糗事百科文字小爬虫(l正则练习)

 1 # _author:   Jolly
 2 # date:  2019/8/30
 3 
 4 import requests
 5 import re
 6 
 7 headers = {
 8     ‘User-Agent‘: ‘Mozilla/5.0 (Windows NT 6.3; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/73.0.3683.103 Safari/537.36‘
 9 }
10 
11 
12 def parse_url(page_url):
13     response = requests.get(page_url)
14     text = response.text
15     authors = re.findall(‘<div\sclass="author clearfix".*?<a.*?<h2>(.*?)</h2>.*?</a>‘, text, re.S)
16     dispose_authors = list(map(lambda data: data.strip(), authors))
17     # print(dispose_author)
18     contents = re.findall(‘<div\sclass="content">.*?<span>(.*?)</span>‘, text, re.DOTALL)
19 
20     dispose_contents = []
21     for content in contents:
22         content = re.sub(‘<.*?>‘, "", content)
23         dispose_contents.append(content)
24     finally_contents = list(map(lambda data: data.strip(), dispose_contents))
25     # print(finally_contents)
26 
27     all_contents = []
28     for data in zip(dispose_authors, finally_contents):
29         author, content = data
30         full_content = {
31             ‘author‘: author,
32             ‘content‘: content
33         }
34         all_contents.append(full_content)
35     print(all_contents)
36 
37 
38 def main(n):
39     url = ‘https://www.qiushibaike.com/text/page/{}/‘
40     for i in range(1, n+1):
41         page_url = url.format(i)
42         parse_url(page_url)
43         print("============"*20, end=‘\n\n‘)
44 
45 if __name__ == ‘__main__‘:
46     main(2)