HowToWinAtGobletGrotto combine supplementary pages

combine.py

import os
import re
import glob

base_dir = '/home/xk/Downloads/WIN/HowToWinAtGobletGrotto/BOOK'
par_dir = os.path.join(base_dir, 'par')
out_file = os.path.join(base_dir, 'supplementary.html')

with open(os.path.join(base_dir, 'paragraphs.html'), 'r', encoding='ISO-8859-1') as f:
    paragraphs_html = f.read()

# Replace links in paragraphs.html
paragraphs_html = re.sub(r'href="par/([^"]+)\.html"', r'href="#\1"', paragraphs_html)

# Extract body contents of paragraphs.html
m = re.search(r'(.*<body[^>]*>)(.*?)(</body>.*)', paragraphs_html, re.IGNORECASE | re.DOTALL)
if not m:
    print("Could not parse paragraphs.html")
    exit(1)

head = m.group(1)
toc_body = m.group(2)
tail = m.group(3)

# Get all files in par/
files = sorted([f for f in os.listdir(par_dir) if f.endswith('.html')])

combined_body = toc_body + "\n<hr>\n<h1>SUPPLEMENTARY PAGES</h1>\n"

for f in files:
    file_id = f[:-5] # remove .html
    filepath = os.path.join(par_dir, f)
    with open(filepath, 'r', encoding='ISO-8859-1') as html_file:
        content = html_file.read()
        
    # Extract body
    bm = re.search(r'<body([^>]*)>(.*?)</body>', content, re.IGNORECASE | re.DOTALL)
    if bm:
        body_attrs = bm.group(1)
        inner_html = bm.group(2)
        
        # Extract background if any
        bg_match = re.search(r'background="([^"]+)"', body_attrs, re.IGNORECASE)
        bg_style = ""
        if bg_match:
            bg_url = bg_match.group(1).replace('../', '')
            bg_style = f"background-image: url('{bg_url}'); "
        
        # Strip absolute positioning
        inner_html = re.sub(r'position:\s*absolute;?', 'position: relative;', inner_html, flags=re.IGNORECASE)
        inner_html = re.sub(r'left:\s*-?\d+px;?', '', inner_html, flags=re.IGNORECASE)
        inner_html = re.sub(r'top:\s*-?\d+px;?', '', inner_html, flags=re.IGNORECASE)
        
        # Fix image and link paths
        inner_html = inner_html.replace('../ImportantResources/', 'ImportantResources/')
        
        # Replace links to other par files
        def repl_link(m):
            target = m.group(1)
            if target in files:
                return f'href="#{target[:-5]}"'
            return m.group(0) # unchanged if not a par file
        
        inner_html = re.sub(r'href="([^"]+\.html)"', repl_link, inner_html)
        
        # Append to combined body
        combined_body += f"<div id='{file_id}' style='{bg_style} padding: 20px; margin-bottom: 20px; min-height: 200px;'>\n"
        combined_body += f"<h2><a name='{file_id}'>{file_id}</a></h2>\n"
        combined_body += inner_html
        combined_body += "\n</div>\n<hr>\n"

final_html = head + combined_body + tail

with open(out_file, 'w', encoding='ISO-8859-1') as f:
    f.write(final_html)