一个豆瓣网页简单网页内容的提取

柠檬冲冲冲

我写到能打印出下文中包含要提取内容的html，但后面就不知道怎么提取了，试了好久都没成功，就是提取上映的电影的名称，评分，参演人员的信息，大家能帮我试试看吗

1. import requests
   
2. import re
   
3. import xlwt
   
4. from lxml import html
   
5. from bs4 import BeautifulSoup
   
6. url = "https://movie.douban.com/cinema/nowplaying/haikou/"
   
7. head = {  # 模拟浏览器头部信息，向豆瓣服务器发送消息
   
8.         "User-Agent": "Mozilla/5.0 (Linux; Android 6.0; Nexus 5 Build/MRA58N) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/100.0.4896.75 Mobile Safari/537.36 Edg/100.0.1185.36"
   
9.     }
   
10. resp = requests.get(url,headers= head)
    
11. content = resp.text
    
12. 
    
13. page = BeautifulSoup(content,"lxml")
    
14. nfo = page.find_all("div",class_= "mod-bd")
    
15. for i in info:
    
16.     title = i.find('li')
    
17.     print(title)
    
18. 
    
19. 
    
20. print("结束")

复制代码

鱼cpython学习者

1. import requests
   
2. import re
   
3. from bs4 import BeautifulSoup
   
4. url = "https://movie.douban.com/cinema/nowplaying/haikou/"
   
5. head = {  # 模拟浏览器头部信息，向豆瓣服务器发送消息
   
6.     "User-Agent": "Mozilla/5.0 (Linux; Android 6.0; Nexus 5 Build/MRA58N) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/100.0.4896.75 Mobile Safari/537.36 Edg/100.0.1185.36"
   
7. }
   
8. resp = requests.get(url, headers=head)
   
9. content = resp.text
   
10. 
    
11. page = BeautifulSoup(content, "lxml")
    
12. info = page.find_all('div', id="nowplaying")[0].find_all("li", class_="list-item")
    
13. for i in info:
    
14.     actors = re.findall(r'data-actors="(.*?)"', str(i))[0]
    
15.     title = re.findall(r'data-title="(.*?)"', str(i))[0]
    
16.     score = re.findall(r'data-score="(.*?)"', str(i))
    
17.     score = score[0] if score != ["0"] else "暂无评分"
    
18.     print(actors, title, score)
    
19. 
    
20. 
    
21. print("结束")
    

复制代码