=\"token punctuation\">)<\/span><\/p>\n<h5>\u95ee\u9898\u4e94&#xff1a;\u89e3\u6790\u7ed3\u679c\u4e2d\u9605\u8bfb\u987a\u5e8f\u9519\u4e71<\/h5>\n<p>\u73b0\u8c61&#xff1a;\u591a\u680f\u6392\u7248\u6216\u56fe\u6587\u6df7\u6392\u7684\u6587\u6863&#xff0c;\u89e3\u6790\u540e\u6bb5\u843d\u987a\u5e8f\u4e0e\u539f\u6587\u4e0d\u4e00\u81f4\u3002<\/p>\n<p>\u6392\u67e5\u6b65\u9aa4&#xff1a;<\/p>\n<li>\u68c0\u67e5\u539f\u6587\u6863\u662f\u5426\u4e3a\u53cc\u680f\u6216\u591a\u680f\u6392\u7248&#xff1b;<\/li>\n<li>\u67e5\u770b\u4e2d\u7ee7\u6587\u4ef6\u4e2d\u7684\u9605\u8bfb\u987a\u5e8f\u6807\u8bb0&#xff08;reading_order&#xff09;&#xff1b;<\/li>\n<li>\u786e\u8ba4\u7248\u9762\u5206\u6790\u662f\u5426\u6b63\u786e\u8bc6\u522b\u4e86\u680f\u533a\u57df\u3002<\/li>\n<p>\u89e3\u51b3\u65b9\u6848&#xff1a;MinerU \u7684\u9605\u8bfb\u987a\u5e8f\u8fd8\u539f\u4f9d\u8d56\u7248\u9762\u5206\u6790\u7ed3\u679c&#xff0c;\u53ef\u5c1d\u8bd5\u8c03\u6574\u89e3\u6790\u6a21\u5f0f\u6216\u5bf9\u5206\u680f\u6587\u6863\u505a\u9884\u5904\u7406\u3002<\/p>\n<p><span class=\"token comment\"># \u67e5\u770b\u4e2d\u7ee7\u6587\u4ef6\u4e2d\u7684\u9605\u8bfb\u987a\u5e8f\u4fe1\u606f&#xff0c;\u5b9a\u4f4d\u9519\u4e71\u539f\u56e0<\/span><br \/>\n<span class=\"token keyword\">import<\/span> json<\/p>\n<p><span class=\"token keyword\">with<\/span> <span class=\"token builtin\">open<\/span><span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;output\/document.json&#034;<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token string\">&#034;r&#034;<\/span><span class=\"token punctuation\">,<\/span> encoding<span class=\"token operator\">&#061;<\/span><span class=\"token string\">&#034;utf-8&#034;<\/span><span class=\"token punctuation\">)<\/span> <span class=\"token keyword\">as<\/span> f<span class=\"token punctuation\">:<\/span><br \/>\n    data <span class=\"token operator\">&#061;<\/span> json<span class=\"token punctuation\">.<\/span>load<span class=\"token punctuation\">(<\/span>f<span class=\"token punctuation\">)<\/span><\/p>\n<p><span class=\"token comment\"># \u6253\u5370\u6bcf\u4e2a\u5185\u5bb9\u5757\u7684\u7c7b\u578b\u4e0e\u987a\u5e8f<\/span><br \/>\n<span class=\"token keyword\">for<\/span> idx<span class=\"token punctuation\">,<\/span> item <span class=\"token keyword\">in<\/span> <span class=\"token builtin\">enumerate<\/span><span class=\"token punctuation\">(<\/span>data<span class=\"token punctuation\">.<\/span>get<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;content_list&#034;<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token punctuation\">[<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">:<\/span><br \/>\n    <span class=\"token keyword\">print<\/span><span class=\"token punctuation\">(<\/span>idx<span class=\"token punctuation\">,<\/span> item<span class=\"token punctuation\">.<\/span>get<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;type&#034;<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">,<\/span> item<span class=\"token punctuation\">.<\/span>get<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;text&#034;<\/span><span class=\"token punctuation\">,<\/span> <span class=\"token string\">&#034;&#034;<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">[<\/span><span class=\"token punctuation\">:<\/span><span class=\"token number\">30<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p><span class=\"token comment\"># \u82e5\u6587\u6863\u4e3a\u53cc\u680f&#xff0c;\u53ef\u5148\u4f7f\u7528\u5de5\u5177\u5c06 PDF \u8f6c\u4e3a\u5355\u680f\u518d\u89e3\u6790<\/span><br \/>\n<span class=\"token comment\"># \u4f8b\u5982\u4f7f\u7528 pdfplumber \u68c0\u6d4b\u680f\u8fb9\u754c\u540e\u88c1\u526a&#xff0c;\u6216\u76f4\u63a5\u4f7f\u7528 MinerU \u7684 auto \u6a21\u5f0f<\/span><br \/>\n<span class=\"token builtin class-name\">export<\/span> <span class=\"token assign-left variable\">MINERU_PARSE_MODE<\/span><span class=\"token operator\">&#061;<\/span>auto<\/p>\n<p>\u5c0f\u7ed3&#xff1a;\u4ee5\u4e0a 5 \u4e2a\u95ee\u9898\u8986\u76d6\u4e86 MinerU \u4f7f\u7528\u4e2d\u6700\u5e38\u89c1\u7684\u6a21\u578b\u3001\u6027\u80fd\u3001\u7cbe\u5ea6\u4e0e\u987a\u5e8f\u573a\u666f\u3002\u9047\u5230\u95ee\u9898\u65f6&#xff0c;\u5efa\u8bae\u5148\u67e5\u770b\u4e2d\u7ee7\u6587\u4ef6\u4e0e\u65e5\u5fd7\u5b9a\u4f4d\u5177\u4f53\u73af\u8282&#xff0c;\u518d\u9488\u5bf9\u6027\u5730\u8c03\u6574\u914d\u7f6e\u6216\u9884\u5904\u7406&#xff0c;\u5f80\u5f80\u80fd\u5feb\u901f\u89e3\u51b3\u3002<\/p>\n<p>\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"<p>\u6458\u8981<br \/>\n\u672c\u6587\u7cfb\u7edf\u62c6\u89e3 MinerU \u6280\u672f\u6808\u7684\u5b8c\u6574\u67b6\u6784&#xff0c;\u6df1\u5165\u8bb2\u89e3\u5176\u6838\u5fc3\u5b9a\u4f4d\u3001\u5de5\u4f5c\u539f\u7406\u4e0e\u5404\u6a21\u5757\u7684\u534f\u4f5c\u65b9\u5f0f\u3002\u6587\u7ae0\u4ece\u5e95\u5c42\u539f\u7406\u51fa\u53d1&#xff0c;\u901a\u8fc7\u5b8c\u6574\u7684\u5b9e\u6218\u6848\u4f8b&#xff0c;\u6f14\u793a\u6587\u6863\u89e3\u6790\u3001\u5185\u5bb9\u63d0\u53d6\u3001\u6570\u636e\u6d41\u8f6c\u4e0e\u5e38\u89c1\u95ee\u9898\u6392\u67e5&#xff0c;\u5e76\u8fdb\u4e00\u6b65\u63a2\u8ba8 API \u96c6\u6210\u3001Docker \u5bb9\u5668\u5316\u3001\u6027\u80fd\u4f18\u5316\u7b49\u8fdb\u9636\u6269\u5c55\u3002\u65e0\u8bba\u4f60\u662f\u521d\u5b66\u8005\u8fd8\u662f\u6709\u4e00\u5b9a\u7ecf\u9a8c\u7684\u5f00\u53d1\u8005&#xff0c;\u90fd\u80fd\u4ece\u4e2d\u5efa\u7acb\u5bf9 MinerU \u7684\u6df1\u5ea6\u8ba4\u77e5\u3002<br \/>\n\u5173\u952e\u8bcd&#xff1a;MinerU&#xff1b;\u6587\u6863\u89e3\u6790&amp;#xf<\/p>\n","protected":false},"author":2,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[1],"tags":[50,188],"topic":[],"class_list":["post-103843","post","type-post","status-publish","format-standard","hentry","category-server","tag-50","tag-188"],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v20.3 - https:\/\/yoast.com\/wordpress\/plugins\/seo\/ -->\n<title>MinerU \u6587\u6863\u89e3\u6790\u670d\u52a1 - \u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3<\/title>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/www.wsisp.com\/helps\/103843.html\" \/>\n<meta property=\"og:locale\" content=\"zh_CN\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"MinerU \u6587\u6863\u89e3\u6790\u670d\u52a1 - \u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3\" \/>\n<meta property=\"og:description\" content=\"\u6458\u8981 \u672c\u6587\u7cfb\u7edf\u62c6\u89e3 MinerU \u6280\u672f\u6808\u7684\u5b8c\u6574\u67b6\u6784&#xff0c;\u6df1\u5165\u8bb2\u89e3\u5176\u6838\u5fc3\u5b9a\u4f4d\u3001\u5de5\u4f5c\u539f\u7406\u4e0e\u5404\u6a21\u5757\u7684\u534f\u4f5c\u65b9\u5f0f\u3002\u6587\u7ae0\u4ece\u5e95\u5c42\u539f\u7406\u51fa\u53d1&#xff0c;\u901a\u8fc7\u5b8c\u6574\u7684\u5b9e\u6218\u6848\u4f8b&#xff0c;\u6f14\u793a\u6587\u6863\u89e3\u6790\u3001\u5185\u5bb9\u63d0\u53d6\u3001\u6570\u636e\u6d41\u8f6c\u4e0e\u5e38\u89c1\u95ee\u9898\u6392\u67e5&#xff0c;\u5e76\u8fdb\u4e00\u6b65\u63a2\u8ba8 API \u96c6\u6210\u3001Docker \u5bb9\u5668\u5316\u3001\u6027\u80fd\u4f18\u5316\u7b49\u8fdb\u9636\u6269\u5c55\u3002\u65e0\u8bba\u4f60\u662f\u521d\u5b66\u8005\u8fd8\u662f\u6709\u4e00\u5b9a\u7ecf\u9a8c\u7684\u5f00\u53d1\u8005&#xff0c;\u90fd\u80fd\u4ece\u4e2d\u5efa\u7acb\u5bf9 MinerU \u7684\u6df1\u5ea6\u8ba4\u77e5\u3002 \u5173\u952e\u8bcd&#xff1a;MinerU&#xff1b;\u6587\u6863\u89e3\u6790&amp;#xf\" \/>\n<meta property=\"og:url\" content=\"https:\/\/www.wsisp.com\/helps\/103843.html\" \/>\n<meta property=\"og:site_name\" content=\"\u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3\" \/>\n<meta property=\"article:published_time\" content=\"2026-09-11T04:49:12+00:00\" \/>\n<meta name=\"author\" content=\"admin\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"\u4f5c\u8005\" \/>\n\t<meta name=\"twitter:data1\" content=\"admin\" \/>\n\t<meta name=\"twitter:label2\" content=\"\u9884\u8ba1\u9605\u8bfb\u65f6\u95f4\" \/>\n\t<meta name=\"twitter:data2\" content=\"13 \u5206\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"WebPage\",\"@id\":\"https:\/\/www.wsisp.com\/helps\/103843.html\",\"url\":\"https:\/\/www.wsisp.com\/helps\/103843.html\",\"name\":\"MinerU \u6587\u6863\u89e3\u6790\u670d\u52a1 - \u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3\",\"isPartOf\":{\"@id\":\"https:\/\/www.wsisp.com\/helps\/#website\"},\"datePublished\":\"2026-09-11T04:49:12+00:00\",\"dateModified\":\"2026-09-11T04:49:12+00:00\",\"author\":{\"@id\":\"https:\/\/www.wsisp.com\/helps\/#\/schema\/person\/358e386c577a3ab51c4493330a20ad41\"},\"breadcrumb\":{\"@id\":\"https:\/\/www.wsisp.com\/helps\/103843.html#breadcrumb\"},\"inLanguage\":\"zh-Hans\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/www.wsisp.com\/helps\/103843.html\"]}]},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/www.wsisp.com\/helps\/103843.html#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"\u9996\u9875\",\"item\":\"https:\/\/www.wsisp.com\/helps\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"MinerU \u6587\u6863\u89e3\u6790\u670d\u52a1\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/www.wsisp.com\/helps\/#website\",\"url\":\"https:\/\/www.wsisp.com\/helps\/\",\"name\":\"\u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3\",\"description\":\"\u9999\u6e2f\u670d\u52a1\u5668_\u9999\u6e2f\u4e91\u670d\u52a1\u5668\u8d44\u8baf_\u670d\u52a1\u5668\u5e2e\u52a9\u6587\u6863_\u670d\u52a1\u5668\u6559\u7a0b\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/www.wsisp.com\/helps\/?s={search_term_string}\"},\"query-input\":\"required name=search_term_string\"}],\"inLanguage\":\"zh-Hans\"},{\"@type\":\"Person\",\"@id\":\"https:\/\/www.wsisp.com\/helps\/#\/schema\/person\/358e386c577a3ab51c4493330a20ad41\",\"name\":\"admin\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"zh-Hans\",\"@id\":\"https:\/\/www.wsisp.com\/helps\/#\/schema\/person\/image\/\",\"url\":\"https:\/\/gravatar.wp-china-yes.net\/avatar\/?s=96&d=mystery\",\"contentUrl\":\"https:\/\/gravatar.wp-china-yes.net\/avatar\/?s=96&d=mystery\",\"caption\":\"admin\"},\"sameAs\":[\"http:\/\/wp.wsisp.com\"],\"url\":\"https:\/\/www.wsisp.com\/helps\/author\/admin\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"MinerU \u6587\u6863\u89e3\u6790\u670d\u52a1 - \u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/www.wsisp.com\/helps\/103843.html","og_locale":"zh_CN","og_type":"article","og_title":"MinerU \u6587\u6863\u89e3\u6790\u670d\u52a1 - \u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3","og_description":"\u6458\u8981 \u672c\u6587\u7cfb\u7edf\u62c6\u89e3 MinerU \u6280\u672f\u6808\u7684\u5b8c\u6574\u67b6\u6784&#xff0c;\u6df1\u5165\u8bb2\u89e3\u5176\u6838\u5fc3\u5b9a\u4f4d\u3001\u5de5\u4f5c\u539f\u7406\u4e0e\u5404\u6a21\u5757\u7684\u534f\u4f5c\u65b9\u5f0f\u3002\u6587\u7ae0\u4ece\u5e95\u5c42\u539f\u7406\u51fa\u53d1&#xff0c;\u901a\u8fc7\u5b8c\u6574\u7684\u5b9e\u6218\u6848\u4f8b&#xff0c;\u6f14\u793a\u6587\u6863\u89e3\u6790\u3001\u5185\u5bb9\u63d0\u53d6\u3001\u6570\u636e\u6d41\u8f6c\u4e0e\u5e38\u89c1\u95ee\u9898\u6392\u67e5&#xff0c;\u5e76\u8fdb\u4e00\u6b65\u63a2\u8ba8 API \u96c6\u6210\u3001Docker \u5bb9\u5668\u5316\u3001\u6027\u80fd\u4f18\u5316\u7b49\u8fdb\u9636\u6269\u5c55\u3002\u65e0\u8bba\u4f60\u662f\u521d\u5b66\u8005\u8fd8\u662f\u6709\u4e00\u5b9a\u7ecf\u9a8c\u7684\u5f00\u53d1\u8005&#xff0c;\u90fd\u80fd\u4ece\u4e2d\u5efa\u7acb\u5bf9 MinerU \u7684\u6df1\u5ea6\u8ba4\u77e5\u3002 \u5173\u952e\u8bcd&#xff1a;MinerU&#xff1b;\u6587\u6863\u89e3\u6790&amp;#xf","og_url":"https:\/\/www.wsisp.com\/helps\/103843.html","og_site_name":"\u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3","article_published_time":"2026-09-11T04:49:12+00:00","author":"admin","twitter_card":"summary_large_image","twitter_misc":{"\u4f5c\u8005":"admin","\u9884\u8ba1\u9605\u8bfb\u65f6\u95f4":"13 \u5206"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/www.wsisp.com\/helps\/103843.html","url":"https:\/\/www.wsisp.com\/helps\/103843.html","name":"MinerU \u6587\u6863\u89e3\u6790\u670d\u52a1 - \u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3","isPartOf":{"@id":"https:\/\/www.wsisp.com\/helps\/#website"},"datePublished":"2026-09-11T04:49:12+00:00","dateModified":"2026-09-11T04:49:12+00:00","author":{"@id":"https:\/\/www.wsisp.com\/helps\/#\/schema\/person\/358e386c577a3ab51c4493330a20ad41"},"breadcrumb":{"@id":"https:\/\/www.wsisp.com\/helps\/103843.html#breadcrumb"},"inLanguage":"zh-Hans","potentialAction":[{"@type":"ReadAction","target":["https:\/\/www.wsisp.com\/helps\/103843.html"]}]},{"@type":"BreadcrumbList","@id":"https:\/\/www.wsisp.com\/helps\/103843.html#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"\u9996\u9875","item":"https:\/\/www.wsisp.com\/helps"},{"@type":"ListItem","position":2,"name":"MinerU \u6587\u6863\u89e3\u6790\u670d\u52a1"}]},{"@type":"WebSite","@id":"https:\/\/www.wsisp.com\/helps\/#website","url":"https:\/\/www.wsisp.com\/helps\/","name":"\u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3","description":"\u9999\u6e2f\u670d\u52a1\u5668_\u9999\u6e2f\u4e91\u670d\u52a1\u5668\u8d44\u8baf_\u670d\u52a1\u5668\u5e2e\u52a9\u6587\u6863_\u670d\u52a1\u5668\u6559\u7a0b","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/www.wsisp.com\/helps\/?s={search_term_string}"},"query-input":"required name=search_term_string"}],"inLanguage":"zh-Hans"},{"@type":"Person","@id":"https:\/\/www.wsisp.com\/helps\/#\/schema\/person\/358e386c577a3ab51c4493330a20ad41","name":"admin","image":{"@type":"ImageObject","inLanguage":"zh-Hans","@id":"https:\/\/www.wsisp.com\/helps\/#\/schema\/person\/image\/","url":"https:\/\/gravatar.wp-china-yes.net\/avatar\/?s=96&d=mystery","contentUrl":"https:\/\/gravatar.wp-china-yes.net\/avatar\/?s=96&d=mystery","caption":"admin"},"sameAs":["http:\/\/wp.wsisp.com"],"url":"https:\/\/www.wsisp.com\/helps\/author\/admin"}]}},"_links":{"self":[{"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/posts\/103843","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/comments?post=103843"}],"version-history":[{"count":0,"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/posts\/103843\/revisions"}],"wp:attachment":[{"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/media?parent=103843"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/categories?post=103843"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/tags?post=103843"},{"taxonomy":"topic","embeddable":true,"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/topic?post=103843"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}