多线程爬取猫眼电影TOP100并保存到mongo数据库中

 import requests

 import re

 import json

 from requests.exceptions import RequestException

 from multiprocessing import Pool

 #　获取网页

 def get_one_page(url):

     headers = {

         'User-Agent':'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko)'+

                      'Chrome/63.0.3239.132 Safari/537.36'}

     try:

         resp = requests.get(url,headers=headers)

         if resp.status_code == 200:

             return resp.text

         return None

     except RequestException:

         return None

 # 解析网页

 def parse_one_page(html):

     pattern = re.compile('<dd>.*?board-index.*?>(\d+)</i>.*?name"><a'

                          +'.*?>(.*?)</a>.*?star">(.*?)</p>.*?releasetime">(.*?)</p>'

                          +'.*?integer">(.*?)</i>.*?fraction">(.*?)</i>.*?</dd>',re.S)

     items = re.findall(pattern,html)

     for item in items:

         yield{

             'index':item[0],

             'title':item[1],

             'actor':item[2].strip(),

             'time':item[3],

             'score':item[4]+item[5],

             # 'image': item[6],

         }

 #　保存数据

 def write_to_file(content):

     with open('TOP1OO.txt','a',encoding='utf-8') as f:

         f.write(json.dumps(content,ensure_ascii=False)+'\n')

 def main(offset):

     url = 'http://maoyan.com/board/4?offset='+str(offset)

     html = get_one_page(url)

     for item in parse_one_page(html):

         write_to_file(item)

 if __name__ == '__main__':

     # for i in range(10):

     #     main(i*10)

     pool = Pool()

     pool.map(main,[i*10 for i in range(10)])