使用request库和正则表达式爬取猫眼电影信息。

1.爬取目标

  猫眼电影TOP100的电影名称,时间,评分,等信息,将结果以文件存储。

2.准备工作

  安装request库。

3.代码实现

 1 import json
 2 import requests
 3 from requests.exceptions import RequestException
 4 import re
 5 import time
 6 
 7 
 8 def get_one_page(url):
 9     try:
10         headers = {
11             'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_13_3) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.110 Safari/537.36'
12         }
13         response = requests.get(url, headers=headers)
14         if response.status_code == 200:
15             return response.text
16         return None
17     except RequestException:
18         return None
19 
20 
21 def parse_one_page(html):
22     pattern = re.compile('<dd>.*?board-index.*?>(\d+)</i>.*?data-src="(.*?)".*?name"><a'
23                          + '.*?>(.*?)</a>.*?star">(.*?)</p>.*?releasetime">(.*?)</p>'
24                          + '.*?integer">(.*?)</i>.*?fraction">(.*?)</i>.*?</dd>', re.S)
25     items = re.findall(pattern, html)
26     for item in items:
27         yield {
28             'index': item[0],
29             'image': item[1],
30             'title': item[2],
31             'actor': item[3].strip()[3:],
32             'time': item[4].strip()[5:],
33             'score': item[5] + item[6]
34         }
35 
36 
37 def write_to_file(content):
38     with open('result.txt', 'a', encoding='utf-8') as f:
39         f.write(json.dumps(content, ensure_ascii=False) + '\n')
40 
41 
42 def main(offset):
43     url = 'http://maoyan.com/board/4?offset=' + str(offset)
44     html = get_one_page(url)
45     for item in parse_one_page(html):
46         print(item)
47         write_to_file(item)
48 
49 
50 if __name__ == '__main__':
51     for i in range(10):
52         main(offset=i * 10)
53         time.sleep(2)