extract_wikipedia.py

import wikipedia as wp

def extract_content_pages(files, page_list, languages=languages):
    # iterate over languages
    for lang in languages:
        print(lang)
        wp.set_lang(lang)
        try:
            files[lang]
        except KeyError:
            files[lang] = {}
        
        # iterate over page names
        for i, name in enumerate(tqdm(page_list)):
            try:
                page_content = wp.page(wp.search(name)[0]).content
                files[lang][name] = page_content
            except:
                continue
    
    return files