Requests+正则表达式爬取猫眼电影

 1 # encoding:utf-8
 2 from requests.exceptions import RequestException
 3 import requests
 4 import re
 5 import json
 6 from multiprocessing import Pool
 7 
 8 def get_one_page(url):
 9     try:
10         response = requests.get(url)
11         if response.status_code == 200:
12             return response.text
13         return None
14     except RequestException:
15         return None
16 
17 def parse_one_page(html):
18     pattern = re.compile(‘<dd>.*?board-index.*?>(\d+)</i>.*?data-src="(.*?)".*?name"><a‘
19                          +‘.*?>(.*?)</a>.*?star">(.*?)</p>.*?releasetime">(.*?)</p>‘
20                           +‘.*?integer">(.*?)</i>.*?fraction">(.*?)</i>.*?</dd>‘,re.S)
21     items = re.findall(pattern, html)
22     # print(items)
23     for item in items:
24         yield {
25             ‘index‘: item[0],
26             ‘image‘: item[1],
27             ‘title‘: item[2],
28             ‘actor‘: item[3].strip()[3:],
29             ‘time‘: item[4].strip()[5:],
30             ‘score‘: item[5]+item[6]
31         }
32 
33 def write_to_file(content):
34     with open(‘MaoyanTop100.txt‘, ‘a‘, encoding=‘utf-8‘) as f:
35         f.write(json.dumps(content, ensure_ascii=False)+‘\n‘)
36         f.close()
37 
38 def main(offset):
39     url = "http://maoyan.com/board/4?offset="+str(offset)
40     html = get_one_page(url)
41     # print(html)
42     # parse_one_page(html)
43     for item in parse_one_page(html):
44         print(item)
45         write_to_file(item)
46 
47 if __name__ == ‘__main__‘:
48     pool = Pool()
49     # for i in range(10):
50     #     main(i*10)
51     # 加快效率
52     pool.map(main, [i*10 for i in range(10)])