thearchitectit/awesome-cline-skills/pdf

from pypdf import PdfReader, PdfWriter
# Read a PDF
reader = PdfReader("document.pdf")
print(f"Pages: {len(reader.pages)}")
# Extract text
text = ""
for page in reader.pages:
    text += page.extract_text()

from pypdf import PdfWriter, PdfReader
writer = PdfWriter()
for pdf_file in ["doc1.pdf", "doc2.pdf", "doc3.pdf"]:
    reader = PdfReader(pdf_file)
    for page in reader.pages:
        writer.add_page(page)
with open("merged.pdf", "wb") as output:
    writer.write(output)

reader = PdfReader("input.pdf")
for i, page in enumerate(reader.pages):
    writer = PdfWriter()
    writer.add_page(page)
    with open(f"page_{i+1}.pdf", "wb") as output:
        writer.write(output)

reader = PdfReader("document.pdf")
meta = reader.metadata
print(f"Title: {meta.title}")
print(f"Author: {meta.author}")
print(f"Subject: {meta.subject}")

reader = PdfReader("input.pdf")
writer = PdfWriter()
page = reader.pages[0]
page.rotate(90)  # Rotate 90 degrees clockwise
writer.add_page(page)
with open("rotated.pdf", "wb") as output:
    writer.write(output)

import pdfplumber
with pdfplumber.open("document.pdf") as pdf:
    for page in pdf.pages:
        text = page.extract_text()
        print(text)

with pdfplumber.open("document.pdf") as pdf:
    for i, page in enumerate(pdf.pages):
        tables = page.extract_tables()
        for j, table in enumerate(tables):
            print(f"Table {j+1} on page {i+1}:")
            for row in table:
                print(row)

import pandas as pd
with pdfplumber.open("document.pdf") as pdf:
    all_tables = []
    for page in pdf.pages:
        tables = page.extract_tables()
        for table in tables:
            if table:
                df = pd.DataFrame(table[1:], columns=table[0])
                all_tables.append(df)
if all_tables:
    combined_df = pd.concat(all_tables, ignore_index=True)
    combined_df.to_excel("extracted_tables.xlsx", index=False)

from reportlab.lib.pagesizes import letter
from reportlab.pdfgen import canvas
c = canvas.Canvas("hello.pdf", pagesize=letter)
width, height = letter
c.drawString(100, height - 100, "Hello World!")
c.drawString(100, height - 120, "This is a PDF created with reportlab")
c.line(100, height - 140, 400, height - 140)
c.save()

from reportlab.lib.pagesizes import letter
from reportlab.platypus import SimpleDocTemplate, Paragraph, Spacer, PageBreak
from reportlab.lib.styles import getSampleStyleSheet
doc = SimpleDocTemplate("report.pdf", pagesize=letter)
styles = getSampleStyleSheet()
story = []
title = Paragraph("Report Title", styles['Title'])
story.append(title)
story.append(Spacer(1, 12))
body = Paragraph("This is the body of the report. " * 20, styles['Normal'])
story.append(body)
story.append(PageBreak())
story.append(Paragraph("Page 2", styles['Heading1']))
story.append(Paragraph("Content for page 2", styles['Normal']))
doc.build(story)

# Extract text
pdftotext input.pdf output.txt
 
# Extract text preserving layout
pdftotext -layout input.pdf output.txt
 
# Extract specific pages
pdftotext -f 1 -l 5 input.pdf output.txt  # Pages 1-5

# Merge PDFs
qpdf --empty --pages file1.pdf file2.pdf -- merged.pdf
 
# Split pages
qpdf input.pdf --pages . 1-5 -- pages1-5.pdf
 
# Rotate pages
qpdf input.pdf output.pdf --rotate=+90:1
 
# Remove password
qpdf --password=mypassword --decrypt encrypted.pdf decrypted.pdf

# Requires: pip install pytesseract pdf2image
import pytesseract
from pdf2image import convert_from_path
images = convert_from_path('scanned.pdf')
text = ""
for i, image in enumerate(images):
    text += f"Page {i+1}:\n"
    text += pytesseract.image_to_string(image)
    text += "\n\n"

from pypdf import PdfReader, PdfWriter
watermark = PdfReader("watermark.pdf").pages[0]
reader = PdfReader("document.pdf")
writer = PdfWriter()
for page in reader.pages:
    page.merge_page(watermark)
    writer.add_page(page)
with open("watermarked.pdf", "wb") as output:
    writer.write(output)

from pypdf import PdfReader, PdfWriter
reader = PdfReader("input.pdf")
writer = PdfWriter()
for page in reader.pages:
    writer.add_page(page)
writer.encrypt("userpassword", "ownerpassword")
with open("encrypted.pdf", "wb") as output:
    writer.write(output)

pip install pypdf pdfplumber reportlab pytesseract pdf2image
sudo apt-get install poppler-utils tesseract-ocr qpdf