Requests+正则表达式爬取猫眼电影

 1 import json
 2 from multiprocessing import Pool
 3 import requests
 4 from requests.exceptions import RequestException
 5 import re
 6 
 7 def get_one_page(url):
 8     try:
 9         response = requests.get(url)
10         if response.status_code == 200:
11             return response.text
12         return None
13     except RequestException:
14         return None
15 
16 def parse_one_page(html):
17     pattern = re.compile(r‘<dd>.*?board-index.*?>(\d+)</i>.*?data-src="(.*?)".*?name"><a‘
18                          +‘.*?>(.*?)</a>.*?star">(.*?)</p>.*?releasetime">(.*?)</p>‘
19                          +‘.*?integer">(.*?)</i>.*?fraction">(.*?)</i>.*?</dd>‘,re.S)
20     items = re.findall(pattern,html)
21     for item in items:
22         yield{
23             ‘index‘:item[0],
24             ‘image‘:item[1],
25             ‘title‘:item[2],
26             ‘actor‘:item[3].strip()[3:],
27             ‘time‘:item[4].strip()[5:],
28             ‘score‘:item[5]+item[6]
29         }
30 
31 def write_to_file(content):
32     with open(‘result.txt‘,‘a‘,encoding=‘utf-8‘) as f:
33         f.write((json.dumps(content, ensure_ascii=False))+‘\n‘)
34         f.close()
35 
36 def main(offset):
37     url = ‘https://maoyan.com/board/4?offset=‘ + str(offset)
38     html = get_one_page(url)
39     # print(html)
40     for item in parse_one_page(html):
41         print(item)
42         write_to_file(item)
43 
44 if __name__ == ‘__main__‘:
45     # for i in range(10):
46     #     main(i*10)
47     pool = Pool()
48     pool.map(main,[i*10 for i in range(10)])