pdf

PDF Skill

Manipulacao completa de PDFs: criar, editar, merge, split, extrair texto/tabelas, OCR, watermark, protecao.

Quick Reference

Python Libraries

pypdf — Merge, Split, Rotate, Encrypt

from pypdf import PdfReader, PdfWriter, PdfMerger

# Read
reader = PdfReader("input.pdf")
print(f"Pages: {len(reader.pages)}")
text = reader.pages[0].extract_text()

# Merge multiple PDFs
merger = PdfMerger()
for pdf in ["a.pdf", "b.pdf", "c.pdf"]:
    merger.append(pdf)
merger.write("merged.pdf")
merger.close()

# Split — extract pages 2-5
writer = PdfWriter()
for i in range(1, 5):  # 0-indexed
    writer.add_page(reader.pages[i])
writer.write("pages_2_to_5.pdf")

# Rotate page
writer = PdfWriter()
for page in reader.pages:
    page.rotate(90)  # 90, 180, 270
    writer.add_page(page)
writer.write("rotated.pdf")

# Encrypt with password
writer = PdfWriter()
writer.append_pages_from_reader(reader)
writer.encrypt("user_password", "owner_password")
writer.write("encrypted.pdf")

# Decrypt
reader = PdfReader("encrypted.pdf")
reader.decrypt("password")

# Fill form fields
reader = PdfReader("form.pdf")
writer = PdfWriter()
writer.append_pages_from_reader(reader)
writer.update_page_form_field_values(
    writer.pages[0],
    {"field_name": "value", "another_field": "value2"}
)
writer.write("filled_form.pdf")

pdfplumber — Extract Text and Tables

import pdfplumber

with pdfplumber.open("input.pdf") as pdf:
    # Extract text from all pages
    for page in pdf.pages:
        text = page.extract_text()
        print(text)

    # Extract tables
    for page in pdf.pages:
        tables = page.extract_tables()
        for table in tables:
            for row in table:
                print(row)

    # Extract table as pandas DataFrame
    import pandas as pd
    table = pdf.pages[0].extract_tables()[0]
    df = pd.DataFrame(table[1:], columns=table[0])