爬虫爬出来没有内容

c451995951

import requests
import bs4
import re


def open_url(url):
    # 使用代理防止被反爬虫禁止
    # proxies = {"http":"127.0.0.1:1080", "https": "127.0.0.1:1080"}
    headers = {
        'user-agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36(KHTML,like Gecko) Chrome/57.0.2987.98 Safari/537.36'}

    # res = requests.get(url, headers=headers, proxies=proxies)
    res = requests.get(url, headers=headers)

    return res


def find_movies(res):
    soup = bs4.BeautifulSoup(res.text, 'html.parser')

    # 电影名
    movies = []
    targets = soup.find_all("div", calss_="hd")
    for each in targets:
        movies.append(each.a.span.text)

    # 评分
    ranks = []
    targets = soup.find_all("span", class_="rating_num")
    for each in targets:
        ranks.append('评分: %s ' % each.text)

    # 资料
    messages = []
    targets = soup.find_all("div", class_="bd")
    for each in targets:
        try:
            messages.append(each.p.text.split('\n')[1].strip() + each.p.text.split('\n')[2].strip())
        except:
            continue

    result = []
    length = len(movies)
    for i in range(length):
        result.append(movies[i] + ranks[i] + messages[i] + '\n')

    return result


# 找出一共有多少个页面
def find_depth(res):
    soup = bs4.BeautifulSoup(res.text, 'html.parser')
    depth = soup.find('span', class_='next').previous_sibling.previous_sibling.text

    return int(depth)


def main():
    host = "https://movie.douban.com/top250"
    res = open_url(host)
    depth = find_depth(res)

    result = []
    for i in range(depth):
        url = host + '/?start=' + str(25 * i)
        res = open_url(url)
        result.extend(find_movies(res))

    with open("豆瓣TOP250电影.txt", "w", encoding="utf-8") as f:
        for each in result:
            f.write(each)


if __name__ == "__main__":
    main()

c451995951

求大佬救救

wp231957

c451995951 发表于 2020-7-2 17:40
求大佬救救

使用本机做代理，哪个教的

qiuyouzhi

太粗心了

1. targets = soup.find_all("div", calss_="hd")

复制代码

class_ 写成了 calss_ ？
改成这样就行了

1. 
   
2. import requests
   
3. import bs4
   
4. import re
   
5. 
   
6. 
   
7. def open_url(url):
   
8.     # 使用代理防止被反爬虫禁止
   
9.     # proxies = {"http":"127.0.0.1:1080", "https": "127.0.0.1:1080"}
   
10.     headers = {
    
11.         'user-agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36(KHTML,like Gecko) Chrome/57.0.2987.98 Safari/537.36'}
    
12. 
    
13.     # res = requests.get(url, headers=headers, proxies=proxies)
    
14.     res = requests.get(url, headers=headers)
    
15. 
    
16.     return res
    
17. 
    
18. 
    
19. def find_movies(res):
    
20.     soup = bs4.BeautifulSoup(res.text, 'html.parser')
    
21. 
    
22.     # 电影名
    
23.     movies = []
    
24.     targets = soup.find_all("div", class_="hd")
    
25.     for each in targets:
    
26.         movies.append(each.a.span.text)
    
27. 
    
28.     # 评分
    
29.     ranks = []
    
30.     targets = soup.find_all("span", class_="rating_num")
    
31.     for each in targets:
    
32.         ranks.append('评分: %s ' % each.text)
    
33. 
    
34.     # 资料
    
35.     messages = []
    
36.     targets = soup.find_all("div", class_="bd")
    
37.     for each in targets:
    
38.         try:
    
39.             messages.append(each.p.text.split('\n')[1].strip() + each.p.text.split('\n')[2].strip())
    
40.         except:
    
41.             continue
    
42. 
    
43.     result = []
    
44.     length = len(movies)
    
45.     for i in range(length):
    
46.         result.append(movies[i] + ranks[i] + messages[i] + '\n')
    
47. 
    
48.     return result
    
49. 
    
50. 
    
51. # 找出一共有多少个页面
    
52. def find_depth(res):
    
53.     soup = bs4.BeautifulSoup(res.text, 'html.parser')
    
54.     depth = soup.find('span', class_='next').previous_sibling.previous_sibling.text
    
55. 
    
56.     return int(depth)
    
57. 
    
58. 
    
59. def main():
    
60.     host = "https://movie.douban.com/top250"
    
61.     res = open_url(host)
    
62.     depth = find_depth(res)
    
63. 
    
64.     result = []
    
65.     for i in range(depth):
    
66.         url = host + '/?start=' + str(25 * i)
    
67.         res = open_url(url)
    
68.         result.extend(find_movies(res))
    
69. 
    
70.     with open("豆瓣TOP250电影.txt", "w", encoding="utf-8") as f:
    
71.         for each in result:
    
72.             f.write(each)
    
73. 
    
74. 
    
75. if __name__ == "__main__":
    
76.     main()

复制代码