Ajax爬取今日头条街拍美图

 1 import requests
 2 from urllib.parse import urlencode
 3 import os
 4 from hashlib import md5
 5 from multiprocessing.pool import Pool
 6 
 7 def get_page(offset):
 8     params = {
 9         ‘offset‘: offset,
10         ‘format‘: ‘json‘,
11         ‘keyword‘: ‘街拍‘,
12         ‘autoload‘: ‘true‘,
13         ‘count‘: ‘20‘,
14         ‘cur_tab‘: ‘1‘,
15         ‘from‘: ‘search_tab‘
16     }
17     url = ‘http://www.toutiao.com/search_content/?‘ + urlencode(params)
18     try:
19         response = requests.get(url)
20         if response.status_code == 200:
21             return response.json()
22     except requests.ConnectionError:
23         return None
24 
25 def get_images(json):
26     if json.get(‘data‘):
27         data = json.get(‘data‘)
28         for item in data:
29             if item.get(‘cell_type‘) is not None:
30                 continue
31             title = item.get(‘title‘)
32             images = item.get(‘image_list‘)
33             for image in images:
34                 yield{
35                     ‘image‘: ‘http:‘ + image.get(‘url‘),
36                     ‘title‘: title
37                 }
38 
39 def save_image(item):
40     image_path = ‘img‘ + os.path.sep + item.get(‘title‘)
41     if not os.path.exists(image_path):
42         os.mkdir(image_path)
43     try:
44         response = requests.get(item.get(‘image‘))
45         if response.status_code == 200:
46             file_path = image_path + os.path.sep + ‘{file_name}.{file_suffix}‘.format(
47                 file_name=md5(response.content).hexdigest(),
48                 file_suffix=‘jpg‘
49             )
50             if not os.path.exists(file_path):
51                 with open(file_path, ‘wb‘) as f:
52                     f.write(response.content)
53                     print(‘Downloaded image path is {0}‘.format(file_path))
54             else:
55                 print(‘Already Downloads‘, file_path)
56     except requests.ConnectionError:
57         print(‘Failed to save image !!!‘)
58 
59 def main(offset):
60     json = get_page(offset)
61     for item in get_images(json):
62         print(item)
63         save_image(item)
64 
65 GROUP_START = 0
66 GROUP_END = 9
67 
68 if __name__ == ‘__main__‘:
69     pool = Pool()
70     groups = ([x * 20 for x in range(GROUP_START, GROUP_END+1)])
71     pool.map(main, groups)
72     pool.close()
73     pool.join()