[已解决]我同样的代码为什么在pycharm上打印不出来

哈哈哈ha1

import requests
import bs4
res = requests.get('https://movie.douban.com/top250')
soup = bs4.BeautifulSoup(res.text,'html.parser')
targets = soup.find_all('div',class_ = 'hd')
for each in targets:
    print(each.span.text)


在pycharm上打印不出来，有无大佬给解决一下

最佳答案

月排行榜 / 总排行榜

suchocolate

2021-11-13 09:55:28

1. import requests
   
2. import bs4
   
3. 
   
4. headers = {'user-agent': 'Mozilla'}  # 替换默认的user-agent, 否则会触发418豆瓣请你喝茶。
   
5. res = requests.get('https://movie.douban.com/top250', headers=headers)
   
6. soup = bs4.BeautifulSoup(res.text, 'html.parser')
   
7. targets = soup.find_all('div', class_='hd')
   
8. for each in targets:
   
9.     print(each.span.text)
   

复制代码

跳转到最佳答案楼层

哈哈哈ha1

最后一行的print函数少打了一个a，应该是print(each.a.span.text)，但是就算这样我尝试在pycharm上打印也还是打印不出来啊

suchocolate

1. import requests
   
2. import bs4
   
3. 
   
4. headers = {'user-agent': 'Mozilla'}  # 替换默认的user-agent, 否则会触发418豆瓣请你喝茶。
   
5. res = requests.get('https://movie.douban.com/top250', headers=headers)
   
6. soup = bs4.BeautifulSoup(res.text, 'html.parser')
   
7. targets = soup.find_all('div', class_='hd')
   
8. for each in targets:
   
9.     print(each.span.text)
   

复制代码

哈哈哈ha1

suchocolate 发表于 2021-11-13 09:55

大佬哪个print(each.a.span.text)是什么意思，为什么会这样写

suchocolate

哈哈哈ha1 发表于 2021-11-15 14:32
大佬哪个print(each.a.span.text)是什么意思，为什么会这样写

each在循环里就是div，each.a.span.text就是打印 div下的a下的span下的文本内容，一点点就时一个层级。
按我的代码执行应该有东西输出吧？

哈哈哈ha1

suchocolate 发表于 2021-11-15 15:19
each在循环里就是div，each.a.span.text就是打印 div下的a下的span下的文本内容，一点点就时一个层级。
...

输出了大佬，可以帮我看一下这个代码么，我爬取豆瓣250电影排行榜，为什么资料和评分那一部分是空的，爬取不到资料和评分，有什么改进的方法么

#完整版代码
import requests
import bs4
import re


def open_url(url):
    #使用代理
    #proxies = (“http”:"127.0.0.1:1080","https":127.0.0.1:1080)
    headers = {'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/95.0.4638.69 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',class_='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.txt)
    #资料
    messages = []
    targets = soup.find_all('div',class_='bd')
    for i 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()

suchocolate

哈哈哈ha1 发表于 2021-11-15 16:34
输出了大佬，可以帮我看一下这个代码么，我爬取豆瓣250电影排行榜，为什么资料和评分那一部分是空的，爬 ...

1. import requests
   
2. import bs4
   
3. import re
   
4. 
   
5. 
   
6. def open_url(url):
   
7.     # 使用代理
   
8.     # proxies = (“http”:"127.0.0.1:1080","https":127.0.0.1:1080)
   
9.     headers = {
   
10.         'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/95.0.4638.69 Safari/537.36'}
    
11.     # res = requests.get(url,headers=headers,proxies=proxies)
    
12.     res = requests.get(url, headers=headers)
    
13.     return res
    
14. 
    
15. 
    
16. def find_movies(res):
    
17.     soup = bs4.BeautifulSoup(res.text, 'html.parser')
    
18.     # 电影名
    
19.     movies = []
    
20.     targets = soup.find_all('div', class_='hd')
    
21.     for each in targets:
    
22.         movies.append(each.a.span.text)
    
23.     # 评分
    
24.     ranks = []
    
25.     targets = soup.find_all('span', class_='rating_num')
    
26.     for each in targets:
    
27.         ranks.append('评分:%s' % each.text)  # 之前写成了each.txt
    
28.     # 资料
    
29.     messages = []
    
30.     targets = soup.find_all('div', class_='bd')
    
31.     for each in targets:
    
32.         try:
    
33.             messages.append(each.p.text.split('\n')[1].strip() + each.p.text.split('\n')[2].strip())
    
34.         except:
    
35.             continue
    
36.     result = []
    
37.     length = len(movies)
    
38.     for i in range(length):
    
39.         result.append(movies[i] + ranks[i] + messages[i] + '\n')  # index漏了
    
40.     return result
    
41. 
    
42. 
    
43. # 找出有多少个页面
    
44. def find_depth(res):
    
45.     soup = bs4.BeautifulSoup(res.text, 'html.parser')
    
46.     depth = soup.find('span', class_='next').previous_sibling.previous_sibling.text
    
47.     return int(depth)
    
48. 
    
49. 
    
50. def main():
    
51.     host = 'https://movie.douban.com/top250'
    
52.     res = open_url(host)
    
53.     depth = find_depth(res)
    
54.     result = []
    
55.     for i in range(depth):
    
56.         url = host + '/?start=' + str(25 * i)
    
57.         res = open_url(url)
    
58.         result.extend(find_movies(res))
    
59.     with open('豆瓣TOP250电影.txt', 'w', encoding='utf-8') as f:
    
60.         for each in result:
    
61.             f.write(each)
    
62. 
    
63. 
    
64. if __name__ == '__main__':
    
65.     main()
    

复制代码

suchocolate

1. import requests
   
2. from bs4 import BeautifulSoup
   
3. 
   
4. 
   
5. def main():
   
6.     headers = {'user-agent': 'Mozilla'}
   
7.     m_name = []
   
8.     m_score = []
   
9.     m_info = []
   
10.     for i in range(10):
    
11.         url = f'https://movie.douban.com/top250?start={i * 25}'
    
12.         r = requests.get(url, headers=headers)
    
13.         soup = BeautifulSoup(r.text, 'html.parser')
    
14.         m_name.extend([item.text.split('\xa0')[0].strip() for item in soup.find_all('div', class_='hd')])
    
15.         m_score.extend([item.text for item in soup.find_all('span', class_='rating_num')])
    
16.         info = [item.text.strip().replace('\n', '').replace('\xa0', '')
    
17.                 for item in soup.find_all('div', class_='bd')]
    
18.         if len(info) > 25:
    
19.             info = info[1:]
    
20.         m_info.extend(info)
    
21.     with open('result.txt', 'w', encoding='utf-8') as f:
    
22.         for i in range(len(m_name)):
    
23.             f.write(f'{m_name[i]}  {m_score[i]}  {m_info[i]}\n')
    
24. 
    
25. 
    
26. if __name__ == '__main__':
    
27.     main()
    

复制代码