[已解决]为啥不打印啊

Hant

import requests
import bs4

def open_url(url):
    headers={'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/65.0.3314.0 Safari/537.36 SE 2.X MetaSr 1.0'}
    res = requests.get(url,headers=headers)
    return res

def find_data(res):
    soup=bs4.BeautifulSoup(res.text,'html.parser')
    content = soup.find(id='Cnt-Main-Article-QQ')
    target=content.find_all("P",style="TEXT-INDENT: 2em")
    for each in target:
        print(each)



def main():
    url=('https://news.house.qq.com/a/20170702/003985.htm')
    res=open_url(url)
    find_data(res)
   
if __name__=='__main__':
    main()

最佳答案

月排行榜 / 总排行榜

Twilight6

2020-7-27 22:48:25

Hant 发表于 2020-7-27 22:30
求解答

你的 P 是大写的 ，但是网站节点是小写的 p

1. import requests
   
2. import bs4
   
3. 
   
4. 
   
5. def open_url(url):
   
6.     headers = {
   
7.         'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/65.0.3314.0 Safari/537.36 SE 2.X MetaSr 1.0'}
   
8.     res = requests.get(url, headers=headers)
   
9.     return res
   
10. 
    
11. 
    
12. def find_data(res):
    
13.     soup = bs4.BeautifulSoup(res.text, 'html.parser')
    
14.     content = soup.find(id='Cnt-Main-Article-QQ')
    
15.     target = content.find_all("p",style="TEXT-INDENT: 2em")
    
16.     for each in target:
    
17.         print(each)
    
18. 
    
19. 
    
20. def main():
    
21.     url = ('https://news.house.qq.com/a/20170702/003985.htm')
    
22.     res = open_url(url)
    
23.     find_data(res)
    
24. 
    
25. 
    
26. if __name__ == '__main__':
    
27.     main()

复制代码

跳转到最佳答案楼层

Hant

求解答

Twilight6

Hant 发表于 2020-7-27 22:30
求解答

你的 P 是大写的 ，但是网站节点是小写的 p

1. import requests
   
2. import bs4
   
3. 
   
4. 
   
5. def open_url(url):
   
6.     headers = {
   
7.         'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/65.0.3314.0 Safari/537.36 SE 2.X MetaSr 1.0'}
   
8.     res = requests.get(url, headers=headers)
   
9.     return res
   
10. 
    
11. 
    
12. def find_data(res):
    
13.     soup = bs4.BeautifulSoup(res.text, 'html.parser')
    
14.     content = soup.find(id='Cnt-Main-Article-QQ')
    
15.     target = content.find_all("p",style="TEXT-INDENT: 2em")
    
16.     for each in target:
    
17.         print(each)
    
18. 
    
19. 
    
20. def main():
    
21.     url = ('https://news.house.qq.com/a/20170702/003985.htm')
    
22.     res = open_url(url)
    
23.     find_data(res)
    
24. 
    
25. 
    
26. if __name__ == '__main__':
    
27.     main()

复制代码

luxiaolan6373

target = content.find_all("p", style="TEXT-INDENT: 2em")#你换上我这句就行了

luxiaolan6373

luxiaolan6373 发表于 2020-7-28 02:48
target = content.find_all("p", style="TEXT-INDENT: 2em")#你换上我这句就行了

应该养成习惯,每一步都print调试一下,,别中间都没成功,就给直接写到后面了

Hant

luxiaolan6373 发表于 2020-7-28 02:49
应该养成习惯,每一步都print调试一下,,别中间都没成功,就给直接写到后面了

好的，感谢