Google image search

demo.py

# Python 3.7
import asyncio
import json
import os
import re

import aiofiles
from aiohttp import ClientSession, ClientTimeout


async def http_query(url, load_cb):
    user_agent = "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/43.0.2357.134 Safari/537.36"

    async with ClientSession(headers={"User-Agent": user_agent}, timeout=ClientTimeout(total=60)) as session:
        try:
            async with session.get(url) as response:
                return await load_cb(response)
        except Exception as e:
            print("GET error: '{}'".format(str(e)))


async def http_read_bytes(url):
    return await http_query(url, lambda response: response.read())


async def http_save(url, path):
    try:
        data = await http_read_bytes(url)

        if data:
            async with aiofiles.open(path, "wb") as f:
                await f.write(data)
    except:
        pass


async def http_read_text(url):
    return await http_query(url, lambda response: response.text())


async def save_images(query, name_prefix, save_path=""):
    search_url = f"https://www.google.com/search?q={query}&source=lnms&tbm=isch"
    page = await http_read_text(search_url)

    return asyncio.gather(*[
        http_save(
            json.loads(f"\"{url}\""),
            os.path.join(save_path, f"{name_prefix}_{idx+1}.jpg")
        )
        for idx, url in enumerate(re.findall("\"ou\":\"(.*?)\"", page))
    ])


async def main():
    await asyncio.gather(*[
        await save_images(query, query, "images")
        for query in ["arachnid", "spider", "scorpion", "scorpion+arachnid"]
    ])


if __name__ == '__main__':
    loop = asyncio.get_event_loop()
    loop.run_until_complete(main())

python27.py

from bs4 import BeautifulSoup
import requests
import re
import urllib2
import os
import cookielib
import json

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


query = raw_input("query image")# you can change the query for the image  here
image_type="ActiOn"
query= query.split()
query='+'.join(query)
url="https://www.google.co.in/search?q="+query+"&source=lnms&tbm=isch"
print url
#add the directory for your image here
DIR="Pictures"
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))

print  "there are total" , len(ActualImages),"images"

if not os.path.exists(DIR):
            os.mkdir(DIR)
DIR = os.path.join(DIR, query.split()[0])

if not os.path.exists(DIR):
            os.mkdir(DIR)
###print images
for i , (img , Type) in enumerate( ActualImages):
    try:
        req = urllib2.Request(img, headers={'User-Agent' : header})
        raw_img = urllib2.urlopen(req).read()

        cntr = len([i for i in os.listdir(DIR) if image_type in i]) + 1
        print cntr
        if len(Type)==0:
            f = open(os.path.join(DIR , image_type + "_"+ str(cntr)+".jpg"), 'wb')
        else :
            f = open(os.path.join(DIR , image_type + "_"+ str(cntr)+"."+Type), 'wb')


        f.write(raw_img)
        f.close()
    except Exception as e:
        print "could not load : "+img
        print e