Compare commits
4
Commits
| Author | SHA1 | Date | |
|---|---|---|---|
 Abimael MartellandClaude Fable 5
|
7467f842a5 | ||
|
Abimael MartellandClaude Fable 5
|
740488d875 | ||
|
Abimael MartellandClaude Fable 5
|
0b894b7d3f | ||
|
Abimael MartellandClaude Fable 5
|
ebc2f05bcd |
@@ -0,0 +1,36 @@
|
||||
name: Deploy landing page
|
||||
|
||||
on:
|
||||
push:
|
||||
branches: [main]
|
||||
paths: ['site/**', '.github/workflows/pages.yml']
|
||||
workflow_dispatch:
|
||||
|
||||
permissions:
|
||||
contents: read
|
||||
pages: write
|
||||
id-token: write
|
||||
|
||||
# Allow one concurrent deployment; don't cancel an in-progress production deploy.
|
||||
concurrency:
|
||||
group: pages
|
||||
cancel-in-progress: false
|
||||
|
||||
jobs:
|
||||
deploy:
|
||||
name: Build & deploy to GitHub Pages
|
||||
runs-on: ubuntu-latest
|
||||
environment:
|
||||
name: github-pages
|
||||
url: ${{ steps.deploy.outputs.page_url }}
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
|
||||
- name: Upload site artifact
|
||||
uses: actions/upload-pages-artifact@v3
|
||||
with:
|
||||
path: site
|
||||
|
||||
- name: Deploy to GitHub Pages
|
||||
id: deploy
|
||||
uses: actions/deploy-pages@v4
|
||||
@@ -0,0 +1,3 @@
|
||||
<svg width="200" height="284" viewBox="0 0 200 284" fill="none" xmlns="http://www.w3.org/2000/svg">
|
||||
<path d="M166.862 90.7716C155.812 94.0514 147.483 101.471 141.383 109.53C140.073 111.26 137.343 109.96 137.863 107.841C149.543 59.8136 134.113 19.896 86.0157 0.247269C83.5758 -0.752669 81.0359 1.43719 81.6759 3.99704C103.555 91.8416 11.5294 84.432 23.1588 184.016C23.3588 185.726 21.4389 186.896 20.039 185.896C15.6792 182.766 10.8095 176.236 7.46963 171.647C6.48968 170.297 4.36978 170.677 3.9198 172.287C1.25994 181.906 0 190.965 0 199.965C0 234.963 17.9891 265.771 45.2177 283.63C46.7777 284.65 48.7776 283.19 48.2476 281.4C46.8477 276.7 46.0577 271.74 45.9977 266.611C45.9977 263.461 46.1977 260.241 46.6877 257.241C47.8276 249.702 50.4475 242.522 54.8473 235.983C69.9365 213.334 100.185 191.455 95.3552 161.747C95.0453 159.867 97.2651 158.627 98.6651 159.917C119.974 179.386 124.194 205.575 120.694 229.063C120.394 231.103 122.954 232.193 124.244 230.593C127.504 226.513 131.483 222.933 135.813 220.244C136.893 219.574 138.333 220.084 138.743 221.284C141.153 228.293 144.733 234.873 148.113 241.452C152.152 249.362 154.302 258.391 153.962 267.951C153.792 272.6 153.022 277.1 151.732 281.38C151.182 283.19 153.162 284.7 154.752 283.66C182.001 265.801 200 234.993 200 199.975C200 187.806 197.87 175.876 193.84 164.697C185.391 141.248 163.952 123.64 169.372 93.0815C169.632 91.6216 168.282 90.3517 166.862 90.7716Z" fill="#FA5D19" style="fill:#FA5D19;fill:color(display-p3 0.9816 0.3634 0.0984);fill-opacity:1;"/>
|
||||
</svg>
|
||||
|
After Width: | Height: | Size: 1.5 KiB |
@@ -0,0 +1,12 @@
|
||||
<svg width="172" height="40" viewBox="0 0 172 40" fill="none" xmlns="http://www.w3.org/2000/svg">
|
||||
<path d="M23.3606 12.8281C21.8137 13.2873 20.6476 14.3261 19.7936 15.4544C19.6102 15.6966 19.228 15.5146 19.3008 15.2178C20.936 8.49401 18.7759 2.90556 12.0422 0.154735C11.7006 0.0147436 11.345 0.321324 11.4346 0.679702C14.4977 12.9779 1.61412 11.9406 3.24224 25.8823C3.27024 26.1217 3.00145 26.2855 2.80546 26.1455C2.19509 25.7073 1.51332 24.7932 1.04575 24.1506C0.908555 23.9616 0.611769 24.0148 0.548773 24.2402C0.176391 25.5869 0 26.8553 0 28.1152C0 33.0149 2.51847 37.328 6.33048 39.8283C6.54887 39.9711 6.82886 39.7667 6.75466 39.5161C6.55867 38.8581 6.44808 38.1638 6.43968 37.4456C6.43968 37.0046 6.46768 36.5539 6.53627 36.1339C6.69587 35.0784 7.06265 34.0732 7.67862 33.1577C9.79111 29.9869 14.0259 26.9239 13.3497 22.7647C13.3063 22.5015 13.6171 22.328 13.8131 22.5085C16.7964 25.2342 17.3871 28.9005 16.8972 32.1889C16.8552 32.4745 17.2135 32.6271 17.3941 32.4031C17.8505 31.832 18.4077 31.3308 19.0138 30.9542C19.165 30.8604 19.3666 30.9318 19.424 31.0998C19.7614 32.0811 20.2626 33.0023 20.7358 33.9234C21.3013 35.0308 21.6023 36.2949 21.5547 37.6332C21.5309 38.2842 21.4231 38.9141 21.2425 39.5133C21.1655 39.7667 21.4427 39.9781 21.6653 39.8325C25.4801 37.3322 28 33.0191 28 28.1166C28 26.4129 27.7018 24.7428 27.1376 23.1777C25.9547 19.8949 22.9533 17.4297 23.712 13.1515C23.7484 12.9471 23.5594 12.7693 23.3606 12.8281Z" fill="#262626" style="fill:#262626;fill:color(display-p3 0.1500 0.1500 0.1500);fill-opacity:1;"/>
|
||||
<path d="M41 34.0521V10.9618H55.7586V14.3264H44.7969V21.0226H53.8436V24.2882H44.7969V34.0521H41Z" fill="#262626" style="fill:#262626;fill:color(display-p3 0.1500 0.1500 0.1500);fill-opacity:1;"/>
|
||||
<path d="M59.9569 14.7882C58.7352 14.7882 57.7777 13.8976 57.7777 12.6441C57.7777 11.3906 58.7352 10.5 59.9569 10.5C61.1785 10.5 62.136 11.3906 62.136 12.6441C62.136 13.8976 61.1785 14.7882 59.9569 14.7882ZM58.1409 34.0521V17.1632H61.7068V34.0521H58.1409Z" fill="#262626" style="fill:#262626;fill:color(display-p3 0.1500 0.1500 0.1500);fill-opacity:1;"/>
|
||||
<path d="M73.5885 17.1632H74.3809V20.4948H72.796C69.6264 20.4948 68.6029 22.9687 68.6029 25.5747V34.0521H65.0371V17.1632H68.2067L68.6029 19.7031C69.4613 18.2847 70.815 17.1632 73.5885 17.1632Z" fill="#262626" style="fill:#262626;fill:color(display-p3 0.1500 0.1500 0.1500);fill-opacity:1;"/>
|
||||
<path d="M83.632 34.25C78.3163 34.25 74.9816 30.8194 74.9816 25.6406C74.9816 20.4288 78.3163 16.9653 83.3019 16.9653C88.1884 16.9653 91.457 20.066 91.5561 25.0139C91.5561 25.4427 91.5231 25.9045 91.457 26.3663H78.7125V26.5972C78.8116 29.467 80.6275 31.3472 83.4339 31.3472C85.613 31.3472 87.1979 30.2587 87.6931 28.3785H91.2589C90.6646 31.7101 87.8252 34.25 83.632 34.25ZM78.8446 23.7604H87.8582C87.561 21.2535 85.8112 19.8351 83.3349 19.8351C81.0567 19.8351 79.1087 21.3524 78.8446 23.7604Z" fill="#262626" style="fill:#262626;fill:color(display-p3 0.1500 0.1500 0.1500);fill-opacity:1;"/>
|
||||
<path d="M102.033 34.25C96.9151 34.25 93.6465 30.9184 93.6465 25.6406C93.6465 20.4288 97.0142 16.9653 102.132 16.9653C106.49 16.9653 109.197 19.3733 109.891 23.1997H106.16C105.698 21.2205 104.278 20 102.066 20C99.1933 20 97.3113 22.309 97.3113 25.6406C97.3113 28.9392 99.1933 31.2153 102.066 31.2153C104.245 31.2153 105.698 29.9618 106.127 28.0156H109.891C109.23 31.842 106.358 34.25 102.033 34.25Z" fill="#262626" style="fill:#262626;fill:color(display-p3 0.1500 0.1500 0.1500);fill-opacity:1;"/>
|
||||
<path d="M121.006 17.1632H121.799V20.4948H120.214C117.044 20.4948 116.021 22.9687 116.021 25.5747V34.0521H112.455V17.1632H115.625L116.021 19.7031C116.879 18.2847 118.233 17.1632 121.006 17.1632Z" fill="#262626" style="fill:#262626;fill:color(display-p3 0.1500 0.1500 0.1500);fill-opacity:1;"/>
|
||||
<path d="M130.614 16.9653C135.104 16.9653 137.679 19.1094 137.679 23.1007V34.0521H134.576L134.279 31.6441C133.123 33.1615 131.505 34.25 128.831 34.25C125.133 34.25 122.657 32.4358 122.657 29.3021C122.657 25.8385 125.166 23.8924 129.92 23.8924H134.147V22.8698C134.147 20.9896 132.793 19.8351 130.449 19.8351C128.336 19.8351 126.916 20.8247 126.652 22.309H123.152C123.515 19.0104 126.355 16.9653 130.614 16.9653ZM129.425 31.4792C132.397 31.4792 134.114 29.7309 134.147 27.125V26.5312H129.722C127.51 26.5312 126.289 27.3559 126.289 29.0712C126.289 30.4896 127.477 31.4792 129.425 31.4792Z" fill="#262626" style="fill:#262626;fill:color(display-p3 0.1500 0.1500 0.1500);fill-opacity:1;"/>
|
||||
<path d="M144.653 34.0521L139.139 17.1632H142.903L146.766 30.0937L150.629 17.1632H153.897L157.595 30.0937L161.59 17.1632H165.222L159.609 34.0521H155.779L152.214 22.5729L148.516 34.0521H144.653Z" fill="#262626" style="fill:#262626;fill:color(display-p3 0.1500 0.1500 0.1500);fill-opacity:1;"/>
|
||||
<path d="M166.934 34.0521V10.9618H170.5V34.0521H166.934Z" fill="#262626" style="fill:#262626;fill:color(display-p3 0.1500 0.1500 0.1500);fill-opacity:1;"/>
|
||||
</svg>
|
||||
|
After Width: | Height: | Size: 4.8 KiB |
+428
@@ -0,0 +1,428 @@
|
||||
<!DOCTYPE html>
|
||||
<html lang="en">
|
||||
<head>
|
||||
<meta charset="utf-8">
|
||||
<meta name="viewport" content="width=device-width, initial-scale=1">
|
||||
<title>pdf-inspector — PDF classification & text extraction, no OCR</title>
|
||||
<meta name="description" content="Fast Rust library that classifies PDFs (text-based vs scanned) and extracts clean Markdown — no OCR, no ML models. Bindings for Rust, Python, and Node.js.">
|
||||
<meta property="og:title" content="pdf-inspector">
|
||||
<meta property="og:description" content="Classify PDFs and extract clean Markdown in milliseconds. No OCR. No ML. Pure Rust.">
|
||||
<meta property="og:type" content="website">
|
||||
<link rel="icon" href="data:image/svg+xml,%3Csvg xmlns='http://www.w3.org/2000/svg' viewBox='0 0 100 100'%3E%3Ctext y='.9em' font-size='90'%3E%F0%9F%93%84%3C/text%3E%3C/svg%3E">
|
||||
<link rel="preconnect" href="https://fonts.googleapis.com">
|
||||
<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin>
|
||||
<link href="https://fonts.googleapis.com/css2?family=Bricolage+Grotesque:opsz,wght@12..96,400;12..96,600;12..96,800&family=Hanken+Grotesk:wght@400;500;600&family=JetBrains+Mono:wght@400;500;700&display=swap" rel="stylesheet">
|
||||
<style>
|
||||
:root {
|
||||
--paper: #f4efe4;
|
||||
--paper-2: #eee7d8;
|
||||
--ink: #1b1712;
|
||||
--ink-soft: #4a433a;
|
||||
--muted: #8b8375;
|
||||
--line: #d9cfbb;
|
||||
--accent: #dd3f22;
|
||||
--accent-deep: #b32d15;
|
||||
--card: #faf6ec;
|
||||
--display: "Bricolage Grotesque", serif;
|
||||
--body: "Hanken Grotesk", sans-serif;
|
||||
--mono: "JetBrains Mono", monospace;
|
||||
}
|
||||
* { box-sizing: border-box; margin: 0; padding: 0; }
|
||||
html { scroll-behavior: smooth; }
|
||||
body {
|
||||
background: var(--paper);
|
||||
color: var(--ink);
|
||||
font-family: var(--body);
|
||||
font-size: 17px;
|
||||
line-height: 1.6;
|
||||
-webkit-font-smoothing: antialiased;
|
||||
overflow-x: hidden;
|
||||
background-image:
|
||||
radial-gradient(circle at 1px 1px, rgba(27,23,18,0.05) 1px, transparent 0);
|
||||
background-size: 22px 22px;
|
||||
}
|
||||
::selection { background: var(--accent); color: var(--paper); }
|
||||
a { color: inherit; text-decoration: none; }
|
||||
|
||||
.wrap { max-width: 1120px; margin: 0 auto; padding: 0 28px; }
|
||||
|
||||
/* ── nav ── */
|
||||
nav {
|
||||
position: sticky; top: 0; z-index: 50;
|
||||
background: rgba(244,239,228,0.82);
|
||||
backdrop-filter: blur(10px);
|
||||
border-bottom: 1px solid var(--line);
|
||||
}
|
||||
.nav-in { display: flex; align-items: center; gap: 22px; height: 60px; }
|
||||
.brand { font-family: var(--mono); font-weight: 700; font-size: 15px; letter-spacing: -0.02em; display: flex; align-items: center; gap: 9px; }
|
||||
.brand .dot { width: 9px; height: 9px; background: var(--accent); border-radius: 50%; box-shadow: 0 0 0 3px rgba(221,63,34,0.18); }
|
||||
.nav-links { margin-left: auto; display: flex; gap: 24px; align-items: center; font-size: 14.5px; font-weight: 500; }
|
||||
.nav-links a { color: var(--ink-soft); transition: color .15s; }
|
||||
.nav-links a:hover { color: var(--accent); }
|
||||
.nav-gh { border: 1px solid var(--ink); border-radius: 999px; padding: 6px 15px; color: var(--ink) !important; transition: all .15s; }
|
||||
.nav-gh:hover { background: var(--ink); color: var(--paper) !important; }
|
||||
@media (max-width: 680px) { .nav-links .hide-sm { display: none; } }
|
||||
|
||||
/* ── hero ── */
|
||||
header { padding: 74px 0 40px; position: relative; }
|
||||
.eyebrow { font-family: var(--mono); font-size: 12.5px; letter-spacing: 0.16em; text-transform: uppercase; color: var(--accent-deep); margin-bottom: 22px; }
|
||||
h1 {
|
||||
font-family: var(--display);
|
||||
font-weight: 800;
|
||||
font-size: clamp(2.9rem, 8vw, 6.1rem);
|
||||
line-height: 0.96;
|
||||
letter-spacing: -0.035em;
|
||||
max-width: 15ch;
|
||||
}
|
||||
h1 .em { color: var(--accent); font-style: normal; position: relative; }
|
||||
h1 .strike { position: relative; white-space: nowrap; }
|
||||
h1 .strike::after { content: ""; position: absolute; left: -2%; right: -2%; top: 54%; height: 0.09em; background: var(--accent); transform: rotate(-3deg); }
|
||||
.lede { margin-top: 28px; font-size: clamp(1.05rem, 2.2vw, 1.32rem); color: var(--ink-soft); max-width: 46ch; line-height: 1.5; }
|
||||
.lede b { color: var(--ink); font-weight: 600; }
|
||||
|
||||
.hero-grid { display: grid; grid-template-columns: 1.15fr 0.85fr; gap: 48px; align-items: end; }
|
||||
@media (max-width: 880px) { .hero-grid { grid-template-columns: 1fr; gap: 40px; } }
|
||||
|
||||
/* readout card */
|
||||
.readout {
|
||||
background: var(--ink); color: var(--paper);
|
||||
border-radius: 14px; padding: 22px 22px 20px;
|
||||
font-family: var(--mono); font-size: 13px;
|
||||
box-shadow: 14px 14px 0 rgba(27,23,18,0.09);
|
||||
position: relative;
|
||||
}
|
||||
.readout .rlabel { color: #b8ad98; font-size: 11px; letter-spacing: 0.14em; text-transform: uppercase; margin-bottom: 16px; display: flex; justify-content: space-between; }
|
||||
.readout .rrow { display: flex; justify-content: space-between; align-items: center; padding: 9px 0; border-top: 1px solid rgba(255,255,255,0.09); }
|
||||
.readout .rrow:first-of-type { border-top: none; }
|
||||
.readout .k { color: #cfc6b3; }
|
||||
.readout .v { font-weight: 700; }
|
||||
.readout .v.hot { color: var(--accent); }
|
||||
.bar { height: 6px; background: rgba(255,255,255,0.1); border-radius: 3px; overflow: hidden; margin-top: 3px; width: 96px; }
|
||||
.bar > i { display: block; height: 100%; background: var(--accent); border-radius: 3px; }
|
||||
|
||||
/* ── install row ── */
|
||||
.installs { display: grid; grid-template-columns: repeat(3,1fr); gap: 14px; margin-top: 54px; }
|
||||
@media (max-width: 720px) { .installs { grid-template-columns: 1fr; } }
|
||||
.inst {
|
||||
background: var(--card); border: 1px solid var(--line); border-radius: 11px;
|
||||
padding: 15px 17px; transition: transform .16s, border-color .16s, box-shadow .16s;
|
||||
cursor: pointer;
|
||||
}
|
||||
.inst:hover { transform: translateY(-3px); border-color: var(--accent); box-shadow: 0 8px 22px rgba(27,23,18,0.07); }
|
||||
.inst .reg { font-family: var(--mono); font-size: 11px; letter-spacing: 0.12em; text-transform: uppercase; color: var(--muted); margin-bottom: 8px; display: flex; justify-content: space-between; }
|
||||
.inst code { font-family: var(--mono); font-size: 14px; color: var(--ink); font-weight: 500; }
|
||||
.inst .arrow { color: var(--accent); opacity: 0; transition: opacity .16s; }
|
||||
.inst:hover .arrow { opacity: 1; }
|
||||
|
||||
/* ── section scaffold ── */
|
||||
section { padding: 66px 0; border-top: 1px solid var(--line); }
|
||||
.sec-head { display: flex; align-items: baseline; gap: 16px; margin-bottom: 40px; flex-wrap: wrap; }
|
||||
.sec-num { font-family: var(--mono); font-size: 13px; color: var(--accent); font-weight: 700; }
|
||||
.sec-title { font-family: var(--display); font-weight: 600; font-size: clamp(1.7rem, 4vw, 2.6rem); letter-spacing: -0.025em; }
|
||||
.sec-sub { color: var(--ink-soft); max-width: 52ch; font-size: 1.02rem; }
|
||||
|
||||
/* ── features ── */
|
||||
.feat-grid { display: grid; grid-template-columns: repeat(4,1fr); gap: 1px; background: var(--line); border: 1px solid var(--line); border-radius: 14px; overflow: hidden; }
|
||||
@media (max-width: 900px) { .feat-grid { grid-template-columns: repeat(2,1fr); } }
|
||||
@media (max-width: 560px) { .feat-grid { grid-template-columns: 1fr; } }
|
||||
.feat { background: var(--card); padding: 24px 22px; transition: background .16s; }
|
||||
.feat:hover { background: #fff; }
|
||||
.feat .fn { font-family: var(--mono); font-size: 12px; color: var(--accent); font-weight: 700; }
|
||||
.feat h3 { font-family: var(--display); font-weight: 600; font-size: 1.16rem; margin: 12px 0 8px; letter-spacing: -0.01em; }
|
||||
.feat p { font-size: 14.5px; color: var(--ink-soft); line-height: 1.5; }
|
||||
|
||||
/* ── benchmark ── */
|
||||
.bench {
|
||||
border: 1px solid var(--line); border-radius: 14px; overflow: hidden;
|
||||
background: var(--card);
|
||||
}
|
||||
table { width: 100%; border-collapse: collapse; font-size: 15px; }
|
||||
thead th { font-family: var(--mono); font-size: 11px; letter-spacing: 0.08em; text-transform: uppercase; color: var(--muted); text-align: right; padding: 15px 18px; background: var(--paper-2); border-bottom: 1px solid var(--line); font-weight: 500; }
|
||||
thead th:first-child { text-align: left; }
|
||||
tbody td { padding: 14px 18px; text-align: right; font-family: var(--mono); border-bottom: 1px solid var(--line); }
|
||||
tbody td:first-child { text-align: left; font-family: var(--body); font-weight: 500; }
|
||||
tbody tr:last-child td { border-bottom: none; }
|
||||
tbody tr.us { background: rgba(221,63,34,0.06); }
|
||||
tbody tr.us td:first-child { color: var(--accent-deep); font-weight: 700; }
|
||||
tbody tr.us td:first-child::before { content: "▸ "; color: var(--accent); }
|
||||
.bench-foot { padding: 15px 18px; font-size: 13.5px; color: var(--ink-soft); background: var(--paper-2); border-top: 1px solid var(--line); }
|
||||
.bench-wrap { overflow-x: auto; }
|
||||
.callouts { display: grid; grid-template-columns: 1fr 1fr; gap: 16px; margin-top: 22px; }
|
||||
@media (max-width: 640px) { .callouts { grid-template-columns: 1fr; } }
|
||||
.callout { border-left: 3px solid var(--accent); padding: 4px 0 4px 16px; }
|
||||
.callout .ct { font-family: var(--mono); font-size: 11px; letter-spacing: 0.1em; text-transform: uppercase; color: var(--accent-deep); margin-bottom: 5px; }
|
||||
.callout p { font-size: 14.5px; color: var(--ink-soft); }
|
||||
|
||||
/* ── quickstart tabs ── */
|
||||
.tabs input { position: absolute; opacity: 0; pointer-events: none; }
|
||||
.tablist { display: flex; gap: 6px; margin-bottom: 0; }
|
||||
.tablist label {
|
||||
font-family: var(--mono); font-size: 13px; font-weight: 500;
|
||||
padding: 10px 18px; cursor: pointer; color: var(--muted);
|
||||
border: 1px solid var(--line); border-bottom: none;
|
||||
border-radius: 9px 9px 0 0; background: var(--paper-2); transition: all .15s;
|
||||
}
|
||||
.tablist label:hover { color: var(--ink); }
|
||||
.panel { display: none; }
|
||||
.code {
|
||||
background: var(--ink); border-radius: 0 12px 12px 12px;
|
||||
padding: 22px 24px; overflow-x: auto;
|
||||
font-family: var(--mono); font-size: 13.5px; line-height: 1.7;
|
||||
color: #e9e2d3;
|
||||
box-shadow: 12px 12px 0 rgba(27,23,18,0.07);
|
||||
}
|
||||
.code .cm { color: #8a8069; }
|
||||
.code .kw { color: #ff9f7a; }
|
||||
.code .st { color: #cbb78a; }
|
||||
.code .fn { color: #f4efe4; font-weight: 700; }
|
||||
#t-rust:checked ~ .tablist label[for=t-rust],
|
||||
#t-py:checked ~ .tablist label[for=t-py],
|
||||
#t-node:checked ~ .tablist label[for=t-node],
|
||||
#t-cli:checked ~ .tablist label[for=t-cli] {
|
||||
background: var(--ink); color: var(--paper); border-color: var(--ink);
|
||||
}
|
||||
#t-rust:checked ~ .panels #p-rust,
|
||||
#t-py:checked ~ .panels #p-py,
|
||||
#t-node:checked ~ .panels #p-node,
|
||||
#t-cli:checked ~ .panels #p-cli { display: block; }
|
||||
.code a.ref { color: #ff9f7a; border-bottom: 1px dotted #ff9f7a; }
|
||||
|
||||
/* ── closing split (OSS vs hosted) ── */
|
||||
.split { display: grid; grid-template-columns: 1fr 1fr; gap: 18px; }
|
||||
@media (max-width: 780px) { .split { grid-template-columns: 1fr; } }
|
||||
.path { border: 1px solid var(--line); border-radius: 16px; padding: 32px 30px; background: var(--card); display: flex; flex-direction: column; }
|
||||
.path .ptag { font-family: var(--mono); font-size: 11px; letter-spacing: 0.12em; text-transform: uppercase; color: var(--muted); margin-bottom: 15px; }
|
||||
.path h3 { font-family: var(--display); font-weight: 600; font-size: 1.5rem; letter-spacing: -0.02em; line-height: 1.05; margin-bottom: 12px; }
|
||||
.path p { color: var(--ink-soft); font-size: 15px; line-height: 1.5; flex: 1; margin-bottom: 24px; }
|
||||
.pbtns { display: flex; gap: 12px; flex-wrap: wrap; }
|
||||
.path-pro { background: var(--ink); border-color: var(--ink); box-shadow: 14px 14px 0 rgba(27,23,18,0.09); }
|
||||
.path-pro .ptag { color: #b8ad98; }
|
||||
.path-pro .ptag b { color: var(--accent); font-weight: 700; }
|
||||
.path-pro h3 { color: var(--paper); }
|
||||
.path-pro p { color: #cfc6b3; }
|
||||
.btn { font-family: var(--mono); font-size: 14px; font-weight: 500; padding: 13px 24px; border-radius: 999px; transition: all .15s; border: 1px solid var(--ink); }
|
||||
.btn-p { background: var(--accent); border-color: var(--accent); color: var(--paper); }
|
||||
.btn-p:hover { background: var(--accent-deep); border-color: var(--accent-deep); }
|
||||
.btn-s:hover { background: var(--ink); color: var(--paper); }
|
||||
.btn-pro { background: var(--accent); border-color: var(--accent); color: var(--paper); }
|
||||
.btn-pro:hover { background: var(--accent-deep); border-color: var(--accent-deep); }
|
||||
.btn-ghost { color: var(--paper); border-color: rgba(255,255,255,0.3); }
|
||||
.btn-ghost:hover { border-color: var(--paper); background: rgba(255,255,255,0.08); }
|
||||
.fc-mark { height: 34px; width: auto; display: block; margin-bottom: 20px; }
|
||||
.fc-wordmark { height: 15px; width: auto; vertical-align: -2px; transition: opacity .15s; }
|
||||
.fc-wordmark:hover { opacity: 0.65; }
|
||||
footer { border-top: 1px solid var(--line); padding: 34px 0; font-size: 14px; color: var(--muted); }
|
||||
.foot-in { display: flex; justify-content: space-between; align-items: center; gap: 18px; flex-wrap: wrap; }
|
||||
.foot-in a { color: var(--ink-soft); }
|
||||
.foot-in a:hover { color: var(--accent); }
|
||||
.foot-links { display: flex; gap: 20px; font-family: var(--mono); font-size: 13px; }
|
||||
|
||||
/* ── load animation ── */
|
||||
.reveal { opacity: 0; transform: translateY(14px); animation: rise .7s cubic-bezier(.2,.7,.3,1) forwards; }
|
||||
@keyframes rise { to { opacity: 1; transform: none; } }
|
||||
.d1 { animation-delay: .05s; } .d2 { animation-delay: .15s; } .d3 { animation-delay: .25s; }
|
||||
.d4 { animation-delay: .35s; } .d5 { animation-delay: .45s; } .d6 { animation-delay: .55s; }
|
||||
@media (prefers-reduced-motion: reduce) { .reveal { animation: none; opacity: 1; transform: none; } }
|
||||
</style>
|
||||
</head>
|
||||
<body>
|
||||
|
||||
<nav>
|
||||
<div class="wrap nav-in">
|
||||
<a href="#top" class="brand"><span class="dot"></span>pdf-inspector</a>
|
||||
<div class="nav-links">
|
||||
<a href="#features" class="hide-sm">Features</a>
|
||||
<a href="#benchmark" class="hide-sm">Benchmark</a>
|
||||
<a href="#start">Quick start</a>
|
||||
<a class="nav-gh" href="https://github.com/firecrawl/pdf-inspector">GitHub ↗</a>
|
||||
</div>
|
||||
</div>
|
||||
</nav>
|
||||
|
||||
<header id="top">
|
||||
<div class="wrap hero-grid">
|
||||
<div>
|
||||
<div class="eyebrow reveal d1">Rust · Python · Node · CLI</div>
|
||||
<h1 class="reveal d2">Classify PDFs. Extract Markdown. <span class="strike">No OCR.</span></h1>
|
||||
<p class="lede reveal d3">A fast Rust library that tells text-based PDFs from scanned ones, then extracts position-aware text and clean Markdown — <b>locally, in milliseconds</b>. Skip the OCR bill for the ~54% of PDFs that never needed it.</p>
|
||||
</div>
|
||||
<div class="readout reveal d4" aria-hidden="true">
|
||||
<div class="rlabel"><span>classify_pdf()</span><span>~12ms</span></div>
|
||||
<div class="rrow"><span class="k">type</span><span class="v hot">TextBased</span></div>
|
||||
<div class="rrow"><span class="k">confidence</span><span class="v">0.98</span></div>
|
||||
<div class="rrow"><span class="k">needs_ocr</span><span class="v">false</span></div>
|
||||
<div class="rrow"><span class="k">route</span><span class="v">local → md</span></div>
|
||||
<div class="rrow" style="border-top:1px solid rgba(255,255,255,.09);padding-top:13px">
|
||||
<span class="k">signal</span>
|
||||
<span class="bar"><i style="width:98%"></i></span>
|
||||
</div>
|
||||
</div>
|
||||
</div>
|
||||
|
||||
<div class="wrap">
|
||||
<div class="installs">
|
||||
<a class="inst reveal d4" href="https://crates.io/crates/pdf-inspector">
|
||||
<div class="reg"><span>crates.io</span><span class="arrow">↗</span></div>
|
||||
<code>cargo add pdf-inspector</code>
|
||||
</a>
|
||||
<a class="inst reveal d5" href="https://pypi.org/project/pdf-inspector/">
|
||||
<div class="reg"><span>PyPI</span><span class="arrow">↗</span></div>
|
||||
<code>pip install pdf-inspector</code>
|
||||
</a>
|
||||
<a class="inst reveal d6" href="https://www.npmjs.com/package/@firecrawl/pdf-inspector">
|
||||
<div class="reg"><span>npm</span><span class="arrow">↗</span></div>
|
||||
<code>npm i @firecrawl/pdf-inspector</code>
|
||||
</a>
|
||||
</div>
|
||||
</div>
|
||||
</header>
|
||||
|
||||
<section id="features">
|
||||
<div class="wrap">
|
||||
<div class="sec-head">
|
||||
<span class="sec-num">01</span>
|
||||
<h2 class="sec-title">Built for routing, not just reading</h2>
|
||||
</div>
|
||||
<div class="feat-grid">
|
||||
<div class="feat"><div class="fn">01</div><h3>Smart classification</h3><p>TextBased, Scanned, ImageBased, or Mixed in ~10–50ms by sampling content streams. Returns a confidence score and per-page OCR routing.</p></div>
|
||||
<div class="feat"><div class="fn">02</div><h3>Position-aware text</h3><p>Extraction with font info, X/Y coordinates, and automatic multi-column reading order.</p></div>
|
||||
<div class="feat"><div class="fn">03</div><h3>Markdown conversion</h3><p>Headings, bullet/numbered lists, code blocks, tables, bold/italic, URL linking, and page breaks.</p></div>
|
||||
<div class="feat"><div class="fn">04</div><h3>Table detection</h3><p>Rectangle-based detection from drawing ops plus heuristic alignment detection. Financial tables, footnotes, and cross-page continuations.</p></div>
|
||||
<div class="feat"><div class="fn">05</div><h3>CID font support</h3><p>ToUnicode CMap decoding for Type0/Identity-H fonts, with UTF-16BE, UTF-8, and Latin-1 encodings.</p></div>
|
||||
<div class="feat"><div class="fn">06</div><h3>Multi-column layout</h3><p>Newspaper-style column detection, sequential reading order, and right-to-left text support.</p></div>
|
||||
<div class="feat"><div class="fn">07</div><h3>Encoding checks</h3><p>Flags broken font encodings automatically so callers can fall back to OCR only when it's actually needed.</p></div>
|
||||
<div class="feat"><div class="fn">08</div><h3>Lightweight</h3><p>Pure Rust. No ML models, no external services. A single parse shared between detection and extraction.</p></div>
|
||||
</div>
|
||||
</div>
|
||||
</section>
|
||||
|
||||
<section id="benchmark">
|
||||
<div class="wrap">
|
||||
<div class="sec-head">
|
||||
<span class="sec-num">02</span>
|
||||
<h2 class="sec-title">Fastest of the direct-text engines</h2>
|
||||
<p class="sec-sub">Evaluated on the <a href="https://github.com/opendataloader-project/opendataloader-bench" style="color:var(--accent-deep);border-bottom:1px solid var(--line)">opendataloader-bench</a> corpus (200 PDFs). Direct text-extraction engines only — no OCR, no ML. Higher is better.</p>
|
||||
</div>
|
||||
<div class="bench">
|
||||
<div class="bench-wrap">
|
||||
<table>
|
||||
<thead>
|
||||
<tr><th>Engine</th><th>Overall</th><th>Reading order</th><th>Tables</th><th>Headings</th><th>200 docs</th></tr>
|
||||
</thead>
|
||||
<tbody>
|
||||
<tr class="us"><td>pdf-inspector</td><td>0.83</td><td>0.88</td><td>0.66</td><td>0.74</td><td>4s</td></tr>
|
||||
<tr><td>opendataloader</td><td>0.84</td><td>0.91</td><td>0.49</td><td>0.74</td><td>11s</td></tr>
|
||||
<tr><td>pymupdf4llm</td><td>0.73</td><td>0.89</td><td>0.40</td><td>0.41</td><td>18s</td></tr>
|
||||
<tr><td>markitdown</td><td>0.58</td><td>0.88</td><td>0.00</td><td>0.00</td><td>8s</td></tr>
|
||||
</tbody>
|
||||
</table>
|
||||
</div>
|
||||
<div class="bench-foot">OCR/ML engines (docling, marker, mineru) score 0.83–0.88 overall — but take 2–180 minutes on the same corpus.</div>
|
||||
</div>
|
||||
<div class="callouts">
|
||||
<div class="callout"><div class="ct">Where we win</div><p>Fastest engine measured, the best table detection of any engine here, and heading quality now on par with opendataloader — at ~2.5× its speed.</p></div>
|
||||
<div class="callout"><div class="ct">Where we're working</div><p>Reading order still trails opendataloader slightly, and tables that need the visual structure only an OCR engine can see.</p></div>
|
||||
</div>
|
||||
</div>
|
||||
</section>
|
||||
|
||||
<section id="start">
|
||||
<div class="wrap">
|
||||
<div class="sec-head">
|
||||
<span class="sec-num">03</span>
|
||||
<h2 class="sec-title">Three lines to Markdown</h2>
|
||||
</div>
|
||||
<div class="tabs">
|
||||
<input type="radio" name="tab" id="t-rust" checked>
|
||||
<input type="radio" name="tab" id="t-py">
|
||||
<input type="radio" name="tab" id="t-node">
|
||||
<input type="radio" name="tab" id="t-cli">
|
||||
<div class="tablist">
|
||||
<label for="t-rust">Rust</label>
|
||||
<label for="t-py">Python</label>
|
||||
<label for="t-node">Node.js</label>
|
||||
<label for="t-cli">CLI</label>
|
||||
</div>
|
||||
<div class="panels">
|
||||
<div class="panel" id="p-rust"><pre class="code"><span class="kw">use</span> pdf_inspector::process_pdf;
|
||||
|
||||
<span class="kw">let</span> result = <span class="fn">process_pdf</span>(<span class="st">"document.pdf"</span>)?;
|
||||
<span class="fn">println!</span>(<span class="st">"Type: {:?}"</span>, result.pdf_type);
|
||||
<span class="kw">if let</span> <span class="kw">Some</span>(markdown) = &result.markdown {
|
||||
<span class="fn">println!</span>(<span class="st">"{}"</span>, markdown);
|
||||
}
|
||||
<span class="cm">// full reference → </span><a class="ref" href="https://github.com/firecrawl/pdf-inspector/blob/main/docs/rust-api.md">docs/rust-api.md</a></pre></div>
|
||||
<div class="panel" id="p-py"><pre class="code"><span class="kw">import</span> pdf_inspector
|
||||
|
||||
result = pdf_inspector.<span class="fn">process_pdf</span>(<span class="st">"document.pdf"</span>)
|
||||
<span class="fn">print</span>(result.pdf_type) <span class="cm"># "text_based" | "scanned" | "image_based" | "mixed"</span>
|
||||
<span class="fn">print</span>(result.markdown) <span class="cm"># Markdown string or None</span>
|
||||
<span class="cm"># full reference → </span><a class="ref" href="https://github.com/firecrawl/pdf-inspector/blob/main/docs/python.md">docs/python.md</a></pre></div>
|
||||
<div class="panel" id="p-node"><pre class="code"><span class="kw">import</span> { readFileSync } <span class="kw">from</span> <span class="st">'fs'</span>;
|
||||
<span class="kw">import</span> { processPdf } <span class="kw">from</span> <span class="st">'@firecrawl/pdf-inspector'</span>;
|
||||
|
||||
<span class="kw">const</span> result = <span class="fn">processPdf</span>(<span class="fn">readFileSync</span>(<span class="st">'document.pdf'</span>));
|
||||
console.<span class="fn">log</span>(result.pdfType); <span class="cm">// "TextBased" | "Scanned" | ...</span>
|
||||
console.<span class="fn">log</span>(result.markdown); <span class="cm">// Markdown string or null</span>
|
||||
<span class="cm">// full reference → </span><a class="ref" href="https://github.com/firecrawl/pdf-inspector/blob/main/napi/README.md">napi/README.md</a></pre></div>
|
||||
<div class="panel" id="p-cli"><pre class="code"><span class="cm"># install the CLI tools</span>
|
||||
cargo <span class="fn">install</span> pdf-inspector
|
||||
|
||||
<span class="cm"># convert a PDF to Markdown</span>
|
||||
<span class="fn">pdf2md</span> document.pdf
|
||||
|
||||
<span class="cm"># classify only — is it scanned?</span>
|
||||
<span class="fn">detect-pdf</span> document.pdf --analyze --json
|
||||
|
||||
<span class="cm"># structured output for pipelines</span>
|
||||
<span class="fn">pdf2md</span> document.pdf --json</pre></div>
|
||||
</div>
|
||||
</div>
|
||||
</div>
|
||||
</section>
|
||||
|
||||
<section class="close">
|
||||
<div class="wrap">
|
||||
<div class="sec-head">
|
||||
<span class="sec-num">04</span>
|
||||
<h2 class="sec-title">Two ways to parse</h2>
|
||||
<p class="sec-sub">Run the classifier locally for text-based PDFs; hand the scanned, OCR, and at-scale work to Firecrawl.</p>
|
||||
</div>
|
||||
<div class="split">
|
||||
<div class="path">
|
||||
<div class="ptag">Open source · runs local</div>
|
||||
<h3>Use pdf-inspector yourself</h3>
|
||||
<p>Pure-Rust library and CLI. Classify and extract text-based PDFs on your own machine in milliseconds — no external calls, no OCR bill, MIT licensed.</p>
|
||||
<div class="pbtns">
|
||||
<a class="btn btn-p" href="https://github.com/firecrawl/pdf-inspector">Get started</a>
|
||||
<a class="btn btn-s" href="https://crates.io/crates/pdf-inspector">crates.io</a>
|
||||
</div>
|
||||
</div>
|
||||
<div class="path path-pro">
|
||||
<img class="fc-mark" src="assets/firecrawl-mark.svg" alt="Firecrawl" width="24" height="34">
|
||||
<div class="ptag"><b>Firecrawl Parse</b> · hosted API</div>
|
||||
<h3>Or let Firecrawl handle the hard ones</h3>
|
||||
<p>Scanned documents, OCR, DOCX / XLSX / HTML, and parsing at scale — clean, LLM-ready Markdown from one API call. The downstream route for everything local parsing can't reach.</p>
|
||||
<div class="pbtns">
|
||||
<a class="btn btn-pro" href="https://docs.firecrawl.dev/api-reference/endpoint/parse">Firecrawl Parse ↗</a>
|
||||
<a class="btn btn-ghost" href="https://firecrawl.dev">firecrawl.dev</a>
|
||||
</div>
|
||||
</div>
|
||||
</div>
|
||||
</div>
|
||||
</section>
|
||||
|
||||
<footer>
|
||||
<div class="wrap foot-in">
|
||||
<div style="display:flex;align-items:center;gap:7px">Built by <a href="https://firecrawl.dev"><img class="fc-wordmark" src="assets/firecrawl-wordmark.svg" alt="Firecrawl"></a> · MIT licensed</div>
|
||||
<div class="foot-links">
|
||||
<a href="https://github.com/firecrawl/pdf-inspector">GitHub</a>
|
||||
<a href="https://crates.io/crates/pdf-inspector">crates.io</a>
|
||||
<a href="https://pypi.org/project/pdf-inspector/">PyPI</a>
|
||||
<a href="https://www.npmjs.com/package/@firecrawl/pdf-inspector">npm</a>
|
||||
</div>
|
||||
</div>
|
||||
</footer>
|
||||
|
||||
</body>
|
||||
</html>
|
||||
Reference in New Issue
Block a user