41 lines
1.3 KiB
Python
41 lines
1.3 KiB
Python
|
import os
|
||
|
import xml.etree.ElementTree as ET
|
||
|
import base64
|
||
|
|
||
|
# Path to the XML dump file
|
||
|
dump_file = './page-and-filedump.xml'
|
||
|
|
||
|
# Directory to save the individual files
|
||
|
output_dir = 'output/'
|
||
|
|
||
|
# Parse the XML dump
|
||
|
tree = ET.parse(source=dump_file)
|
||
|
root = tree.getroot()
|
||
|
|
||
|
# Iterate through the pages and save them
|
||
|
for page in root.findall('./{http://www.mediawiki.org/xml/export-0.11/}page'):
|
||
|
title = page.find('./{http://www.mediawiki.org/xml/export-0.11/}title').text
|
||
|
text = page.find('./{http://www.mediawiki.org/xml/export-0.11/}revision/{http://www.mediawiki.org/xml/export-0.11/}text').text
|
||
|
|
||
|
print(title)
|
||
|
|
||
|
if ":" in title:
|
||
|
splitName = title.split(":")
|
||
|
|
||
|
title = splitName[1]
|
||
|
|
||
|
if splitName[0] == "File":
|
||
|
content = page.find("./{http://www.mediawiki.org/xml/export-0.11/}upload/{http://www.mediawiki.org/xml/export-0.11/}contents").text
|
||
|
img = base64.b64decode(content)
|
||
|
f = open(output_dir+title, "wb")
|
||
|
f.write(img)
|
||
|
f.close()
|
||
|
continue
|
||
|
|
||
|
|
||
|
# Create the output file path
|
||
|
output_file = os.path.join(output_dir, f'{title}.html')
|
||
|
|
||
|
# Save the page content as an HTML file
|
||
|
with open(output_file, 'w', encoding='utf-8') as f:
|
||
|
f.write(f'<h1>{title}</h1>\n{text}')
|