From 4402f2ea4bdfce0f18834f6ae30d5b188c241e41 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=C3=81sgeir=20Thor=20Johnson?= Date: Thu, 2 Oct 2025 08:12:17 +0000 Subject: [PATCH] Create pdf.md --- Anthropic/pdf.md | 297 +++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 297 insertions(+) create mode 100644 Anthropic/pdf.md diff --git a/Anthropic/pdf.md b/Anthropic/pdf.md new file mode 100644 index 0000000..30b8f18 --- /dev/null +++ b/Anthropic/pdf.md @@ -0,0 +1,297 @@ +# PDF Processing (/mnt/skills/public/pdf/SKILL.md) + +--- +name: PDF Processing +description: Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. +when_to_use: When Claude needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale. +version: 0.0.1 +dependencies: pytesseract>=0.3.10, pdf2image>=1.16.0 +--- + +# PDF Processing Guide + +## Overview + +This guide covers essential PDF processing operations using Python libraries and command-line tools. For advanced features, JavaScript libraries, and detailed examples, see REFERENCE.md. If you need to fill out a PDF form, read FORMS.md and follow its instructions. + +## Quick Start +```python +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() +``` + +## Python Libraries + +### pypdf - Basic Operations + +#### Merge PDFs +```python +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) +``` + +#### Split PDF +```python +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) +``` + +#### Extract Metadata +```python +reader = PdfReader("document.pdf") +meta = reader.metadata +print(f"Title: {meta.title}") +print(f"Author: {meta.author}") +print(f"Subject: {meta.subject}") +print(f"Creator: {meta.creator}") +``` + +#### Rotate Pages +```python +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) +``` + +### pdfplumber - Text and Table Extraction + +#### Extract Text with Layout +```python +import pdfplumber + +with pdfplumber.open("document.pdf") as pdf: + for page in pdf.pages: + text = page.extract_text() + print(text) +``` + +#### Extract Tables +```python +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) +``` + +#### Advanced Table Extraction +```python +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: # Check if table is not empty + df = pd.DataFrame(table[1:], columns=table[0]) + all_tables.append(df) + +# Combine all tables +if all_tables: + combined_df = pd.concat(all_tables, ignore_index=True) + combined_df.to_excel("extracted_tables.xlsx", index=False) +``` + +### reportlab - Create PDFs + +#### Basic PDF Creation +```python +from reportlab.lib.pagesizes import letter +from reportlab.pdfgen import canvas + +c = canvas.Canvas("hello.pdf", pagesize=letter) +width, height = letter + +# Add text +c.drawString(100, height - 100, "Hello World!") +c.drawString(100, height - 120, "This is a PDF created with reportlab") + +# Add a line +c.line(100, height - 140, 400, height - 140) + +# Save +c.save() +``` + +#### Create PDF with Multiple Pages +```python +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 = [] + +# Add content +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()) + +# Page 2 +story.append(Paragraph("Page 2", styles['Heading1'])) +story.append(Paragraph("Content for page 2", styles['Normal'])) + +# Build PDF +doc.build(story) +``` + +## Command-Line Tools + +### pdftotext (poppler-utils) +```bash +# 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 +``` + +### qpdf +```bash +# Merge PDFs +qpdf --empty --pages file1.pdf file2.pdf -- merged.pdf + +# Split pages +qpdf input.pdf --pages . 1-5 -- pages1-5.pdf +qpdf input.pdf --pages . 6-10 -- pages6-10.pdf + +# Rotate pages +qpdf input.pdf output.pdf --rotate=+90:1 # Rotate page 1 by 90 degrees + +# Remove password +qpdf --password=mypassword --decrypt encrypted.pdf decrypted.pdf +``` + +### pdftk (if available) +```bash +# Merge +pdftk file1.pdf file2.pdf cat output merged.pdf + +# Split +pdftk input.pdf burst + +# Rotate +pdftk input.pdf rotate 1east output rotated.pdf +``` + +## Common Tasks + +### Extract Text from Scanned PDFs +```python +# Requires: pip install pytesseract pdf2image +import pytesseract +from pdf2image import convert_from_path + +# Convert PDF to images +images = convert_from_path('scanned.pdf') + +# OCR each page +text = "" +for i, image in enumerate(images): + text += f"Page {i+1}:\n" + text += pytesseract.image_to_string(image) + text += "\n\n" + +print(text) +``` + +### Add Watermark +```python +from pypdf import PdfReader, PdfWriter + +# Create watermark (or load existing) +watermark = PdfReader("watermark.pdf").pages[0] + +# Apply to all pages +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) +``` + +### Extract Images +```bash +# Using pdfimages (poppler-utils) +pdfimages -j input.pdf output_prefix + +# This extracts all images as output_prefix-000.jpg, output_prefix-001.jpg, etc. +``` + +### Password Protection +```python +from pypdf import PdfReader, PdfWriter + +reader = PdfReader("input.pdf") +writer = PdfWriter() + +for page in reader.pages: + writer.add_page(page) + +# Add password +writer.encrypt("userpassword", "ownerpassword") + +with open("encrypted.pdf", "wb") as output: + writer.write(output) +``` + +## Quick Reference + +| Task | Best Tool | Command/Code | +|------|-----------|--------------| +| Merge PDFs | pypdf | `writer.add_page(page)` | +| Split PDFs | pypdf | One page per file | +| Extract text | pdfplumber | `page.extract_text()` | +| Extract tables | pdfplumber | `page.extract_tables()` | +| Create PDFs | reportlab | Canvas or Platypus | +| Command line merge | qpdf | `qpdf --empty --pages ...` | +| OCR scanned PDFs | pytesseract | Convert to image first | +| Fill PDF forms | pdf-lib or pypdf (see FORMS.md) | See FORMS.md | + +## Next Steps + +- For advanced pypdfium2 usage, see REFERENCE.md +- For JavaScript libraries (pdf-lib), see REFERENCE.md +- If you need to fill out a PDF form, follow the instructions in FORMS.md +- For troubleshooting guides, see REFERENCE.md