爬虫遇到的好像是数据库的问题--UnicodeEncodeError

qq13459621230

1. import urllib.request
   
2. import os
   
3. import re
   
4. 
   
5. def url_open(url):
   
6.     req=urllib.request.Request(url)
   
7.     req.add_header('User-Agent','Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/50.0.2661.102 UBrowser/6.1.2716.5 Safari/537.36')
   
8.     response=urllib.request.urlopen(url)
   
9.     html=response.read()
   
10.     return html
    
11.    
    
12.    
    
13. def get_totalpages(url):
    
14.     html=url_open(url).decode('utf-8')
    
15.     reg=r'共(.*?)页'
    
16.     totalpages=re.findall(reg,html)[0]
    
17.     return int(totalpages)
    
18. 
    
19. def get_sercoverurl(pageurl):
    
20.     html=url_open(pageurl).decode('utf-8')
    
21.     reg=r'<a href="(.*?)" target="_blank">'
    
22.     sercoverurl=re.findall(reg,html)
    
23.     return sercoverurl
    
24. 
    
25. def get_picurl(sercoverurl):
    
26.     html=url_open(sercoverurl).decode('utf-8')
    
27.     reg='<img src="(.*?)"'
    
28.     picurl=re.findall(reg,html)[0]
    
29.     return picurl
    
30. 
    
31. def main():
    
32.     os.chdir('E://OOXX')
    
33.    
    
34. 
    
35.     url='http://www.mmjpg.com/'
    
36. 
    
37.     totalpages=get_totalpages(url)
    
38.     print(totalpages)
    
39.     count=0
    
40.     for eachpage in range(1,totalpages+1):
    
41.         pageurl=url+'home/'+str(eachpage)
    
42.         print(pageurl)
    
43.         
    
44.         sercoverurl=get_sercoverurl(pageurl)
    
45.         print(sercoverurl)
    
46.         
    
47.         for eachpic in sercoverurl:   
    
48.             picurl=get_picurl(eachpic)           
    
49.             print(picurl)
    
50.             filename=str(count)+picurl.split('/')[-2]+'and'+picurl.split('/')[-1]
    
51.             urllib.request.urlretrieve(picurl,filename)
    
52.         count+=1
    
53. 
    
54. if __name__=='__main__':
    
55.     main()

复制代码

照着大佬们的代码，自己加以修改的爬取美女的图片，但是出现了这些代码，代码好像不能实现翻页的功能，水平有限，实在找不出问题所在，求大佬解答！！！百度了一下，说是数据库什么的问题，但是找不到解决的方法。

1. Traceback (most recent call last):
   
2.   File "C:/Users/Administrator/Desktop/4.py", line 55, in <module>
   
3.     main()
   
4.   File "C:/Users/Administrator/Desktop/4.py", line 48, in main
   
5.     picurl=get_picurl(eachpic)
   
6.   File "C:/Users/Administrator/Desktop/4.py", line 26, in get_picurl
   
7.     html=url_open(sercoverurl).decode('utf-8')
   
8.   File "C:/Users/Administrator/Desktop/4.py", line 8, in url_open
   
9.     response=urllib.request.urlopen(url)
   
10.   File "C:\Users\Administrator\AppData\Local\Programs\Python\Python36-32\lib\urllib\request.py", line 223, in urlopen
    
11.     return opener.open(url, data, timeout)
    
12.   File "C:\Users\Administrator\AppData\Local\Programs\Python\Python36-32\lib\urllib\request.py", line 526, in open
    
13.     response = self._open(req, data)
    
14.   File "C:\Users\Administrator\AppData\Local\Programs\Python\Python36-32\lib\urllib\request.py", line 544, in _open
    
15.     '_open', req)
    
16.   File "C:\Users\Administrator\AppData\Local\Programs\Python\Python36-32\lib\urllib\request.py", line 504, in _call_chain
    
17.     result = func(*args)
    
18.   File "C:\Users\Administrator\AppData\Local\Programs\Python\Python36-32\lib\urllib\request.py", line 1346, in http_open
    
19.     return self.do_open(http.client.HTTPConnection, req)
    
20.   File "C:\Users\Administrator\AppData\Local\Programs\Python\Python36-32\lib\urllib\request.py", line 1318, in do_open
    
21.     encode_chunked=req.has_header('Transfer-encoding'))
    
22.   File "C:\Users\Administrator\AppData\Local\Programs\Python\Python36-32\lib\http\client.py", line 1239, in request
    
23.     self._send_request(method, url, body, headers, encode_chunked)
    
24.   File "C:\Users\Administrator\AppData\Local\Programs\Python\Python36-32\lib\http\client.py", line 1280, in _send_request
    
25.     self.putheader(hdr, value)
    
26.   File "C:\Users\Administrator\AppData\Local\Programs\Python\Python36-32\lib\http\client.py", line 1212, in putheader
    
27.     values[i] = one_value.encode('latin-1')
    
28. UnicodeEncodeError: 'latin-1' codec can't encode characters in position 15-18: ordinal not in range(256)

复制代码

hldh214

sercoverurl 这个 list 已经告诉你答案
仔细检查其中的每一个元素

SixPy

url 里有中文

qq13459621230

hldh214 发表于 2017-7-28 22:18
sercoverurl 这个 list 已经告诉你答案
仔细检查其中的每一个元素

请问错误代码哪里是提示sercoverurl错误的 ，我找不到。。

qq13459621230

SixPy 发表于 2017-7-29 07:54
url 里有中文

请问中文是？我有点不明白。。