爬取圖片（一）

源碼：

 1 import requests
 2 from lxml import etree
 3 from urllib import request
 4 import os
 5 
 6 # 獲取頁面圖集連接
 7 def get_url_list(page,headers):
 8     url = 'http://www.meizitu.com/a/more_{}.html'.format(page)
 9     response = requests.get(url,headers=headers)
10     response.encoding = 'gbk'
11     # print(response.text)
12     html_ele = etree.HTML(response.text)
13     ele_list = html_ele.xpath('//ul[@class="wp-list clearfix"]/li')
14     page_list = []
15     for ele in ele_list:
16         url = ele.xpath('./div/div/a/@href')
17         # print(url)
18         page_list.append(url[0])
19     return page_list
20 
21 # 保存圖片
22 def get_pictures(url,headers):
23     response = requests.get(url,headers=headers)
24     response.encoding = 'gbk'
25     html_ele = etree.HTML(response.text)
26     dir = html_ele.xpath('//div[@class="metaRight"]/h2/a')[0].text
27     dir_name = '妹子圖/' + dir
28     if not os.path.exists(dir_name):
29         os.makedirs(dir_name)
30     url_list = html_ele.xpath('//div[@id="picture"]/p/img/@src')
31     for url in url_list:
32         try:
33             name = url.split('/')[-1]
34             filename = dir_name + '/' + name
35             if not os.path.exists(filename):
36                 request.urlretrieve(url,filename)
37                 print(filename)
38         except:
39             pass
40 
41 
42 if __name__ == '__main__':
43     headers = {
44         'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/67.0.3396.99 Safari/537.36'
45     }
46     for page in range(1,73):
47         page_list = get_url_list(page,headers)
48         for url in page_list:
49             get_pictures(url,headers)