scraping full size images from Google Images

scrapeImages.py

from bs4 import BeautifulSoup
import requests
import re
import urllib2
import os
import argparse
import sys
import json

# adapted from http://stackoverflow.com/questions/20716842/python-download-images-from-google-image-search

def get_soup(url,header):
    return BeautifulSoup(urllib2.urlopen(urllib2.Request(url,headers=header)),'html.parser')

def main(args):
	parser = argparse.ArgumentParser(description='Scrape Google images')
	parser.add_argument('-s', '--search', default='bananas', type=str, help='search term')
	parser.add_argument('-n', '--num_images', default=10, type=int, help='num images to save')
	parser.add_argument('-d', '--directory', default='/Users/gene/Downloads/', type=str, help='save directory')
	args = parser.parse_args()
	query = args.search#raw_input(args.search)
	max_images = args.num_images
	save_directory = args.directory
	image_type="Action"
	query= query.split()
	query='+'.join(query)
	url="https://www.google.co.in/search?q="+query+"&source=lnms&tbm=isch"
	header={'User-Agent':"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/43.0.2357.134 Safari/537.36"}
	soup = get_soup(url,header)
	ActualImages=[]# contains the link for Large original images, type of  image
	for a in soup.find_all("div",{"class":"rg_meta"}):
	    link , Type =json.loads(a.text)["ou"]  ,json.loads(a.text)["ity"]
	    ActualImages.append((link,Type))
	for i , (img , Type) in enumerate( ActualImages[0:max_images]):
	    try:
	        req = urllib2.Request(img, headers={'User-Agent' : header})
	        raw_img = urllib2.urlopen(req).read()
	        if len(Type)==0:
	            f = open(os.path.join(save_directory , "img" + "_"+ str(i)+".jpg"), 'wb')
	        else :
	            f = open(os.path.join(save_directory , "img" + "_"+ str(i)+"."+Type), 'wb')
	        f.write(raw_img)
	        f.close()
	    except Exception as e:
	        print "could not load : "+img
	        print e

if __name__ == '__main__':
    from sys import argv
    try:
        main(argv)
    except KeyboardInterrupt:
        pass
    sys.exit()

You have to import selenium By module.

Thank you. I imported selenium By module and the program can go further but I still have an error (photo)

you have to update the class definition in xpath

Thanks, I will try !

Hello, I tried to update the Xpath class but it does not change anything. I did some research but I have trouble understanding. I had to change some things, now there is no more error but it still doesn't work. Google opens the page, scrolls and that's it. Do you think you could try on your side with the link and tell me if it works? And eventually tell me how you did it please?
Here is the link (https://www.google.com/search?q=french+pedestrian+light&rlz=1C1CHBF_frFR1008FR1008&source=lnms&tbm=isch&sa=X&ved=2ahUKEwiGgui61IX9AhVaQaQEHeS4CkgQ_AUoAXoECAEQAw&biw=1536&bih=714&dpr=1.25).

`
from selenium import webdriver
from selenium.webdriver.common.by import By
from selenium.webdriver.chrome.service import Service
import time
import requests
import shutil
import os
import argparse

def save_img(inp,img,i, directory):
try:
filename = inp+str(i)+'.jpg'
response = requests.get(img,stream=True)
image_path = os.path.join(directory, filename)
with open(image_path, 'wb') as file:
shutil.copyfileobj(response.raw, file)
except Exception:
pass

def find_urls(inp,url,driver, directory):
driver.get(url)
img_urls = driver.find_elements(By.XPATH,'//img[contains(@Class,"rg_i yDmH0d")]')
#img_urls = driver.find_elements(By.XPATH,'//*[@id="yDmH0d"]')
for _ in range(500):
driver.execute_script("window.scrollBy(0,10000)")
try:
driver.find_element_by_css_selector('.mye4qd').click()
except:
continue
for j, imgurl in enumerate(img_urls):
try:
img = imgurl.get_attribute('src')
save_img(inp,img,j, directory)
time.sleep(1.5)
except:
pass
s=Service('C:\chromedriver.exe')
if name == "main":
parser = argparse.ArgumentParser(description='Scrape Google images')
parser.add_argument('-s', '--search', default='banana', type=str, help='search term')
parser.add_argument('-d', '--directory', default='../Downloads/', type=str, help='save directory')
args = parser.parse_args()
driver = webdriver.Chrome(service=s)
directory = args.directory
inp = args.search
if not os.path.isdir(directory):
os.makedirs(directory)
url = 'https://www.google.com/search?q=french+pedestrian+light&rlz=1C1CHBF_frFR1008FR1008&source=lnms&tbm=isch&sa=X&ved=2ahUKEwiGgui61IX9AhVaQaQEHeS4CkgQ_AUoAXoECAEQAw&biw=1536&bih=714&dpr=1.25'
find_urls(inp,url,driver, directory)
`

Sorry, I tried to keep the identation of the code but it doesn't work

Sorry, I tried to keep the indentation of the code but it doesn't work

That's because it looks like you used only one backtick above and below instead of three. Also, tip for you, after the first three backticks, identify the language so that there will be syntax highlighting like so:

```python

<your code here>

```

Your code would look like this (plus my best guess at correct indentations) then:

from selenium import webdriver
from selenium.webdriver.common.by import By
from selenium.webdriver.chrome.service import Service
import time
import requests
import shutil
import os
import argparse


def save_img(inp,img,i, directory):
try:
  filename = inp+str(i)+'.jpg'
  response = requests.get(img,stream=True)
  image_path = os.path.join(directory, filename)
  with open(image_path, 'wb') as file:
    shutil.copyfileobj(response.raw, file)
except Exception:
  pass


def find_urls(inp,url,driver, directory):
driver.get(url)
img_urls = driver.find_elements(By.XPATH,'//img[contains(@Class,"rg_i yDmH0d")]')
#img_urls = driver.find_elements(By.XPATH,'//*[@id="yDmH0d"]')
for _ in range(500):
  driver.execute_script("window.scrollBy(0,10000)")
  try:
    driver.find_element_by_css_selector('.mye4qd').click()
  except:
    continue
    for j, imgurl in enumerate(img_urls):
      try:
        img = imgurl.get_attribute('src')
        save_img(inp,img,j, directory)
        time.sleep(1.5)
      except:
        pass
        s=Service('C:\chromedriver.exe')
        if name == "main":
          parser = argparse.ArgumentParser(description='Scrape Google images')
          parser.add_argument('-s', '--search', default='banana', type=str, help='search term')
          parser.add_argument('-d', '--directory', default='../Downloads/', type=str, help='save directory')
          args = parser.parse_args()
          driver = webdriver.Chrome(service=s)
          directory = args.directory
          inp = args.search
        if not os.path.isdir(directory):
          os.makedirs(directory)
          url = 'https://www.google.com/search?
q=french+pedestrian+light&rlz=1C1CHBF_frFR1008FR1008&source=lnms&tbm=isch&sa=X&ved=2ahUKEwiGgui61IX9AhVaQaQEHeS4CkgQ_AUoAXoECAEQAw&biw=1536&bih=714&dpr=1.25'

find_urls(inp,url,driver, directory)