Cleans up a specific type of bad conversion from pdf to epub

cleanupepub.py

import re, os, sys

path = "EXTRACTED EPUB CONTENTS"

dirs = os.listdir(path)

for file in dirs:
    if '.html' in file:
        with open(path + "\\" + file, "r+") as f:
            data = f.read()
            data = data.replace('<p class="calibre1"><a id="12"></a>3RD PASS MASTER</p>', '')
            data = data.replace('<p class="calibre1">12/29/11   11:58 AM</p>', '')
            data = data.replace('<p class="calibre1">1L</p>', '')
            data = data.replace('<p class="calibre1">index</p>', '')
            data = data.replace('<p class="calibre1">R</p>', '')
            data = data.replace('<p class="calibre1">1S</p>', '')
            data = data.replace('<p class="calibre1">Intentional Blank</p>', '')
            data = data.replace('1S', '')
            data = data.replace('1L', '')
            data = data.replace('<p class="calibre1">1S</p>', '')
            data = data.replace(' R<', ' <')

            
            data = re.sub('<p class="calibre1">1S<\/p>((.|\n)*)<p class="calibre1"><a id="11"><\/a>3RD PASS MASTER<\/p>', '', data)
            data = re.sub('<p class="calibre1">85885_TheArt(.*).indd(.*)<\/p>', '', data)
            data = re.sub('<p class="calibre1"><a id="(.*)"><\/a>3RD PASS MASTER<\/p>', '', data)
            data = re.sub('<p class="calibre1"> <i class="calibre3">(.*)<\/i><\/p>', '', data)
            data = re.sub('Th</p>((\n)*)<p class="calibre1">', 'Th', data)
            data = re.sub('(?<=[A-z])<\/p>(\n*)<p class="calibre1">(?=[A-z])', '', data)
            data = re.sub('(?<=[A-z])-<\/p>(\n*)<p class="calibre1">(?=[A-z])', '', data)
            data = re.sub('(?<=[A-z]\s)<\/p>(\n*)<p class="calibre1">(?=[A-z])', '', data)
            
            
            data = re.sub(r'\n\s*\n', '\n', data)
            f.seek(0)
            f.write(data)
            f.truncate()