新手入门爬虫

wenwen123

import urllib.request
import os
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/55.0.2883.87 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+255)
        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()


出现这样的错误，该怎么办？
Traceback (most recent call last):
  File "C:\Users\admin\Desktop\girl.py", line 55, in <module>
    download__mm()
  File "C:\Users\admin\Desktop\girl.py", line 51, in download__mm
    save_imgs(folder,img_addrs)
  File "C:\Users\admin\Desktop\girl.py", line 35, in save_imgs
    img=url_open(each)
  File "C:\Users\admin\Desktop\girl.py", line 4, in url_open
    req=urllib.request.Request(url)
  File "C:\Users\admin\AppData\Local\Programs\Python\Python36-32\lib\urllib\request.py", line 329, in __init__
    self.full_url = url
  File "C:\Users\admin\AppData\Local\Programs\Python\Python36-32\lib\urllib\request.py", line 355, in full_url
    self._parse()
  File "C:\Users\admin\AppData\Local\Programs\Python\Python36-32\lib\urllib\request.py", line 384, in _parse
    raise ValueError("unknown url type: %r" % self.full_url)
ValueError: unknown url type: '//wx2.sinaimg.cn/mw600/6cca1403ly1ffncgh8zfaj20ex0h53zv.jpg'

gopythoner

自己在论坛利用搜索功能找答案，这问题被问了无数遍了，图片链接前要加“http:”