解决下载妹子网图片数据不全的两种方法

方法一：

# -*- coding: utf-8 -*-
"""
Created on Tue Nov 22 02:24:33 2016

@author: alis
"""

import urllib,urllib2
import time
import traceback
begin = time.clock()
x = 0
b = '/media/alis/个人文件资料/Spider/MeiZi/photo/'
with open('/media/alis/个人文件资料/Spider/MeiZi/MeiZi/output.txt') as fle:
for url in fle.readlines():
x += 1
print url
try:
req = urllib2.Request(url, headers={'User-Agent': r'Mozilla/5.0 (Windows NT 6.1; WOW64; rv:45.0) Gecko/20100101 Firefox/45.0'})
data = urllib2.urlopen(req, timeout=1).read()
filename = b+'{0}.jpg'.format(x)
with open(filename, 'wb') as fle:
fle.write(data)
except:
traceback.print_exc()
end = time.clock()
print end - begin

原理其实就是进去图片的网页获取其源码，然后把它写进去一个文件中即可。（注意添加headers）
方法二：

import requests
from PIL import Image
from io import BytesIO

url = 'http://mm.howkuai.com/wp-content/uploads/2016a/08/31/01.jpg'
headers = {'User-Agent':'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/54.0.2840.99 Safari/537.36',
'Host':'mm.howkuai.com'}
response = requests.get(url, headers=headers)
print response.status_code
img = Image.open(BytesIO(response.content))
img.save('/home/alis/桌面/mm.jpg')这种方法是利用二进制读写，一位网友写的，其实不是很看得懂，具体用法可以参考廖雪峰的教学视频
‘http://www.liaoxuefeng.com/wiki/0014316089557264a6b348958f449949df42a6d3a2e542c000/001431918785710e86a1a120ce04925bae155012c7fc71e000’