import pdfplumber

# Document metadata
print(pdf.metadata)

# Number of pages
print(len(pdf.pages))

undefined

PDF Document
├── metadata (title, author, creation date)
├── pages[]
│   ├── chars (individual characters with position)
│   ├── words (grouped characters)
│   ├── lines (horizontal/vertical lines)
│   ├── rects (rectangles)
│   ├── curves (bezier curves)
│   └── images (embedded images)
└── outline (bookmarks/TOC)

with pdfplumber.open('document.pdf') as pdf:
    # Single page
    text = pdf.pages[0].extract_text()
    
    # All pages
    full_text = ''
    for page in pdf.pages:
        full_text += page.extract_text() or ''

undefined

undefined

undefined

undefined

with pdfplumber.open('report.pdf') as pdf:
    page = pdf.pages[0]
    
    # Extract all tables
    tables = page.extract_tables()
    
    for i, table in enumerate(tables):
        print(f"Table {i+1}:")
        for row in table:
            print(row)

undefined

undefined

undefined

# Extract specific table
data = table.extract()

undefined

undefined

undefined

undefined

undefined

undefined

undefined

undefined

undefined

with pdfplumber.open('document.pdf') as pdf:
    # Document metadata
    meta = pdf.metadata
    print(f"Title: {meta.get('Title')}")
    print(f"Author: {meta.get('Author')}")
    print(f"Created: {meta.get('CreationDate')}")
    
    # Page info
    for i, page in enumerate(pdf.pages):
        print(f"Page {i+1}: {page.width} x {page.height}")
        print(f"  Rotation: {page.rotation}")

import pandas as pd

def pdf_tables_to_dataframes(pdf_path):
    """Extract all tables from PDF as pandas DataFrames."""
    dfs = []
    
    with pdfplumber.open(pdf_path) as pdf:
        for i, page in enumerate(pdf.pages):
            tables = page.extract_tables()
            
            for j, table in enumerate(tables):
                if table and len(table) > 1:
                    # First row as header
                    df = pd.DataFrame(table[1:], columns=table[0])
                    df['_page'] = i + 1
                    df['_table'] = j + 1
                    dfs.append(df)
    
    return dfs

def extract_invoice_amount(pdf_path):
    """Extract amount from typical invoice layout."""
    with pdfplumber.open(pdf_path) as pdf:
        page = pdf.pages[0]
        
        # Search for "Total" and get nearby numbers
        words = page.extract_words()
        
        for i, word in enumerate(words):
            if 'total' in word['text'].lower():
                # Look at next few words
                for next_word in words[i+1:i+5]:
                    text = next_word['text'].replace(',', '').replace('$', '')
                    try:
                        return float(text)
                    except ValueError:
                        continue
    
    return None

def extract_columns(page, num_columns=2):
    """Extract text from multi-column layout."""
    width = page.width
    col_width = width / num_columns
    
    columns = []
    for i in range(num_columns):
        x0 = i * col_width
        x1 = (i + 1) * col_width
        
        cropped = page.crop((x0, 0, x1, page.height))
        columns.append(cropped.extract_text())
    
    return columns

import pdfplumber
import pandas as pd

def extract_financial_tables(pdf_path):
    """Extract tables from financial report and save to Excel."""
    
    with pdfplumber.open(pdf_path) as pdf:
        all_tables = []
        
        for page_num, page in enumerate(pdf.pages):
            # Debug: save table visualization
            im = page.to_image()
            im.debug_tablefinder()
            im.save(f'debug_page_{page_num+1}.png')
            
            # Extract tables
            tables = page.extract_tables({
                "vertical_strategy": "lines",
                "horizontal_strategy": "lines",
                "snap_tolerance": 5,
            })
            
            for table in tables:
                if table and len(table) > 1:
                    # Clean data
                    clean_table = []
                    for row in table:
                        clean_row = [cell.strip() if cell else '' for cell in row]
                        clean_table.append(clean_row)
                    
                    df = pd.DataFrame(clean_table[1:], columns=clean_table[0])
                    df['Source Page'] = page_num + 1
                    all_tables.append(df)
        
        # Save to Excel with multiple sheets
        with pd.ExcelWriter('extracted_tables.xlsx') as writer:
            for i, df in enumerate(all_tables):
                df.to_excel(writer, sheet_name=f'Table_{i+1}', index=False)
        
        return all_tables

tables = extract_financial_tables('annual_report.pdf')
print(f"Extracted {len(tables)} tables")

import pdfplumber
import re
from datetime import datetime

def extract_invoice_data(pdf_path):
    """Extract structured data from invoice PDF."""
    
    data = {
        'invoice_number': None,
        'date': None,
        'total': None,
        'line_items': []
    }
    
    with pdfplumber.open(pdf_path) as pdf:
        page = pdf.pages[0]
        text = page.extract_text()
        
        # Extract invoice number
        inv_match = re.search(r'Invoice\s*#?\s*:?\s*(\w+)', text, re.IGNORECASE)
        if inv_match:
            data['invoice_number'] = inv_match.group(1)
        
        # Extract date
        date_match = re.search(r'Date\s*:?\s*(\d{1,2}[/-]\d{1,2}[/-]\d{2,4})', text)
        if date_match:
            data['date'] = date_match.group(1)
        
        # Extract total
        total_match = re.search(r'Total\s*:?\s*\$?([\d,]+\.?\d*)', text, re.IGNORECASE)
        if total_match:
            data['total'] = float(total_match.group(1).replace(',', ''))
        
        # Extract line items from table
        tables = page.extract_tables()
        for table in tables:
            if table and any('description' in str(row).lower() for row in table[:2]):
                # Found line items table
                for row in table[1:]:  # Skip header
                    if row and len(row) >= 3:
                        data['line_items'].append({
                            'description': row[0],
                            'quantity': row[1] if len(row) > 1 else None,
                            'amount': row[-1]
                        })
    
    return data

invoice = extract_invoice_data('invoice.pdf')
print(f"Invoice #{invoice['invoice_number']}")
print(f"Total: ${invoice['total']}")

import pdfplumber

def parse_resume(pdf_path):
    """Extract structured sections from resume."""
    
    with pdfplumber.open(pdf_path) as pdf:
        full_text = ''
        for page in pdf.pages:
            full_text += (page.extract_text() or '') + '\n'
        
        # Common resume sections
        sections = {
            'contact': '',
            'summary': '',
            'experience': '',
            'education': '',
            'skills': ''
        }
        
        # Split by common headers
        import re
        section_patterns = {
            'summary': r'(summary|objective|profile)',
            'experience': r'(experience|employment|work history)',
            'education': r'(education|academic)',
            'skills': r'(skills|competencies|technical)'
        }
        
        lines = full_text.split('\n')
        current_section = 'contact'
        
        for line in lines:
            line_lower = line.lower().strip()
            
            # Check if line is a section header
            for section, pattern in section_patterns.items():
                if re.match(pattern, line_lower):
                    current_section = section
                    break
            
            sections[current_section] += line + '\n'
        
        return sections

resume = parse_resume('resume.pdf')
print("Skills:", resume['skills'])

pip install pdfplumber

undefined