Untitled

from PyPDF2 import PdfReader
from reportlab.platypus import SimpleDocTemplate, Paragraph
from reportlab.lib.styles import getSampleStyleSheet
from xml.sax.saxutils import escape
import re

# Input and output file paths
input_pdf = "GmailSherlock - 1.pdf"
output_pdf = "CleanedMail.pdf"

# Read the original PDF
reader = PdfReader(input_pdf)
styles = getSampleStyleSheet()
content = []

for page in reader.pages:
    text = page.extract_text()
    if not text:
        continue

    cleaned_lines = []
    skip_block = False
    for line in text.split("\n"):
        # Remove [Quoted text hidden]
        if "[Quoted text hidden]" in line:
            continue

        # Detect start of Gmail-style quoted reply
        if re.match(r"^On .* wrote:$", line.strip()):
            skip_block = True
            continue

        # Skip lines while inside quoted block
        if skip_block:
            if line.strip() == "":
                skip_block = False
            continue

        cleaned_lines.append(line)

    cleaned_text = "\n".join(cleaned_lines)

    # Add cleaned text to PDF story
    for para in cleaned_text.split("\n"):
        if para.strip():  # skip empty lines
            safe_text = escape(para)  # escape special characters
            content.append(Paragraph(safe_text, styles["Normal"]))

# Write the cleaned PDF
pdf = SimpleDocTemplate(output_pdf)
pdf.build(content)

print(f"Cleaned PDF saved as {output_pdf}")