ExisPdfPythonDemo/examples/03_text_extraction.py at main · exisllc/ExisPdfPythonDemo · GitHub

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
52
53
54
"""
03 - Text extraction.

Two modes:
- Plain text (.fullText / per-page .text)
- Structured (per-block coordinates, font name, font size)

Run:
    python examples/03_text_extraction.py
"""

from _common import header, info, success, get_sample_pdf, init_license

import exis_pdfeditor


def main() -> None:
    init_license()
    header("Demo 03 - Text Extraction")

    sample = get_sample_pdf()

    # Plain text
    info("Plain text extraction...")
    result = exis_pdfeditor.extract_text(str(sample))
    success(f"Extracted {len(result.fullText):,} characters from {len(result.pages)} pages")

    if result.pages:
        first_page_preview = result.pages[0].text[:200].replace("\n", " ")
        print(f"      First page preview: {first_page_preview}...")

    # Specific pages
    info("Extracting only page 1...")
    page_result = exis_pdfeditor.extract_text(str(sample), pages=[1])
    success(f"Page 1: {len(page_result.fullText):,} characters")

    # Structured (positions, fonts)
    info("Structured extraction...")
    structured = exis_pdfeditor.extract_text_structured(str(sample))
    if structured.pages:
        page1 = structured.pages[0]
        success(f"Page 1 has {len(page1.textBlocks)} text blocks")
        print()
        info("First 5 text blocks on page 1:")
        for block in page1.textBlocks[:5]:
            text_preview = block.text[:50].replace("\n", " ")
            print(
                f"      [{block.x:6.1f}, {block.y:6.1f}] "
                f"{block.fontName} {block.fontSize:.1f}pt: {text_preview}"
            )


if __name__ == "__main__":
    main()