wikiparse.py

from xmltodict import parse
from collections import namedtuple

with open("vimwikiacom-20190108-current.xml", "rb") as file:
    wiki = parse(file, xml_attribs=True)
    pages = wiki['mediawiki']['page']

    def extract_pages(section):
        return  [page for page in pages if page['title'].startswith(section)]

    # TODO: write code to read the namespaces from the wiki dump
    page_types = ('VimTip', 'Talk:', 'User:', 'User talk:', 'Vim Tips Wiki:', 'Vim Tips Wiki talk:', 'Template talk:', 'File:', 'MediaWiki:', 'MediaWiki talk:', 'Template:', 'Help:', 'Help talk:', 'Category:', 'Category talk:', 'Forum:', 'Script:', 'Script talk:')

    pages =  [page for page in pages if not page['title'].startswith(page_types)]

    def parse_page(page):
        Page = namedtuple('Page', 'title content comments last_updated id')
        return Page(title=page['title'],
             content=page['revision']['text']['#text'],
             comments=page['revision']['comment'],
             last_updated=page['revision']['timestamp'],
             id=page['id'])

    n = parse_page(pages[500])

    print(n.content)