Wikipedia article downloader (HTML/PDF)

wikipedia-dl.py

#!/usr/bin/python3
# example usage:
# ./wikipedia-dl.py https://en.wikipedia.org/wiki/Wikipedia
# you could also specify which format you want. for example:
# ./wikipedia-dl.py https://en.wikipedia.org/wiki/Wikipedia html
from sys import argv
from urllib.parse import urlparse
import requests
import lxml.html


def get_pagename_d(url):
    page = urlparse(url)
    _page_name = page.path.split('/')
    page_name = '/'.join(_page_name[2:]).replace(':_', ': ')
    return (page_name, page)

def download_pdf(url):
    page_name, page = get_pagename_d(url)
    new_uri = '{uri.scheme}://{uri.netloc}/wiki/Special:ElectronPdf'.format(uri=page)
    printable_pdf = requests.post(
        new_uri,
        allow_redirects=True,
        params={'action': 'redirect-to-electron',
                'page': page_name}).content
    open(page_name.replace('/', ' - ') + '.pdf', 'wb').write(printable_pdf)

def download_html(url):
    page_name, page = get_pagename_d(url)
    uri_scheme = '{uri.scheme}://{uri.netloc}/'.format(uri=page)
    printable_html = requests.get(
        uri_scheme + 'w/index.php',
        params={
            'title': page_name,
            'printable': 'yes'
        }
    ).content.decode()
    printable_html = lxml.html.make_links_absolute(printable_html, uri_scheme)
    open(page_name.replace('/', ' - ') + '.html', 'wb').write(printable_html.encode('utf-8'))

if __name__ == '__main__':
    if len(argv) >= 2:
        if argv[2] == 'pdf':
            download_pdf(argv[1])
        elif argv[2] == 'html':
            download_html(argv[1])
    else:
        download_pdf(argv[1])