Pdf Reading

import pdfplumber
from pathlib import Path

def extract_pdf_text(pdf_path: str) -> str:
    """Extract all text from a PDF file."""
    text_parts = []
    with pdfplumber.open(pdf_path) as pdf:
        for page in pdf.pages:
            text = page.extract_text()
            if text:
                text_parts.append(text)
    return "\n\n".join(text_parts)

# Usage
text = extract_pdf_text("/root/artifacts/paper.pdf")
print(text)

Extracting Specific Information

Find Commands in Text

import re

def find_commands(text: str) -> list:
    """Extract shell commands from text."""
    # Look for common command patterns
    patterns = [
        r'docker run[^\n]+',
        r'\$[^\n]+',
        r'--package=[^\s]+\s+--version=[^\s]+',
    ]
    commands = []
    for pattern in patterns:
        commands.extend(re.findall(pattern, text))
    return commands

text = extract_pdf_text("/root/artifacts/paper.pdf")
commands = find_commands(text)

Extract Tables

import pdfplumber

def extract_tables(pdf_path: str) -> list:
    """Extract all tables from a PDF."""
    tables = []
    with pdfplumber.open(pdf_path) as pdf:
        for i, page in enumerate(pdf.pages):
            page_tables = page.extract_tables()
            for table in page_tables:
                tables.append({
                    "page": i + 1,
                    "data": table
                })
    return tables

Find Package Information

import re

def find_package_info(text: str) -> list:
    """Find npm package references (name@version)."""
    # Match patterns like [email protected]
    pattern = r'([a-z0-9-]+)@(\d+\.\d+\.\d+)'
    matches = re.findall(pattern, text.lower())
    return [{"name": m[0], "version": m[1]} for m in matches]

Tips

1. Check available PDFs first:

   ls -la /root/artifacts/
   

2. Preview before full extraction:

   pdftotext /root/artifacts/paper.pdf - | head -100
   

3. Handle multi-column layouts: pdfplumber handles them better than pdftotext

4. For structured data: Look for JSON blocks in the text:

   import json
   import re
   
   json_blocks = re.findall(r'\{[^{}]*\}', text)
   for block in json_blocks:
       try:
           data = json.loads(block)
           print(data)
       except json.JSONDecodeError:
           pass