爬虫_古诗文网（正则表达式）

程序中请求到的和网页中内容不一样，但也是古诗，不是道是不是因为请求头的原因，使得网站推荐的古诗有差异

 1 import requests
 2 import re
 3 
 4 headers = 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/65.0.3325.181 Safari/537.36'
 5 
 6 def get_html(url):
 7     try:
 8         response = requests.get(url, headers)
 9         response.raise_for_status()
10         response.encoding = response.apparent_encoding
11         return response.text
12     except:
13         print('get_html(url) faild')
14 
15 
16 def parse_html(html):
17     titles = re.findall(r'<div class="cont">.*?<b>(.*?)</b>', html, re.DOTALL)
18     dynasties = re.findall(r'<p class="source"><a.*?>(.*?)</a>', html, re.DOTALL)
19     authors = re.findall(r'<p class="source"><a.*?><a.*?>(.*?)</a>', html, re.DOTALL)
20     content_tags = re.findall(r'<div class="contson".*?>(.*?)</div>', html, re.DOTALL)
21     contents = []
22     for content in content_tags:
23         content = re.sub(r'<.*?>', '', content)
24         contents.append(content.strip())
25     poems = []    
26     for value in zip(titles, dynasties, authors, contents):
27         title, dynasties, authors, content = value
28         poem = {
29             'title': title,
30             'dynasties': dynasties,
31             'authors': authors,
32             'content': content
33         }
34         print(poem)
35         poems.append(poem)
36     return poems
37 
38 
39 def main():
40     page_num = 10
41     for i in range(1, page_num+1):
42         url = 'https://www.gushiwen.org/default_{0}.aspx'.format(i)
43         html = get_html(url)
44         parse_html(html)
45 
46 
47 if __name__ == '__main__':
48     main()

运行结果