Created
August 14, 2019 08:49
-
-
Save r-chris/5bbcdc3b330d174cec4d1608e1d0f930 to your computer and use it in GitHub Desktop.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
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 |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment