requests和正则表达式爬取猫眼电影Top100练习

 1 import requests
 2 import re
 3 from multiprocessing import Pool
 4 from requests.exceptions import RequestException
 5 import json
 6 import time
 7
 8
 9 # 抓取单页内容
10 def get_one_page(url):
11     headers = {"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) "
12                              "Chrome/85.0.4183.121 Safari/537.36"}
13     try:
14         response = requests.get(url, headers=headers)
15         if response.status_code == 200:
16             return response.text
17         else:
18             return None
19     except RequestException:
20         return None
21
22
23 # 解析单页内容
24 def parser_one_page(html):
25     pattern = re.compile('<dd>.*?board-index.*?>(\d+)</i>.*?data-src="(.*?)".*?name"><a.*?>(.*?)</a>'
26                          + '.*?star">(.*?)</p>.*?releasetime">(.*?)</p>.*?integer">(.*?)</i>.*?fraction">(.*?)</i>'
27                          + '.*?</dd>', re.S)
28     contents = re.findall(pattern, html)
29     for content in contents:
30         yield {                                   # 生成一个generator，对区域内的内容进行迭代处理
31             'index': content[0],
32             'image': content[1],
33             'name': content[2].strip(),
34             'actor': content[3].strip()[3:],
35             'time': content[4][5:],
36             'score': content[5]+content[6]
37         }
38
39
40 # 将单页内容写入文件
41 def write_to_file(content):
42     with open('猫眼电影.txt', 'a', encoding='utf-8') as f:
43         f.write(json.dumps(content, ensure_ascii=False) + '\n')
44         f.close()
45
46
47 def main(offset):
48     url = 'http://maoyan.com/board/4?offset=' + str(offset)
49     html = get_one_page(url)
50     for item in parser_one_page(html):
51         write_to_file(item)
52
53 if __name__ == "__main__":
54     time1 = time.time()
55     for i in range(0, 100, 10):
56         main(i)
57     time2 = time.time()
58     pool = Pool()    # 使用多进程提高爬取效率
59     pool.map(main, [i*10 for i in range(0, 10)])
60     time3 = time.time()
61     print(time2-time1)    # for...in花费时间
62     print(time3-time2)    # 多线程花费时间

运行时间如下：

补充对yield用法的理解：

相关博客文章：https://blog.csdn.net/qq_33472765/article/details/80839417