[已解决]python中ASCII码的问题

木子航木

书中14.4案例2：
import urllib.request
import urllib.parse
import re
from bs4 import BeautifulSoup

def main():
    keyword = input("请输入要查询的的关键词：")
    keyword = urllib.parse.urlencode({"word":keyword})
    response = urllib.request.urlopen("http://baike.baidu.com/item/word?%s"% keyword)
    html = response.read()
    soup = BeautifulSoup(html,"html.parser")
   
    #BS
    for each in soup.find_all(href = re.compile("item")):
        content = ''.join([each.text])
        url2 = ''.join(["http://baike.baidu.com",each["href"]])
        response2 =urllib.request.urlopen(url2)
        html2 =response2.read()
        soup2 =BeautifulSoup(html2,"html.parser")
        if soup2.h2:
            content = ''.join([content,soup2.h2.text])
        content = ''.join([content,"——>",url2])
        print(content)

if __name__ == "__main__":
        main()

报错UnicodeEncodeError: 'ascii' codec can't encode characters in position 10-12: ordinal not in range(128)
求解决

最佳答案

月排行榜 / 总排行榜

ba21

2017-8-21 18:56:04

事实证明输英文是没事的，输中文就不对了。所以URL带中文部份进行URL编码就可以了
代码：

1. import urllib.request
   
2. import urllib.parse
   
3. import re
   
4. from bs4 import BeautifulSoup
   
5. 
   
6. def main():
   
7.     keyword = input("请输入要查询的的关键词：")
   
8.     keyword = urllib.parse.urlencode({"word":keyword})
   
9.     response = urllib.request.urlopen("http://baike.baidu.com/item/word?%s"% keyword)
   
10.     html = response.read()
    
11.     soup = BeautifulSoup(html,"html.parser")
    
12.    
    
13.     #BS
    
14.     for each in soup.find_all(href = re.compile("item")):
    
15.         content = ''.join([each.text])
    
16.         url2 = ''.join(["http://baike.baidu.com",urllib.parse.quote(each["href"])]) #URL中文编码
    
17.         response2 =urllib.request.urlopen(url2)
    
18.         html2 =response2.read()
    
19.         soup2 =BeautifulSoup(html2,"html.parser")
    
20.         if soup2.h2:
    
21.             content = ''.join([content,soup2.h2.text])
    
22.         content = ''.join([content,"——>",url2])
    
23.         print(content)
    
24. 
    
25. if __name__ == "__main__":
    
26.         main()
    

复制代码

跳转到最佳答案楼层

ba21

事实证明输英文是没事的，输中文就不对了。所以URL带中文部份进行URL编码就可以了
代码：

1. import urllib.request
   
2. import urllib.parse
   
3. import re
   
4. from bs4 import BeautifulSoup
   
5. 
   
6. def main():
   
7.     keyword = input("请输入要查询的的关键词：")
   
8.     keyword = urllib.parse.urlencode({"word":keyword})
   
9.     response = urllib.request.urlopen("http://baike.baidu.com/item/word?%s"% keyword)
   
10.     html = response.read()
    
11.     soup = BeautifulSoup(html,"html.parser")
    
12.    
    
13.     #BS
    
14.     for each in soup.find_all(href = re.compile("item")):
    
15.         content = ''.join([each.text])
    
16.         url2 = ''.join(["http://baike.baidu.com",urllib.parse.quote(each["href"])]) #URL中文编码
    
17.         response2 =urllib.request.urlopen(url2)
    
18.         html2 =response2.read()
    
19.         soup2 =BeautifulSoup(html2,"html.parser")
    
20.         if soup2.h2:
    
21.             content = ''.join([content,soup2.h2.text])
    
22.         content = ''.join([content,"——>",url2])
    
23.         print(content)
    
24. 
    
25. if __name__ == "__main__":
    
26.         main()
    

复制代码

木子航木

ba21 发表于 2017-8-21 18:56
事实证明输英文是没事的，输中文就不对了。所以URL带中文部份进行URL编码就可以了
代码：

谢谢大佬