[已解决]Python 第56课 一直遇到404错误 不知问题在哪儿

吴芒果

1. import urllib.request
   
2. import sys
   
3. import os
   
4. 
   
5. 
   
6. def url_open(url):
   
7.     req = urllib.request.Request(url)
   
8.     req.add_header('User-Agent',
   
9.                    'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/55.0.2883.87 Safari/537.36')
   
10.     resp = urllib.request.urlopen(url)
    
11.     html = resp.read()
    
12.     # print(html)
    
13.     return html
    
14. 
    
15. 
    
16. def get_page(url):  # 获取图片页码
    
17.     html = url_open(url).decode('utf-8')  # 解码，之后查找图片页码做准备
    
18.     a = html.find('current-comment-page') + 23  # 返回页码数的首位置
    
19.     b = html.find(']', a)  # 返回页码数的末位置
    
20.     # print(html[a:b])
    
21.     return html[a:b]  # 拼接返回页码
    
22. 
    
23. 
    
24. def find_imgs(url):  # 在当前URL查找图片
    
25.     html = url_open(url).decode('utf-8')
    
26.     img_addrs = []
    
27. 
    
28.     a = html.find('img src=')  # 图片真实地址
    
29. 
    
30.     while a != -1:
    
31.         b = html.find('.jpg', a, a + 200)
    
32.         if b != -1:
    
33.             img_addrs.append(html[a + 9:b + 4])
    
34.         else:
    
35.             b = a + 9
    
36. 
    
37.         a = html.find('img src=', b)
    
38.     return img_addrs
    
39. 
    
40. 
    
41. def save_imgs(img_addrs):
    
42.     for each in img_addrs:
    
43.         filename = each.split('/')[-1]
    
44.         with open(filename, 'wb') as f:
    
45.             img = url_open(each)
    
46.             f.write(img)
    
47. 
    
48. 
    
49. def download(folder='Girls', pages=20):
    
50.     os.mkdir(folder)  # 创建文件夹
    
51.     os.chdir(folder)  # 切换到文件夹目录
    
52. 
    
53.     url = 'http://jandan.net/ooxx'
    
54.     page_num = int(get_page(url))  # 获取当前该图片页码
    
55. 
    
56.     for i in range(pages):  # 依次下载指定页数的图片
    
57.         page_num -= 1
    
58.         page_url = url + 'page-' + str(page_num) + '#comments'  # 图片的URL
    
59.         # print(page_url)
    
60.         img_addrs = find_imgs(page_url)
    
61.         save_imgs(img_addrs)
    
62. 
    
63. 
    
64. if __name__ == '__main__':
    
65.     download()
    

复制代码

错误原因如下：

1. Traceback (most recent call last):
   
2.   File "C:\Program Files\JetBrains\PyCharm 2017.1.4\helpers\pydev\pydev_run_in_console.py", line 78, in <module>
   
3.     globals = run_file(file, None, None)
   
4.   File "C:\Program Files\JetBrains\PyCharm 2017.1.4\helpers\pydev\pydev_run_in_console.py", line 35, in run_file
   
5.     pydev_imports.execfile(file, globals, locals)  # execute the script
   
6.   File "C:\Program Files\JetBrains\PyCharm 2017.1.4\helpers\pydev\_pydev_imps\_pydev_execfile.py", line 18, in execfile
   
7.     exec(compile(contents+"\n", file, 'exec'), glob, loc)
   
8.   File "E:/Python_Learn/PycharmProjects/Spider_Test/DownloadMMPic.py", line 65, in <module>
   
9.     download()
   
10.   File "E:/Python_Learn/PycharmProjects/Spider_Test/DownloadMMPic.py", line 60, in download
    
11.     img_addrs = find_imgs(page_url)
    
12.   File "E:/Python_Learn/PycharmProjects/Spider_Test/DownloadMMPic.py", line 25, in find_imgs
    
13.     html = url_open(url).decode('utf-8')
    
14.   File "E:/Python_Learn/PycharmProjects/Spider_Test/DownloadMMPic.py", line 10, in url_open
    
15.     resp = urllib.request.urlopen(url)
    
16.   File "C:\Users\imwoo\AppData\Local\Programs\Python\Python36\lib\urllib\request.py", line 223, in urlopen
    
17.     return opener.open(url, data, timeout)
    
18.   File "C:\Users\imwoo\AppData\Local\Programs\Python\Python36\lib\urllib\request.py", line 532, in open
    
19.     response = meth(req, response)
    
20.   File "C:\Users\imwoo\AppData\Local\Programs\Python\Python36\lib\urllib\request.py", line 642, in http_response
    
21.     'http', request, response, code, msg, hdrs)
    
22.   File "C:\Users\imwoo\AppData\Local\Programs\Python\Python36\lib\urllib\request.py", line 570, in error
    
23.     return self._call_chain(*args)
    
24.   File "C:\Users\imwoo\AppData\Local\Programs\Python\Python36\lib\urllib\request.py", line 504, in _call_chain
    
25.     result = func(*args)
    
26.   File "C:\Users\imwoo\AppData\Local\Programs\Python\Python36\lib\urllib\request.py", line 650, in http_error_default
    
27.     raise HTTPError(req.full_url, code, msg, hdrs, fp)
    
28. urllib.error.HTTPError: HTTP Error 404: Not Found
    

复制代码

最佳答案

月排行榜 / 总排行榜

ba21

2017-8-1 22:57:21

跳转到最佳答案楼层

老甲鱼与小甲鱼

404不关你的事吧，要么是url错了，要么网站出问题了

吴芒果

老甲鱼与小甲鱼 发表于 2017-8-1 21:56
404不关你的事吧，要么是url错了，要么网站出问题了

1. get_page(url)

复制代码

没有出错，也能正确print(html)
但是在

1. find_imgs()

复制代码

中就会出错，也不能print(html).

1. import urllib.request
   
2. 
   
3. def url_open(url):
   
4.     req = urllib.request.Request(url)
   
5.     req.add_header('User-Agent', 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/55.0.2883.87 Safari/537.36')
   
6.     resp = urllib.request.urlopen(url)
   
7.     html = resp.read()
   
8.     # print(html)
   
9.     return html
   
10. 
    
11. def find_imgs():  # 在当前URL查找图片
    
12.     html = url_open('http://jandan.net/pic/page-303#comments').decode('utf-8')
    
13.     print(html)
    
14.     # img_addrs = []
    
15.     # a = html.find('img src=')  # 图片真实地址
    
16.     #
    
17.     # while a != -1:
    
18.     #     b = html.find('.jpg', a, a + 200)
    
19.     #     if b != -1:
    
20.     #         img_addrs.append(html[a + 9:b + 4])
    
21.     #     else:
    
22.     #         b = a + 9
    
23.     #     a = html.find('img src=', b)
    
24.     # return img_addrs
    

复制代码

单独运行find_imgs()方法也出错
错误原因一样

ba21

吴芒果

ba21 发表于 2017-8-1 22:57

十分感谢