请帮我看一下抓取程序出错的原因？

zbhdpx

import requests
from bs4 import BeautifulSoup
def getNewsDetail(newsurl):
    result = {}
    res = requests.get(newsurl)
    res.encoding = 'utf-8'
    soup = BeautifulSoup(res.text,'html.parser')
    result['title'] = soup.select('h1')[0].text
    result['time'] = soup.select('.info-title span')[1].text
    result['article'] = [p.text.strip() for p in soup.select('.info-con span')]
    return result
def parseListLinks(url):
    newsdetails = {}
    res = requests.get(url)
    res.encoding = 'utf-8'
    soup = BeautifulSoup(res.text,'html.parser')
    for news in soup.select('.mb20'):
        newsdetails.append(getNewsDetail(news.select('a')[0]['href']))
    return newsdetails

url = 'http://www.iron-powder.cn/knowledge'
parseListLinks(url)

AttributeError                            Traceback (most recent call last)
<ipython-input-78-b47a839534d7> in <module>()
      1 url = 'http://www.iron-powder.cn/knowledge'
----> 2 parseListLinks(url)
<ipython-input-77-69f7954642e8> in parseListLinks(url)
      8          #   h3 = news.select('h3')[0].text
      9           #  a = news.select('a')[0]['href']
---> 10         newsdetails.append(getNewsDetail(news.select('a')[0]['href']))
     11     return newdetails
AttributeError: 'dict' object has no attribute 'append'

    这是根据教程写的抓取程序，单页内容已经抓取成功，但是抓取列就出错了？刚学python，请帮我改一下错误，谢谢！

q1208c

回复 1# zbhdpx

import requests
from bs4 import BeautifulSoup
def getNewsDetail(newsurl):
    result = {}
    res = requests.get(newsurl)
    res.encoding = 'utf-8'
    soup = BeautifulSoup(res.text,'html.parser')
    result['title'] = soup.select('h1')[0].text
    result['time'] = soup.select('.info-title span')[1].text
    result['article'] = [p.text.strip() for p in soup.select('.info-con span')]
    return result
def parseListLinks(url):
    newsdetails = {}
    res = requests.get(url)
    res.encoding = 'utf-8'
    soup = BeautifulSoup(res.text,'html.parser')
    for news in soup.select('.mb20'):
        newsdetails.append(getNewsDetail(news.select('a')[0]['href']))
    return newsdetails

url = 'http://www.iron-powder.cn/knowledge'
parseListLinks(url)

AttributeError                            Traceback (most recent call last)
<ipython-input-78-b47a839534d7> in <module>()
      1 url = 'http://www.iron-powder.cn/knowledge'
----> 2 parseListLinks(url)
<ipython-input-77-69f7954642e8> in parseListLinks(url)
      8          #   h3 = news.select('h3')[0].text
      9           #  a = news.select('a')[0]['href']
---> 10         newsdetails.append(getNewsDetail(news.select('a')[0]['href']))
     11     return newdetails
AttributeError: 'dict' object has no attribute 'append'

sunslj

1. import requests
   
2. from bs4 import BeautifulSoup
   
3. def getNewsDetail(newsurl):
   
4.     result = {}
   
5.     res = requests.get(newsurl)
   
6.     res.encoding = 'utf-8'
   
7.     soup = BeautifulSoup(res.text,'html.parser')
   
8.     result['title'] = soup.select('h1')[0].text
   
9.     result['time'] = soup.select('.info-title span')[1].text
   
10.     result['article'] = [p.text.strip() for p in soup.select('.info-con span')]
    
11.     return result
    
12. def parseListLinks(url):
    
13.     newsdetails = []
    
14.     res = requests.get(url)
    
15.     res.encoding = 'utf-8'
    
16.     soup = BeautifulSoup(res.text,'html.parser')
    
17.     for news in soup.select('li.mb20'):
    
18.         content = getNewsDetail(news.select('a')[0]['href'])
    
19.         newsdetails.append(content)
    
20.     return newsdetails
    
21. 
    
22. url = 'http://www.iron-powder.cn/knowledge'
    
23. parseListLinks(url)

复制代码

这是单个页面的，你这个不能循环爬所有页面

sunslj

1. import requests
   
2. from bs4 import BeautifulSoup
   
3. def getNewsDetail(newsurl):
   
4.     result = {}
   
5.     res = requests.get(newsurl)
   
6.     res.encoding = 'utf-8'
   
7.     soup = BeautifulSoup(res.text,'html.parser')
   
8.     result['title'] = soup.select('h1')[0].text
   
9.     result['time'] = soup.select('.info-title span')[1].text
   
10.     result['article'] = [p.text.strip() for p in soup.select('.info-con span')]
    
11.     return result
    
12. def parseListLinks(url):
    
13.     newsdetails = []
    
14.     res = requests.get(url)
    
15.     res.encoding = 'utf-8'
    
16.     soup = BeautifulSoup(res.text,'html.parser')
    
17.     for news in soup.select('li.mb20'):
    
18.         content = getNewsDetail(news.select('a')[0]['href'])
    
19.         newsdetails.append(content)
    
20.     return newsdetails
    
21. 
    
22. url = 'http://www.iron-powder.cn/knowledge'
    
23. parseListLinks(url)

复制代码

这是单个页面的，你这个不能循环爬所有页面

sunslj

1. import requests
   
2. from bs4 import BeautifulSoup
   
3. def getNewsDetail(newsurl):
   
4.     result = {}
   
5.     res = requests.get(newsurl)
   
6.     res.encoding = 'utf-8'
   
7.     soup = BeautifulSoup(res.text,'html.parser')
   
8.     result['title'] = soup.select('h1')[0].text
   
9.     result['time'] = soup.select('.info-title span')[1].text
   
10.     result['article'] = [p.text.strip() for p in soup.select('.info-con span')]
    
11.     return result
    
12. def parseListLinks(url):
    
13.     newsdetails = []
    
14.     res = requests.get(url)
    
15.     res.encoding = 'utf-8'
    
16.     soup = BeautifulSoup(res.text,'html.parser')
    
17.     for news in soup.select('li.mb20'):
    
18.         content = getNewsDetail(news.select('a')[0]['href'])
    
19.         newsdetails.append(content)
    
20.     return newsdetails
    
21. 
    
22. url = 'http://www.iron-powder.cn/knowledge'
    
23. parseListLinks(url)

复制代码

这是单个页面的，你这个不能循环爬所有页面

sunslj

1. import requests
   
2. from bs4 import BeautifulSoup
   
3. def getNewsDetail(newsurl):
   
4.     result = {}
   
5.     res = requests.get(newsurl)
   
6.     res.encoding = 'utf-8'
   
7.     soup = BeautifulSoup(res.text,'html.parser')
   
8.     result['title'] = soup.select('h1')[0].text
   
9.     result['time'] = soup.select('.info-title span')[1].text
   
10.     result['article'] = [p.text.strip() for p in soup.select('.info-con span')]
    
11.     return result
    
12. def parseListLinks(url):
    
13.     newsdetails = []
    
14.     res = requests.get(url)
    
15.     res.encoding = 'utf-8'
    
16.     soup = BeautifulSoup(res.text,'html.parser')
    
17.     for news in soup.select('li.mb20'):
    
18.         content = getNewsDetail(news.select('a')[0]['href'])
    
19.         newsdetails.append(content)
    
20.     return newsdetails
    
21. 
    
22. url = 'http://www.iron-powder.cn/knowledge'
    
23. parseListLinks(url)
    

复制代码

你这只能爬第一页

sunslj

1. import requests
   
2. from bs4 import BeautifulSoup
   
3. def getNewsDetail(newsurl):
   
4.     result = {}
   
5.     res = requests.get(newsurl)
   
6.     res.encoding = 'utf-8'
   
7.     soup = BeautifulSoup(res.text,'html.parser')
   
8.     result['title'] = soup.select('h1')[0].text
   
9.     result['time'] = soup.select('.info-title span')[1].text
   
10.     result['article'] = [p.text.strip() for p in soup.select('.info-con span')]
    
11.     return result
    
12. def parseListLinks(url):
    
13.     newsdetails = []
    
14.     res = requests.get(url)
    
15.     res.encoding = 'utf-8'
    
16.     soup = BeautifulSoup(res.text,'html.parser')
    
17.     for news in soup.select('li.mb20'):
    
18.         content = getNewsDetail(news.select('a')[0]['href'])
    
19.         newsdetails.append(content)
    
20.     return newsdetails
    
21. 
    
22. url = 'http://www.iron-powder.cn/knowledge'
    
23. parseListLinks(url)
    

复制代码

你这只能爬第一页，

sunslj

1. import requests
   
2. from bs4 import BeautifulSoup
   
3. def getNewsDetail(newsurl):
   
4.     result = {}
   
5.     res = requests.get(newsurl)
   
6.     res.encoding = 'utf-8'
   
7.     soup = BeautifulSoup(res.text,'html.parser')
   
8.     result['title'] = soup.select('h1')[0].text
   
9.     result['time'] = soup.select('.info-title span')[1].text
   
10.     result['article'] = [p.text.strip() for p in soup.select('.info-con span')]
    
11.     return result
    
12. def parseListLinks(url):
    
13.     newsdetails = []
    
14.     res = requests.get(url)
    
15.     res.encoding = 'utf-8'
    
16.     soup = BeautifulSoup(res.text,'html.parser')
    
17.     for news in soup.select('li.mb20'):
    
18.         content = getNewsDetail(news.select('a')[0]['href'])
    
19.         newsdetails.append(content)
    
20.     return newsdetails
    
21. 
    
22. url = 'http://www.iron-powder.cn/knowledge'
    
23. parseListLinks(url)
    

复制代码

这个只能抓第一页

sunslj

1. import requests
   
2. from bs4 import BeautifulSoup
   
3. def getNewsDetail(newsurl):
   
4.     result = {}
   
5.     res = requests.get(newsurl)
   
6.     res.encoding = 'utf-8'
   
7.     soup = BeautifulSoup(res.text,'html.parser')
   
8.     result['title'] = soup.select('h1')[0].text
   
9.     result['time'] = soup.select('.info-title span')[1].text
   
10.     result['article'] = [p.text.strip() for p in soup.select('.info-con span')]
    
11.     return result
    
12. def parseListLinks(url):
    
13.     newsdetails = []
    
14.     res = requests.get(url)
    
15.     res.encoding = 'utf-8'
    
16.     soup = BeautifulSoup(res.text,'html.parser')
    
17.     for news in soup.select('li.mb20'):
    
18.         content = getNewsDetail(news.select('a')[0]['href'])
    
19.         newsdetails.append(content)
    
20.     return newsdetails
    
21. 
    
22. url = 'http://www.iron-powder.cn/knowledge'
    
23. parseListLinks(url)
    

复制代码

你这只能爬第一页，

sunslj

1. import requests
   
2. from bs4 import BeautifulSoup
   
3. def getNewsDetail(newsurl):
   
4.     result = {}
   
5.     res = requests.get(newsurl)
   
6.     res.encoding = 'utf-8'
   
7.     soup = BeautifulSoup(res.text,'html.parser')
   
8.     result['title'] = soup.select('h1')[0].text
   
9.     result['time'] = soup.select('.info-title span')[1].text
   
10.     result['article'] = [p.text.strip() for p in soup.select('.info-con span')]
    
11.     return result
    
12. def parseListLinks(url):
    
13.     newsdetails = []
    
14.     res = requests.get(url)
    
15.     res.encoding = 'utf-8'
    
16.     soup = BeautifulSoup(res.text,'html.parser')
    
17.     for news in soup.select('li.mb20'):
    
18.         content = getNewsDetail(news.select('a')[0]['href'])
    
19.         newsdetails.append(content)
    
20.     return newsdetails
    
21. 
    
22. url = 'http://www.iron-powder.cn/knowledge'
    
23. parseListLinks(url)
    

复制代码

你这只能爬第一页，