[已解决]爬虫报错找不到原因

张冬冬

import urllib.request
import os
import random


def url_open(url):
    req = urllib.request.Request(url)
    req.add_header('User-Agent', 'Mozilla/5.0 (Windows NT 6.3; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/39.0.2171.65 Safari/537.36')
    response = urllib.request.urlopen(url)
    html = response.read()

    return html


def get_page(url):
    html = url_open(url).decode('utf-8')

    a = html.find('current-comment-page') + 23
    b = html.find(']', a)

    return html[a:b]


def find_imgs(url):
    html = url_open(url).decode('utf-8')
    img_addrs = []

    a = html.find('img src=')

    while a != -1:
        b = html.find('.jpg', a, a+225)
        if b != -1:
            img_addrs.append(html[a+9:b+4])
        else:
            b = a + 9

        a = html.find('img src=', b)

    return img_addrs
     

def save_imgs(folder, img_addrs):
    for each in img_addrs:
        filename = each.split('/')[-1]
        with open(filename,'wb') as f:
            img =url_open(each)
            f.write(img)
            
def download_mm(folder='OOXX', pages=10):
    os.mkdir(folder)
    os.chdir(folder)

    url = "http://jandan.net/ooxx/"
    page_num = int(get_page(url))

    for i in range(pages):
        page_num -= i
        page_url = url + 'page-' + str(page_num) + '#comments'
        img_addrs = find_imgs(page_url)
        save_imgs(folder, img_addrs)

if __name__ == '__main__':
    download_mm()

===========
Traceback (most recent call last):
  File "E:\Python\056轮一只爬虫的自我修养4：OOXX\课堂演示\meizhi.py", line 63, in <module>
    download_mm()
  File "E:\Python\056轮一只爬虫的自我修养4：OOXX\课堂演示\meizhi.py", line 60, in download_mm
    save_imgs(folder, img_addrs)
  File "E:\Python\056轮一只爬虫的自我修养4：OOXX\课堂演示\meizhi.py", line 46, in save_imgs
    img =url_open(each)
  File "E:\Python\056轮一只爬虫的自我修养4：OOXX\课堂演示\meizhi.py", line 7, in url_open
    req = urllib.request.Request(url)
  File "C:\Users\Administrator\AppData\Local\Programs\Python\Python36\lib\urllib\request.py", line 329, in __init__
    self.full_url = url
  File "C:\Users\Administrator\AppData\Local\Programs\Python\Python36\lib\urllib\request.py", line 355, in full_url
    self._parse()
  File "C:\Users\Administrator\AppData\Local\Programs\Python\Python36\lib\urllib\request.py", line 384, in _parse
    raise ValueError("unknown url type: %r" % self.full_url)
ValueError: unknown url type: '//wx1.sinaimg.cn/mw600/a2edc015ly1fhhk0q9xl3j20ml0xwq7k.jpg'
请问应该怎么解决

最佳答案

月排行榜 / 总排行榜

SixPy

2017-7-14 01:27:25

http://search.fishc.com/cse/search?s=14988791857133860392&q=ValueError%3A%20unknown%20url%20type&partner=discuz

跳转到最佳答案楼层

SixPy

http://search.fishc.com/cse/search?s=14988791857133860392&q=ValueError%3A%20unknown%20url%20type&partner=discuz

新手·ing

//wx1.sinaimg.cn/mw600/a2edc015ly1fhhk0q9xl3j20ml0xwq7k.jpg
前面加http或https

张冬冬

新手·ing 发表于 2017-7-14 07:47
//wx1.sinaimg.cn/mw600/a2edc015ly1fhhk0q9xl3j20ml0xwq7k.jpg
前面加http或https

请问在哪里加，这是属于图片链接，下载下来的

新手·ing

张冬冬 发表于 2017-7-15 01:08
请问在哪里加，这是属于图片链接，下载下来的

1. 
   
2. import urllib.request
   
3. import os
   
4. import random
   
5. 
   
6. 
   
7. def url_open(url):
   
8.     req = urllib.request.Request(url)
   
9.     req.add_header('User-Agent', 'Mozilla/5.0 (Windows NT 6.3; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/39.0.2171.65 Safari/537.36')
   
10.     response = urllib.request.urlopen(url)
    
11.     html = response.read()
    
12. 
    
13.     return html
    
14. 
    
15. 
    
16. def get_page(url):
    
17.     html = url_open(url).decode('utf-8')
    
18. 
    
19.     a = html.find('current-comment-page') + 23
    
20.     b = html.find(']', a)
    
21. 
    
22.     return html[a:b]
    
23. 
    
24. 
    
25. def find_imgs(url):
    
26.     html = decode('utf-8')
    
27.     img_addrs = []
    
28. 
    
29.     a = html.find('img src=')
    
30. 
    
31.     while a != -1:
    
32.         b = html.find('.jpg', a, a+225)
    
33.         if b != -1:
    
34.             img_addrs.append(html[a+9:b+4])
    
35.         else:
    
36.             b = a + 9
    
37. 
    
38.         a = html.find('img src=', b)
    
39. 
    
40.     return img_addrs
    
41.      
    
42. 
    
43. def save_imgs(folder, img_addrs):
    
44.     for each in img_addrs:
    
45.         filename = each.split('/')[-1]
    
46.         with open(filename,'wb') as f:
    
47.             img =url_open(each)
    
48.             f.write(img)
    
49.             
    
50. def download_mm(folder='OOXX', pages=10):
    
51.     os.mkdir(folder)
    
52.     os.chdir(folder)
    
53. 
    
54.     url = "http://jandan.net/ooxx/"
    
55.     page_num = int(get_page(url))
    
56. 
    
57.     for i in range(pages):
    
58.         page_num -= i
    
59.         page_url = url + 'page-' + str(page_num) + '#comments'
    
60.         img_addrs = find_imgs(page_url)
    
61.         save_imgs(folder, img_addrs)
    
62. 
    
63. if __name__ == '__main__':
    
64.     download_mm()
    
65. 
    

复制代码

张冬冬

新手·ing 发表于 2017-7-15 07:26

我以前跟你这个一样，有错误，save_imgs应该改成这个样子
def save_imgs(folder, img_addrs):
    for each in img_addrs:
        filename = each.split('/')[-1]
        with open(filename,'wb') as f:
            print(each)
            img = url_open('http:'+each)
            f.write(img)