Last active
May 8, 2019 13:21
-
-
Save meatyite/7258808d30185a1c8008fb1622ad6fcc to your computer and use it in GitHub Desktop.
wikia (fandom.com) Downloader
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/python3 | |
# requires beautifulsoup4, install it with pip if you don't have it already | |
# usage: ./wikia-dl.py [wikia article url] | |
import re | |
import requests | |
from sys import argv | |
from bs4 import BeautifulSoup as bs | |
def slugify(value): | |
""" | |
Normalizes string, converts to lowercase, removes non-alpha characters, | |
and converts spaces to hyphens so it could be saved properly in a windows filename. | |
""" | |
import unicodedata | |
value = unicodedata.normalize('NFKD', value).encode('ascii', 'ignore').decode('ascii') | |
value = str(re.sub('[^\w\s-]', '', value).strip().lower()) | |
value = str(re.sub('[-\s]+', '-', value)) | |
return value | |
def download(url): | |
total_html = """\ | |
<!DOCTYPE html> | |
<html> | |
<head> | |
""" | |
pageSource = requests.get(url).text | |
soup = bs(pageSource, 'html.parser') | |
title = soup.find('h1', {'class':'page-header__title'}).string | |
total_html += "\n<title>" + title + "</title>\n</head>\n<body>\n<h1>" + title + "</h1>" | |
htmlChildTags = soup.find('div', {'id':'mw-content-text'}).findChildren(recursive=True) | |
for htmlChildTag in htmlChildTags: | |
total_html += "\n" + str(htmlChildTag) | |
total_html += "\n</body>\n</html>" | |
open(slugify(title) + '.html', 'wb').write(total_html.encode('utf-8')) | |
download(argv[1]) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment