Download images from Google Image search using Python

gistfile1.py

import json
import os
import time
import requests
from PIL import Image
from StringIO import StringIO
from requests.exceptions import ConnectionError

def go(query, path):
  """Download full size images from Google image search.

  Don't print or republish images without permission.
  I used this to train a learning algorithm.
  """
  BASE_URL = 'https://ajax.googleapis.com/ajax/services/search/images?'\
             'v=1.0&q=' + query + '&start=%d'

  BASE_PATH = os.path.join(path, query)

  if not os.path.exists(BASE_PATH):
    os.makedirs(BASE_PATH)

  start = 0 # Google's start query string parameter for pagination.
  while start < 60: # Google will only return a max of 56 results.
    r = requests.get(BASE_URL % start)
    for image_info in json.loads(r.text)['responseData']['results']:
      url = image_info['unescapedUrl']
      try:
        image_r = requests.get(url)
      except ConnectionError, e:
        print 'could not download %s' % url
        continue

      # Remove file-system path characters from name.
      title = image_info['titleNoFormatting'].replace('/', '').replace('\\', '')

      file = open(os.path.join(BASE_PATH, '%s.jpg') % title, 'w')
      try:
        Image.open(StringIO(image_r.content)).save(file, 'JPEG')
      except IOError, e:
        # Throw away some gifs...blegh.
        print 'could not save %s' % url
        continue
      finally:
        file.close()

    print start
    start += 4 # 4 images per page.

    # Be nice to Google and they'll be nice back :)
    time.sleep(1.5)

# Example use
go('landscape', 'myDirectory')

@fieldse: try with python2 binary. I had no issues at all. Useful script.

The images which are downloaded are just stripes of colour.Any specific reason?

IOError: [Errno 22] invalid mode ('w') or filename: u'myDirectory\landscape\Na
ture - Photo gallery | MIRIADNA.COM.jpg'

@vinayshekhar000, @innermond, @fieldse, @crizCraig this is the error thaat showed any help?
pretty new to python pardon my ignorance.

@senam1 Substitute the line title = image_info['titleNoFormatting'].replace('/', '').replace('\\', '') with the following

title = image_info['titleNoFormatting']
title = "".join(x for x in title if x.isalnum())

@vinayshekhar000 To remove the stripes that you described, indicating 'binary' is important. Try replacing

file = open(os.path.join(BASE_PATH, '%s.jpg') % title, 'w')

with the following:

file = open(os.path.join(BASE_PATH, '%s.jpg') % title, 'wb')

Cheers!

How can one take >56 images?

    Traceback (most recent call last):
      File "gid.py", line 100, in <module>
        soup = get_soup(url,header)
      File "gid.py", line 89, in get_soup
        return BeautifulSoup(urllib2.urlopen(urllib2.Request(url,headers=header)))
      File "PYTHON_DIR/lib/urllib2.py", line 154, in urlopen
        return opener.open(url, data, timeout)
      File "PYTHON_DIR/lib/urllib2.py", line 437, in open
        response = meth(req, response)
      File "PYTHON_DIR/lib/urllib2.py", line 550, in http_response
        'http', request, response, code, msg, hdrs)
      File "PYTHON_DIR/lib/urllib2.py", line 475, in error
        return self._call_chain(*args)
      File "PYTHON_DIR/lib/urllib2.py", line 409, in _call_chain
        result = func(*args)
      File "PYTHON_DIR/lib/urllib2.py", line 558, in http_error_default
        raise HTTPError(req.get_full_url(), code, msg, hdrs, fp)
    urllib2.HTTPError: HTTP Error 404: Not Found

no longer service support

in go
    for image_info in json.loads(r.text)['responseData']['results']:
TypeError: 'NoneType' object has no attribute '__getitem__'

{"responseData": null, "responseDetails": "This API is no longer available.", "responseStatus": 403}

bummer :(

line 24, in crawl_images
for image_info in json.loads(r.text)['responseData']['results']:
TypeError: 'NoneType' object has no attribute 'getitem'

TypeError: 'NoneType' object has no attribute 'getitem'

Guys, look for another solution as this APU is no longer available. You can see that if you add "print r.text" before for-loop:
{"responseData": null, "responseDetails": "This API is no longer available.", "responseStatus": 403}

import random
import urllib.request

def web_image(url):
name=random.randrange(1,1000)
fullname= str(name)+".jpg"
urllib.request.urlretrieve(url,fullname)
web_image("https://www.tutorialspoint.com/python/images/python-mini.jpg")

please help me!!!!!!!!!!!!!!!!!
there is error in this code please short out this problem
this program of download an image from web using python

def recherche_image_phrase(self, phrase):
    #nom commun + adjectif
    
    self.phrase = phrase

    liste = []

    path =  "https://www.google.co.in/search?q={0}&source=lnms&tbm=isch"
    path1 = path.format(self.phrase)
    requete = requests.get(path1)
    page = requete.content
    soup = BeautifulSoup(page, "html.parser")  
    propriete = soup.find_all("img")
    
    with open("requete.py", "w") as file:
        file.write(str(propriete))
                
    with open("requete.py", "r") as file2:
        b = file2.read()
    liste.append(b)

     #
    for i in range(5):
        a = str(liste).find(str("src"))
        b = str(liste).find(str('" width='))
        
        url = liste[0][a+2:b-3]
        image = str("image_"+self.phrase+str(i)+".jpg")

        liste[0] = liste[0][b:-3]

        urllib.request.urlretrieve(str(url), image)
 #

euh c'est pas pour du telechargement de masse mais tu peux prendre AU MOINS la page d'image :D juste a changer le range et au pire tu met un try exept au #

bah ca a pas tout mis:
en gros pour les # tu met un try except pour ignorer l'erreur !

The API is no longer available unfortunately.

TypeError: 'NoneType' object is not subscriptable