爬煎蛋妹子图时，打开图片网址报错

Hit_echo

已经到最后保存了，网址找的也是对的，就是打开时，提示未知url类型，但是我用浏览器是能打开图片的！

========== RESTART: C:\Users\acer\Desktop\MyPython\download_girl.py ==========
//ww1.sinaimg.cn/mw600/005vbOHfgw1fbn002fhfjj31ai1xr133.jpg
Traceback (most recent call last):
  File "C:\Users\acer\Desktop\MyPython\download_girl.py", line 78, in <module>
    download_girl()
  File "C:\Users\acer\Desktop\MyPython\download_girl.py", line 65, in download_girl
    save_imag(folder, imag_addrs)
  File "C:\Users\acer\Desktop\MyPython\download_girl.py", line 47, in save_imag
    imag = url_open(each)
  File "C:\Users\acer\Desktop\MyPython\download_girl.py", line 6, in url_open
    req = urllib.request.Request(url)
  File "C:\Users\acer\AppData\Local\Programs\Python\Python35\lib\urllib\request.py", line 269, in __init__
    self.full_url = url
  File "C:\Users\acer\AppData\Local\Programs\Python\Python35\lib\urllib\request.py", line 295, in full_url
    self._parse()
  File "C:\Users\acer\AppData\Local\Programs\Python\Python35\lib\urllib\request.py", line 324, in _parse
    raise ValueError("unknown url type: %r" % self.full_url)
ValueError: unknown url type: '//ww1.sinaimg.cn/mw600/005vbOHfgw1fbn002fhfjj31ai1xr133.jpg'

hldh214

前面加上 http:

yaopu

具体是什么问题啊？上代码啊！！！！

Hit_echo

hldh214 发表于 2017-1-13 13:32
前面加上 http:

没用

Hit_echo

yaopu 发表于 2017-1-13 13:37
具体是什么问题啊？上代码啊！！！！

代码跟小甲鱼的一样的  前面步骤都对  网址已经找出来了 就是下载保存的时候   不能识别url的类型

Hit_echo

import urllib.request
import os


def url_open(url):
    req = urllib.request.Request(url)
    req.add_header('User-Agent', 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/55.0.2883.87 Safari/537.36')
    #proxies = ['119.6.144.70:81', '111.1.36.9:80', '203.144.144.162:8080']
    response = urllib.request.urlopen(req)
    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_imag(url):
    html = url_open(url).decode('utf-8')
    imag_addrs = []

    a = html.find('img src=')

    while a != -1:
        b = html.find('.jpg', a, a+255)

        if b != -1:
            imag_addrs.append(html[a+9:b+4])
        else:
            b = a + 9

        a = html.find('img src=', b)
        
    return imag_addrs
   

def save_imag(folder, imag_addrs):
    for each in imag_addrs:
        filename = each.split('/')[-1]  #取最后一个
        with open(filename, 'wb') as f:
            print(each)
            imag = url_open(each)
            f.write(imag)




def download_girl(folder='OOXX',pages=1):
    os.mkdir(folder)  #创建目录
    os.chdir(folder)  #改变当前工作目录

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

    for i in range(pages):
        page_num -= 1
        page_url = url + '/page-' + str(page_num) + '#comments'

        imag_addrs = find_imag(page_url)
        save_imag(folder, imag_addrs)

if __name__ == '__main__':
    download_girl()

Hit_echo

//ww2.sinaimg.cn/mw600/ec684c61gw1fbr65mzyqqj20j60xkwis.jpg
Traceback (most recent call last):
  File "C:\Users\acer\Desktop\MyPython\download_girl.py", line 78, in <module>
    download_girl()
  File "C:\Users\acer\Desktop\MyPython\download_girl.py", line 65, in download_girl
    save_imag(folder, imag_addrs)
  File "C:\Users\acer\Desktop\MyPython\download_girl.py", line 47, in save_imag
    imag = url_open(each)
  File "C:\Users\acer\Desktop\MyPython\download_girl.py", line 6, in url_open
    req = urllib.request.Request(url)
  File "C:\Users\acer\AppData\Local\Programs\Python\Python35\lib\urllib\request.py", line 269, in __init__
    self.full_url = url
  File "C:\Users\acer\AppData\Local\Programs\Python\Python35\lib\urllib\request.py", line 295, in full_url
    self._parse()
  File "C:\Users\acer\AppData\Local\Programs\Python\Python35\lib\urllib\request.py", line 324, in _parse
    raise ValueError("unknown url type: %r" % self.full_url)
ValueError: unknown url type: '//ww2.sinaimg.cn/mw600/ec684c61gw1fbr65mzyqqj20j60xkwis.jpg'

hldh214

def save_imag(folder, imag_addrs):
    for each in imag_addrs:
        filename = each.split('/')[-1]  #取最后一个
        with open(filename, 'wb') as f:
            print(each)
            imag = url_open('http:' + each)
            f.write(imag)

lqq802877

楼主 这个问题解决了吗

fishshuke

hldh214 发表于 2017-1-15 16:00

正解！
小甲鱼的代码要填上url_open('http:' + each)