Simple method to scrape google image from google search engine. - https://informationcorners.com/google-search-image-scraper/ ‎

google-image-download.py

# coding: utf-8

import time  # Importing the time library to check the time of code execution
import sys  # Importing the System Library
import os
import urllib.request
import rfc6266, requests
import random
import string

# ########## Edit From Here ###########

# This list is used to search keywords. You can edit this list to search for google images of your choice.
# You can simply add and remove elements of the list.
search_keyword = ['famous']

# This list is used to further add suffix to your search term.
# Each element of the list will help you download 100 images.
# First element is blank which denotes that no suffix is added to the search keyword of the above list.
# You can edit the list by adding/deleting elements from it.
# So if the first element of the search_keyword is 'Australia' and the second element of keywords is 'high resolution',
#  then it will search for 'Australia High Resolution'
keywords = ['quotes', 'sayings', 'best quotes', 'memes']

# local storage folder
storage_path = 'media'
storage_path = os.path.join(os.getcwd(), storage_path)

# ########## End of Editing ###########

error_links = []
error_count = 0


# random string
def random_string(n=8):
    chars = string.ascii_uppercase + string.ascii_lowercase + string.digits
    return ''.join([random.choice(chars) for _ in range(n)])


# Downloading entire Web Document (Raw Page Content)
def download_page(url):
    try:
        header = {'User-Agent': "Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.36 (KHTML, "
                                "like Gecko) Chrome/41.0.2228.0 Safari/537.36"}
        req = urllib.request.Request(url, headers=header)
        resp = urllib.request.urlopen(req)
        response_data = str(resp.read())
        return response_data
    except Exception as e:
        error_links.append(url)
        print(str(e))


# Finding 'Next Image' from the given raw page
def _images_get_next_item(s):
    start_line = s.find('rg_di')
    if start_line == -1:  # If no links are found then give an error!
        end_quote = 0
        link = "no_links"
        return link, end_quote
    else:
        start_line = s.find('"class="rg_meta"')
        start_content = s.find('"ou"', start_line + 1)
        end_content = s.find(',"ow"', start_content + 1)
        content_raw = str(s[start_content + 6:end_content - 1])
        return content_raw, end_content


# Getting all links with the help of '_images_get_next_image'
def _images_get_all_items(page):
    _items = []
    while True:
        item, end_content = _images_get_next_item(page)
        if item == "no_links":
            break
        else:
            error_url = item
            fault_value = 'u003d'
            if fault_value in error_url:
                urls = error_url.split(fault_value, 2)
                url = urls[1]
                url = url.split('\\', 2)[0]
                item = url
            _items.append(item)  # Append all the links in the list named 'Links'
            time.sleep(0.1)  # Timer could be used to slow down the request for image downloads
            page = page[end_content:]
    return _items

############## Main Program ############
t0 = time.time()  # start the timer

# Download Image Links
index = 0
while index < len(search_keyword):
    items = []
    iteration = "Item no.: {} -->  Item name =  {}".format(index + 1, search_keyword[index])
    print(iteration)
    print("Evaluating...")
    search_keywords = search_keyword[index]
    search = search_keywords.replace(' ', '%20')
    path_to_store = os.path.join(storage_path, search_keywords.strip().replace(' ', '_'))

    # make a search keyword  directory
    if not os.path.exists(path_to_store):
        os.makedirs(path_to_store)

    j = 0
    while j < len(keywords):
        pure_keyword = keywords[j].replace(' ', '%20')
        url = 'https://www.google.com/search?q=' + search + '%20' + pure_keyword + \
              '&espv=2&biw=1366&bih=667&site=webhp&source=lnms&tbm=isch&sa=X&ei=XosDVaCXD8TasATItgE&ved=0CAcQ_AUoAg'
        raw_html = (download_page(url))
        time.sleep(0.1)
        items += _images_get_all_items(raw_html)
        j += 1

    # print ("Image Links = "+str(items))
    print("Total Image Links = " + str(len(items)))
    print("\n")

    # This allows you to write all the links into a test file.
    # This text file will be created in the same directory as your code.
    # You can comment out the below 3 lines to stop writing the output to the text file.
    # Open the text file called database.txt
    with open('output.txt', 'a') as info:
        info.write('\n')
        info.write("Google search results for " + search_keyword[index - 1])
        info.write("Total Image Links = " + str(len(items)))
        info.write('\n')
        info.write(str(index) + ': ' + str(search_keyword[index - 1]) + ": " + str(items) + "\n\n\n")

    t1 = time.time()  # stop the timer
    total_time = t1 - t0  # Calculating the total time required to crawl,
    print("Total time taken: " + str(total_time) + " Seconds")
    print("Starting Download...")

    # To save images to the same directory
    # IN this saving process we are just skipping the URL if there is any error

    k = 0
    while k < len(items):
        try:
            header = dict()
            header['User-Agent'] = "Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.36 (KHTML, like Gecko) " \
                                   "Chrome/41.0.2228.0 Safari/537.36"
            req = urllib.request.Request(items[k], headers=header)
            print(items[k])
            response = urllib.request.urlopen(req, None, 15)
            file_name = rfc6266.parse_requests_response(response).filename_unsafe
            file_to_write = os.path.join(path_to_store, random_string() + '_' + file_name)

            with open(file_to_write, 'wb') as output_file:
                data = response.read()
                output_file.write(data)
            response.close()
            print("completed ====> " + str(k + 1))
            k += 1
        except Exception as e:
            error_links.append(items[k])
            error_count += 1
            print("URLError " + str(k))
            k += 1
    t2 = time.time()  # stop the timer
    total_time = t2 - t1  # Calculating the total time required to crawl,
    print("Total time taken: " + str(total_time) + " Seconds")
    index += 1

print("\n")
print("Everything downloaded!")
print("\n" + str(error_count) + " ----> Total Errors")
print(error_links)
# ----End of the main program ----#