How to download images from Bing?

Here is a small python script I used to download images from bing search engine. An extra test is performed to check if the image has the focal length in the exif information. This information is mandatory for bundler so the download system will skip the images which are not matching.

To download images from bing, you must first create an app_id for your application here:  http://www.bing.com/developers/createapp.aspx

There already exists libraries to get search result from bing: pybing and bingapi. They both work pretty well. I decided to use pybing. So let's install it:

sudo easy_install pybing

The next step is to install the python imaging library in order to capture the EXIF information:

sudo easy_install PIL

Script

1. from pybing.query.query import BingQuery
2. from pybing.resultset import BingResultSet
3. from pybing.query import BingQuery
4. from pybing.query import Pagable
6. import Image
7. import ExifTags
9. import os
10. import sys
12. __author__ = 'jacques fontignie'
14. from pybing import *
16. APP_ID = <ENTER_YOUR_APP_ID>
18. exifAttrs = dict(Model=True,Make=True,ExifImageWidth=True,ExifImageHeight=True,FocalLength=True)
19.                  
20. class ImageQuery(BingQuery, Pagable):
21.     SOURCE_TYPE = constants.IMAGE_SOURCE_TYPE
22.    
23.     def get_request_parameters(self):
24.         params = super(ImageQuery, self).get_request_parameters()
25.         params.update({
26.             'Image.Filters': 'Style:Photo'        
27.         })
28.         return params
30. def download(dir, filename, url):
31.     """Copy the contents of a file from a given URL
32.    to a local file.
33.    """
34.     import urllib2
35.    
36.     try:
37.         webFile = urllib2.urlopen(url)
38.     except:
39.         print "Unexpected error:", sys.exc_info()[0]
40.         return False
41.     extension = url.split('.')[-1].lower()
42.     if not extension == "jpg":
43.         print "not a jpg extension: " + url
44.         return False
45.     localPath = dir + "/" + filename + "." + extension
46.     localFile = open(localPath, 'w')
47.     localFile.write(webFile.read())
48.     webFile.close()
49.     localFile.close()  
50.    
51.     print "File successfully downloaded"
52.     try:
53.         photoHandle = Image.open(localPath)
54.        
55.         found = False
56.         exif = {}
57.         info = photoHandle._getexif()
58.         if info:
59.             for attr, value in info.items():
60.                 decodedAttr = ExifTags.TAGS.get(attr, attr)
61.                 if decodedAttr in exifAttrs: exif[decodedAttr] = value
62.                 if 'FocalLength' in exif:
63.                     found = True    
64.            
65.         if not found:
66.             print "Dropping the file as it does not contain any useful exif information"
67.             os.remove(localPath)
68.             return False
69.    
70.     except:
71.         print "Unexpected error:", sys.exc_info()[0]
72.         os.remove(localPath)
73.         return False
74.         # get EXIF information as a dictionary
75.    
76.    
77.     return True
79. def main():
80.    
81.     dir = "images"
82.     if not os.path.exists(dir):
83.         os.makedirs(dir)
84.    
85.    
86.     query = ImageQuery(APP_ID,query="rushmore")      
87.          
88.     results = query.execute()
89.     default_name = "img_"
90.     index = 0
91.     count = 0
92.    
93.     for result in results:
94.         count = count +1
95.        
96.         url = result.mediaurl
97.         print (str(index) + ") " + str(count) + "- " + url)
98.         filename = default_name + '%05d' % index
99.                  
100.         if download(dir,filename,url):
101.             index = index + 1
102.        
103.        
104.         if index == 500:
105.             break
107.        
108.     print "Images succesfully fetched ({})".format(index)
109.        
110.    
111. if __name__ == '__main__':
112.   main()