wikipedia_scrape_page.py

def wiki_page(page_name):
    wiki_api = wikipediaapi.Wikipedia(language='en',
            extract_format=wikipediaapi.ExtractFormat.WIKI)
    page_name = wiki_api.page(page_name)
    if not page_name.exists():
        print('Page {} does not exist.'.format(page_name))
        return

    page_data = pd.DataFrame({
        'page': page_name,
        'text': page_name.text,
        'link': page_name.fullurl,
        'categories': [[y[9:] for y in
                       list(page_name.categories.keys())]],
        })

    return page_data