小甲鱼爬豆瓣TOP250有个代码看不懂

起风了番茄

1. import requests
   
2. import bs4
   
3. import re
   
4. 
   
5. def open_url(url):
   
6.     #使用代理
   
7.     # proxies = {'https':'223.243.174.152:9999','https':'223.214.205.179:9999'}
   
8.     headers = {'user-agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/99.0.4844.74 Safari/537.36 Edg/99.0.1150.46'}
   
9.     res = requests.get(url,headers=headers)
   
10.     return res
    
11. 
    
12. def find_movies(res):
    
13.     #炖汤
    
14.     soup = bs4.BeautifulSoup(res.text,'html.parser')
    
15.     #电影名
    
16.     movies = []
    
17.     targets = soup.find_all('div',class_ = 'hd')
    
18.     for each in targets:
    
19.         movies.append(each.a.span.text)
    
20. 
    
21.     #评分
    
22.     ranks = []
    
23.     targets = soup.find_all('span',class_='rating_num')
    
24.     for each in targets:
    
25.         ranks.append('评分%s'%each.text)
    
26.     #资料
    
27.     messages = []
    
28.     targets = soup.find_all('div',class_='bd')
    
29.     for each in targets:
    
30.         try:
    
31.             messages.append(each.p.text.split('\n')[0].strip() + each.p.text.split('\n')[1].strip())
    
32.         except:
    
33.             continue
    
34. 
    
35.     result = []
    
36.     length = len(movies)
    
37.     for i in range(length):
    
38.         result.append(movies[i] + ranks[i] + messages[i] +'\n')
    
39.     return result
    
40. 
    
41. #找出一共有多少个页面
    
42. def find_depth(res):
    
43.     soup = bs4.BeautifulSoup(res.text,'html.parser')
    
44.     depth = soup.find('span',class_= 'next').previous_sibling.previous_sibling.text #这一行什么意思呀?
    
45.     return int(depth)
    
46. 
    
47. def main():
    
48.     host = 'https://movie.douban.com/top250'
    
49.     res = open_url(host)
    
50.     depth = find_depth(res)
    
51. 
    
52.     result = []
    
53.     for i in range(depth):
    
54.         url = host + '/?start='+str(25*i)
    
55.         res =open_url(url)
    
56.         result.extend(find_movies(res))
    
57. 
    
58.     with open('豆瓣TOP250.txt','w',encoding='utf-8') as f:
    
59.         for each in result:
    
60.             f.write(each)
    
61. 
    
62. if __name__ == '__main__':
    
63.     main()

复制代码

起风了番茄

我知道previous_sibling是找之前的同级标签,可是我查看了html代码还是只有个大体的猜测,需要大佬们的指导下.

isdkz

https://blog.csdn.net/Winterto1990/article/details/47794941

起风了番茄

isdkz 发表于 2022-3-24 23:05
https://blog.csdn.net/Winterto1990/article/details/47794941

可是我看使用两次previous_sibling找到的不应该是9号标签吗?

cxslovefishc

就是span节点的上一个兄弟节点的上一个兄弟节点，这么说你看你有点乱，我举一个例子吧

1. In [12]: text = "<div><a>text0</a><b>text1</b><c>text2</c></div>"
   
2. In [13]: soup = bs4.BeautifulSoup(text, "html.parser")
   
3. In [14]: soup.find("c").previous_sibling.previous_sibling.text
   
4. Out[14]: 'text0'

复制代码

c的上上个兄弟节点就是a，所以拿到的文本是text0

C丁洞杀O

啥子东东啊？？