爬虫_斗图啦_表情包下载

 1 import requests
 2 from lxml import etree
 3 import re
 4 from urllib import request
 5 import time
 6 import os
 7 
 8 def get_html(url):
 9     headers = {‘User-Agent‘: ‘Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/68.0.3440.75 Safari/537.36‘}
10     try:
11         response = requests.get(url, headers=headers)
12         response.raise_for_status()
13 
14         response.encoding = ‘utf-8‘
15         return response.text
16     except:
17         return 0
18 
19 
20 def parse_html(html):
21     html_element = etree.HTML(html)
22     imgs = html_element.xpath(‘//div[@class="page-content text-center"]//img[@class!="gif"]‘)
23     for img in imgs:
24         url = img.get(‘data-original‘)
25         name = img.get(‘alt‘)
26         name = re.sub(‘[?？，。]‘, ‘‘, name)#看系统的命名要求了
27         tail = os.path.splitext(url)[1] #取后缀
28 
29         file_name = name + tail  #拼接文件名
30         request.urlretrieve(url, ‘images/‘ + file_name)  #注意提前新建images文件夹
31 
32 
33 def main():
34     for i in range(1, 50):
35         url = ‘http://www.doutula.com/photo/list/?page=%d‘ % i
36         html = get_html(url)
37         while html == 0:
38             time.sleep(2)
39             html = get_html(url)
40         parse_html(html)
41         # break
42 
43             
44 if __name__ == ‘__main__‘:
45     main()