UnicodeEncodeError:'ascii' codec can't encode...ordinal not in range(128)

cct

1. import urllib.request
   
2. import urllib.parse
   
3. import re
   
4. from bs4 import BeautifulSoup
   
5. 
   
6. def main():
   
7.     keward = input("请输入关键字:")
   
8.     keward = urllib.parse.urlencode({"word":keward})
   
9.     response = urllib.request.urlopen("http://baike.baidu.com/search/word?%s" %keward)
   
10. 
    
11.     html = response.read()
    
12.     soup = BeautifulSoup(html, "html.parser")
    
13. 
    
14.     for each in soup.find_all(href = re.compile("view")):
    
15.         content = ''.join([each.text])
    
16.         tmp = each["href"].split('=')
    
17.         if len(tmp) == 2:
    
18.             each["href"] = ''.join([tmp[0], urllib.parse.urlencode({'':tmp[1]})])
    
19.         url2 = ''.join(["http://baike.baidu.com", each["href"]])
    
20.         response2 = urllib.request.urlopen(url=url2)
    
21.         html2 = response2.read().decode("utf-8")
    
22.         soup2 = BeautifulSoup(html2, "html.parser")
    
23.         
    
24.         if soup2.h2:
    
25.             content = ''.join([content, soup2.h2.text])
    
26.         content = ''.join([content, "->", url2])
    
27.         print(content)
    
28. 
    
29. if __name__ == "__main__":
    
30.     main()

复制代码

each["href"]这个里面有可能有中文，你需要转码