《零基础学习Python》p14-92 爬虫程序求助

Martine

1. import urllib.request
   
2. import urllib.parse
   
3. import re
   
4. from bs4 import BeautifulSoup
   
5. 
   
6. def main():
   
7.         keyword =  input("key words :")
   
8.         keyword = urllib.parse.urlencode({"word":keyword})
   
9.         response = \
   
10. urllib.request.urlopen("http://baike.baidu.com/search/word? % s" % \
    
11. keyword)
    
12.         html = response.read()
    
13.         soup = BeautifulSoup(html, "html.parser")
    
14. 
    
15.         for each in soup.find_all(href=re.compile("view")):
    
16.                 content =''.join([each.text])
    
17.                 url2 = ''.join(["http://baike.baidu.com", each["href"]])
    
18.                 response2 = urllib.request.urlopen(url2)
    
19.                 html2 = response2.read()
    
20.                 soup2 = BeautifulSoup(html2, "html.parser")
    
21.                 if soup2.h2:
    
22.                         content = ''.join([content, soup2, h2.txt])
    
23.                 content  = ''.join([content, "->", url2])
    
24.                 print(content)
    
25. if __name__=="__main__":
    
26.         main()
    

复制代码

IDE报错

1. key words :qq
   
2. Traceback (most recent call last):
   
3.   File "C:\Users\Martin\Desktop\Python_Course\p14_92.py", line 26, in <module>
   
4.     main()
   
5.   File "C:\Users\Martin\Desktop\Python_Course\p14_92.py", line 11, in main
   
6.     keyword)
   
7.   File "D:\Program\Python\lib\urllib\request.py", line 223, in urlopen
   
8.     return opener.open(url, data, timeout)
   
9.   File "D:\Program\Python\lib\urllib\request.py", line 532, in open
   
10.     response = meth(req, response)
    
11.   File "D:\Program\Python\lib\urllib\request.py", line 642, in http_response
    
12.     'http', request, response, code, msg, hdrs)
    
13.   File "D:\Program\Python\lib\urllib\request.py", line 570, in error
    
14.     return self._call_chain(*args)
    
15.   File "D:\Program\Python\lib\urllib\request.py", line 504, in _call_chain
    
16.     result = func(*args)
    
17.   File "D:\Program\Python\lib\urllib\request.py", line 650, in http_error_default
    
18.     raise HTTPError(req.full_url, code, msg, hdrs, fp)
    
19. urllib.error.HTTPError: HTTP Error 400: Bad Request
    
20. >>>

复制代码

ooxx7788

response = \
urllib.request.urlopen("http://baike.baidu.com/search/word? % s" % \
keyword)

这个地方有错，别换行，就写一行里面