1 #!/usr/bin/evn python
  2 # -*- coding:utf-8 -*-
  3 # __author__:
  4 #import urllib2
  5 import bs4
  6 import time
  7 import requests
  8 import fake_useragent
  9 import os
 10 import re
 11 import sys
 12 #import xlrd
 13 import random
 14
 15 # 用于将u 转换成 string
 16 reload(sys)
 17 sys.setdefaultencoding('utf-8')  # u -> str
 18
 19
 20 class GetPictures(object):
 21     def __init__(self):
 22         self.url = 'http://www.mmjpg.com/mm/1'
 23         self.first_num = 0
 24         self.sum_num = 0
 25         self.pictures_sum()
 26         self.urls = self.get_urls()
 27         for url in self.urls:
 28             self.down_pictures(self.get_img_urls(url))
 29
 30     # 输入需要的套数
 31     def pictures_sum(self):
 32         str1 = raw_input(r"第几套开始，重复会跳过")
 33         try:
 34             self.first_num = int(float(str1))
 35         except ValueError:
 36             print ('输入的不为数字')
 37
 38         str1 = raw_input("收集多少套")
 39         try:
 40             self.sum_num = int(float(str1))
 41         except ValueError:
 42             print("输入的不为数字")
 43             exit(1)
 44
 45     # 得到所有套图的第一张所在网页的URL
 46     def get_urls(self):
 47         urls = []
 48         for i in xrange(self.first_num, self.first_num+self.sum_num):
 49             url_split = self.url.split('/')
 50             url_split[-1] = str(i)
 51             urls.append('/'.join(url_split))
 52         # print urls
 53         return urls
 54
 55     # 得到一共有多少张图
 56     def get_img_sum_num(self, img_url):
 57         fa = fake_useragent.UserAgent()
 58         headers = {'User-Agent': fa.random,
 59                    'Referer': 'http://www.mmjpg.com'}
 60         request = requests.get(img_url, headers=headers)
 61         soup = bs4.BeautifulSoup(request.content, 'lxml')
 62         # 获取标签里面的值
 63         img_sum_number = soup.find_all('a', href=re.compile('/mm'))[8].get_text().strip()
 64         print img_sum_number
 65         img_sum_number = int(img_sum_number)
 66         # print img_sum_number
 67         return img_sum_number
 68
 69     # 得到该套图中的所有图片的URL
 70     def get_img_urls(self, url):
 71         fa = fake_useragent.UserAgent()
 72         headers = {'User-Agent': fa.random,
 73                    'Referer': 'http://m.mmjpg.com'}
 74         request = requests.get(url, headers=headers)
 75         soup = bs4.BeautifulSoup(request.content, 'lxml')
 76         first_img_url = soup.find('img').get('src')     # 获取标签值
 77         url_split = first_img_url.split('/')
 78         img_urls = []
 79         for i in xrange(1, self.get_img_sum_num(url)+1):
 80             url_split[-1] = (str(i)+'.jpg')
 81             img_urls.append('/'.join(url_split))
 82         # print img_urls
 83         return img_urls
 84
 85     # 下载图片
 86     def down_pictures(self, img_urls):
 87         img_name = str(img_urls[0].split('/')[-2])+'-'+str(img_urls[0].split('/')[-3])
 88         if os.path.exists(img_name):    # 查重 如果这个文件夹存在则跳过 防止重复下载
 89             time.sleep(1)
 90             print img_name+'存在'
 91             return
 92         os.mkdir(img_name)
 93         for img_url in img_urls:
 94             fa = fake_useragent.UserAgent()
 95             headers = {'User-Agent': fa.random,
 96                        'Referer': 'http://m.mmjpg.com'}
 97             request = requests.get(img_url, headers=headers)
 98
 99             with open(img_name + u'/' + img_url.split('/')[-1], 'wb') as f:
100                 f.write(request.content)    # contents返回的为二进制   text返回的为union类型
101                 f.close()
102                 print "已保存" + img_name + '/' + img_url.split('/')[-1]
103                 time.sleep(random.random()*2)
104
105
106 # 运行程序
107 if __name__ == '__main__':
108     GetPictures()
109
110 '''
111 用requests,bs4 抓取mmjpg.com上的套图
112 将上面的套图按套进行保存
113 '''