Python3之爬虫中回调函数的简单应用

import re
from multiprocessing import Pool

import requests


'''
<a href="/films/344264" title="战狼2" data-act="boarditem-click" data-val="{movieId:344264}">战狼2</a>'''
movie_pattern = re.compile(r'}">(.*?)</a></p>\n<p class="star">(.*?)</p>')


def get_page(url):
    res = requests.get(url).text
    return {'url': url, 'res': res}


def deal_data(res):
    print(res['url'], res['res'])
    movie_name = movie_pattern.findall(res['res'])
    with open('movie_info.txt', 'a', encoding='utf-8') as f:
        # print(movie_name)
        for item in movie_name:
            moviename, mainstar = item
            f.write('电影：%s，%s\n' % (moviename, mainstar))


if __name__ == '__main__':
    urls = [
        'http://maoyan.com/board/7',
        'http://maoyan.com/board/6',
        'http://maoyan.com/board/1',
        'http://maoyan.com/board/2',
        'http://maoyan.com/board/4',

    ]
    p = Pool(4)
    for url in urls:
        p.apply_async(get_page, args=(url,), callback=deal_data)

    p.close()
    p.join()