PDF Analysis

Step 0, Detect PDF type (text vs scanned)

Critical first step: determine whether the PDF has extractable text or is a scanned image. Never skip this, using the wrong parser wastes time and produces empty results.

import fitz  # PyMuPDF

def detect_pdf_type(pdf_path, sample_pages=3):
    """
    Returns 'text' if PDF has extractable text, 'scanned' if image-based.
    Checks first N pages (or all if fewer).
    """
    doc = fitz.open(pdf_path)
    total_chars = 0
    pages_checked = min(sample_pages, len(doc))

    for i in range(pages_checked):
        page = doc[i]
        text = page.get_text("text")
        total_chars += len(text.strip())

    doc.close()
    avg_chars = total_chars / max(pages_checked, 1)
    pdf_type = 'text' if avg_chars > 50 else 'scanned'
    print(f"PDF type: {pdf_type} (avg {avg_chars:.0f} chars/page, checked {pages_checked} pages)")
    return pdf_type

---

Core Method 1: Text PDF, Full Text Extraction (ALL pages)

import fitz

def extract_text_pdf(pdf_path):
    """Extract text from all pages of a text-based PDF."""
    doc = fitz.open(pdf_path)
    total_pages = len(doc)
    print(f"Total pages: {total_pages}")

    all_text = []
    for i, page in enumerate(doc):
        text = page.get_text("text").strip()
        if text:
            all_text.append(f"=== Page {i+1} ===\n{text}")
        else:
            print(f"  Page {i+1}: no text (may be image, will caption later)")

    doc.close()
    return '\n\n'.join(all_text)

# ⚠️ MUST iterate ALL pages, never stop at page 1
full_text = extract_text_pdf(pdf_path)
print(f"Total text length: {len(full_text)} chars")

---

Core Method 2: Text PDF, Table Extraction

For PDFs with tables, pdfplumber gives better table structure than fitz:

import pdfplumber
import pandas as pd