lyrics.py 文件源码

def get_lyrics_with_urls(urls):
    # TODO

    ret = []
    for url in urls:
        time.sleep(3)
        print(url)

        response = urlopen(url, timeout=5)
        content = response.read()
        for lyrics in bs(content, "html.parser", parse_only=SoupStrainer('p')):
            if(lyrics.has_attr('style')):
                lyrics = re.sub('</?br/?>', '\n', str(lyrics))
                lyrics = re.sub('<.*?>', '', str(lyrics))
                lyrics = re.sub('\n', ' \n', str(lyrics))
                ret.append(lyrics)
                print(lyrics)
                print(str(get_sentiment(lyrics)))
    return ret