利用Xpath爬取dytt8 全部电影名字. 看思路就好

johnnyb

特别鸣谢.5群 叙白 大佬给的提示..

1. import requests
   
2. from lxml import etree
   
3. 
   
4. headers = {
   
5.     'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/83.0.4103.116 Safari/537.36'
   
6. }
   
7. url = 'https://www.ygdy8.net/html/gndy/dyzz/list_23_1.html'
   
8. for i in range(1, 219):
   
9.     new_url = 'https://www.ygdy8.net/html/gndy/dyzz/list_23_'+str(i)+'.html'
   
10.     response = requests.get(url=url, headers=headers)
    
11.     response.raise_for_status()
    
12.     response.encoding = 'gbk'
    
13.     r_text = response.text
    
14.     tree = etree.HTML(r_text)
    
15.     r = tree.xpath('//div[@class="co_content8"]/ul//a[@class="ulink"]')
    
16.     for a in r:
    
17.         print(a.text)

复制代码