pdf_oxide 0.3.24

The fastest Rust PDF library with text extraction: 0.8ms mean, 100% pass rate on 3,830 PDFs. 5× faster than pdf_extract, 17× faster than oxidize_pdf. Extract, create, and edit PDFs.
Documentation 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51

// Extract words with bounding boxes and tables from a PDF page.
// Run: node index.js document.pdf

const binding = require("pdf-oxide");

const path = process.argv[2];
if (!path) {
  console.error("Usage: node index.js <file.pdf>");
  process.exit(1);
}

const handle = binding.open(path);
try {
  console.log(`Opened: ${path}`);

  const page = 0;

  // Extract words with position data
  const words = binding.extractWords(handle, page);
  console.log(`\n--- Words (page ${page + 1}) ---`);
  words.slice(0, 20).forEach((w) => {
    console.log(
      `"${w.text}"`.padEnd(20) +
        ` x=${w.x.toFixed(1).padEnd(7)} y=${w.y.toFixed(1).padEnd(7)}` +
        ` w=${w.width.toFixed(1).padEnd(7)} h=${w.height.toFixed(1).padEnd(7)}` +
        ` font=${w.fontName}  size=${w.fontSize.toFixed(1)}`
    );
  });
  if (words.length > 20) {
    console.log(`... (${words.length - 20} more words)`);
  }

  // Extract tables
  const tables = binding.extractTables(handle, page);
  console.log(`\n--- Tables (page ${page + 1}) ---`);
  if (tables.length === 0) {
    console.log("(no tables found)");
  }
  tables.forEach((t, i) => {
    console.log(`Table ${i + 1}: ${t.rows} rows x ${t.cols} cols`);
    t.cells.slice(0, 5).forEach((row, r) => {
      const cells = row
        .slice(0, 6)
        .map((v, c) => `[${r},${c}] "${v}"`)
        .join("  ");
      console.log(`  ${cells}`);
    });
  });
} finally {
  binding.close(handle);
}