Robust PDF Extraction

# Check file exists and get basic info
ls -la /path/to/document.pdf

# Or search for files if location uncertain
find /path -name "*.pdf" -type f 2>/dev/null

import pdfplumber

def extract_with_pdfplumber(pdf_path):
    text = ""
    with pdfplumber.open(pdf_path) as pdf:
        for page in pdf.pages:
            page_text = page.extract_text()
            if page_text:
                text += page_text + "\n"
    return text.strip()

import pdfium2

def extract_with_pypdfium2(pdf_path):
    pdf = pdfium2.PdfDocument(pdf_path)
    text = ""
    for page in pdf:
        text_page = page.get_textpage()
        page_text = text_page.get_text_bounded()
        if page_text:
            text += page_text + "\n"
    return text.strip()

pdftotext /path/to/document.pdf - 2>/dev/null

import subprocess

def extract_with_pdftotext(pdf_path):
    result = subprocess.run(
        ['pdftotext', pdf_path, '-'],
        capture_output=True,
        text=True
    )
    return result.stdout.strip()

def is_meaningful_text(text, min_chars=50):
    """Check if extracted text is meaningful (not empty or just whitespace)"""
    if not text:
        return False
    # Remove whitespace and check length
    cleaned = ''.join(text.split())
    return len(cleaned) >= min_chars

import pdf2image
import pytesseract
from PIL import Image

def extract_with_ocr(pdf_path, dpi=300):
    """Extract text from scanned PDFs using OCR"""
    text = ""
    images = pdf2image.convert_from_path(pdf_path, dpi=dpi)
    for image in images:
        page_text = pytesseract.image_to_string(image)
        text += page_text + "\n"
    return text.strip()

def robust_pdf_extract(pdf_path):
    """
    Extract text from PDF using progressive fallback methods.
    Returns (text, method_used) tuple.
    """
    methods = [
        ("pdfplumber", extract_with_pdfplumber),
        ("pypdfium2", extract_with_pypdfium2),
        ("pdftotext", extract_with_pdftotext),
    ]
    
    for method_name, extract_func in methods:
        try:
            text = extract_func(pdf_path)
            if is_meaningful_text(text):
                return text, method_name
        except Exception as e:
            print(f"{method_name} failed: {e}")
            continue
    
    # All text methods failed - try OCR
    try:
        text = extract_with_ocr(pdf_path)
        if is_meaningful_text(text):
            return text, "ocr"
    except Exception as e:
        print(f"OCR failed: {e}")
    
    return "", "failed"

pip install pdfplumber pypdfium2 pdf2image pytesseract pillow
# Also need system packages:
# apt-get install poppler-utils tesseract-ocr  # Debian/Ubuntu
# brew install poppler tesseract  # macOS