To scrape thumbnail, original size images, you need to scrape data from the <script> tags using regex.
Code and full example in the online IDE that scrapes and downloads Google Images:
import requests, lxml, re, json
from bs4 import BeautifulSoup
headers = {
"User-Agent":
"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.102 Safari/537.36 Edge/18.19582"
}
params = {
"q": "batman wallpaper", # query
"tbm": "isch",
"hl": "en", # language
"ijn": "0", # batch of 100 images
}
html = requests.get("https://www.google.com/search", params=params, headers=headers)
soup = BeautifulSoup(html.text, 'lxml')
def get_images_data():
print('\nGoogle Images Metadata:')
for google_image in soup.select('.isv-r.PNCib.MSM1fd.BUooTd'):
title = google_image.select_one('.VFACy.kGQAp.sMi44c.lNHeqe.WGvvNb')['title']
source = google_image.select_one('.fxgdke').text
link = google_image.select_one('.VFACy.kGQAp.sMi44c.lNHeqe.WGvvNb')['href']
print(f'{title}\n{source}\n{link}\n')
# this steps could be refactored to a more compact
all_script_tags = soup.select('script')
# # https://regex101.com/r/48UZhY/4
matched_images_data = ''.join(re.findall(r"AF_initDataCallback\(([^<]+)\);", str(all_script_tags)))
# https://kodlogs.com/34776/json-decoder-jsondecodeerror-expecting-property-name-enclosed-in-double-quotes
# if you try to json.loads() without json.dumps it will throw an error:
# "Expecting property name enclosed in double quotes"
matched_images_data_fix = json.dumps(matched_images_data)
matched_images_data_json = json.loads(matched_images_data_fix)
# https://regex101.com/r/pdZOnW/3
matched_google_image_data = re.findall(r'\[\"GRID_STATE0\",null,\[\[1,\[0,\".*?\",(.*),\"All\",', matched_images_data_json)
# https://regex101.com/r/NnRg27/1
matched_google_images_thumbnails = ', '.join(
re.findall(r'\[\"(https\:\/\/encrypted-tbn0\.gstatic\.com\/images\?.*?)\",\d+,\d+\]',
str(matched_google_image_data))).split(', ')
print('Google Image Thumbnails:') # in order
for fixed_google_image_thumbnail in matched_google_images_thumbnails:
# https://stackoverflow.com/a/4004439/15164646 comment by Frédéric Hamidi
google_image_thumbnail_not_fixed = bytes(fixed_google_image_thumbnail, 'ascii').decode('unicode-escape')
# after first decoding, Unicode characters are still present. After the second iteration, they were decoded.
google_image_thumbnail = bytes(google_image_thumbnail_not_fixed, 'ascii').decode('unicode-escape')
print(google_image_thumbnail)
# removing previously matched thumbnails for easier full resolution image matches.
removed_matched_google_images_thumbnails = re.sub(
r'\[\"(https\:\/\/encrypted-tbn0\.gstatic\.com\/images\?.*?)\",\d+,\d+\]', '', str(matched_google_image_data))
# https://regex101.com/r/fXjfb1/4
# https://stackoverflow.com/a/19821774/15164646
matched_google_full_resolution_images = re.findall(r"(?:'|,),\[\"(https:|http.*?)\",\d+,\d+\]",
removed_matched_google_images_thumbnails)
print('\nFull Resolution Images:') # in order
for index, fixed_full_res_image in enumerate(matched_google_full_resolution_images):
# https://stackoverflow.com/a/4004439/15164646 comment by Frédéric Hamidi
original_size_img_not_fixed = bytes(fixed_full_res_image, 'ascii').decode('unicode-escape')
original_size_img = bytes(original_size_img_not_fixed, 'ascii').decode('unicode-escape')
print(original_size_img)
-----------------
'''
Google Images Metadata:
Batman's Throne by Mizuri Official on Artstation | Batman artwork, Batman wallpaper, Batman
pinterest.com
https://www.pinterest.com/pin/682436149771063635/
..
Google Image Thumbnails:
https://encrypted-tbn0.gstatic.com/images?q=tbn:ANd9GcROCc-723eFmX7pigzuvsbIa9sCRIorG1TZMOa9KjFlDhgjrVd1B2AsW8dbAvU2MCjpAAM&usqp=CAU
https://encrypted-tbn0.gstatic.com/images?q=tbn:ANd9GcRi4CcR3vRBPGg_4JsE4hb_rni5mzD1zKkwztbrxcZrhBrSUH-cxLdwwI08MB0yDFa1z8E&usqp=CAU
https://encrypted-tbn0.gstatic.com/images?q=tbn:ANd9GcQ1iAgOw8uW2jmmLtZQdnWYT6sP5h1-QR4SyVZxLxNZOELr90NbN5X8ChgVH3P9Unc3OD4&usqp=CAU
...
Full Resolution Images:
https://i.pinimg.com/originals/cf/f8/20/cff820cb3ea56f6b09a8fea0c33f8cb2.jpg
https://cdn.wallpapersafari.com/87/73/rbEyqd.jpg
https://wallpaperaccess.com/full/197277.jpg
...
'''
Alternatively, you can achieve the same thing by using Google Images API from SerpApi. It's a paid API with a free plan.
The difference in your case is that you only need to iterate over structured JSON and get the data you want rather than doing everything from scratch and maintain it over time.
import os, json # json for pretty output
from serpapi import GoogleSearch
def get_google_images():
params = {
"api_key": os.getenv("API_KEY"),
"engine": "google",
"q": "batman wallpaper",
"tbm": "isch"
}
search = GoogleSearch(params)
results = search.get_dict()
print(json.dumps(results['images_results'], indent=2, ensure_ascii=False))
------------
'''
[
{
"position": 90,
"thumbnail": "https://encrypted-tbn0.gstatic.com/images?q=tbn:ANd9GcQ2sBG4WzQCO_z4z3XyJsjZiT4gwhr46mT00Q&usqp=CAU",
"source": "wallpapers-clan.com",
"title": "Batman Wallpaper for iPhone & Android - Wallpapers Clan",
"link": "https://wallpapers-clan.com/wallpapers/batman-dark-purple/",
"original": "https://wallpapers-clan.com/wp-content/uploads/2021/05/batman-dark-purple-wallpaper-scaled.jpg",
"is_product": false
}
]
'''
P.S - I wrote a more in-depth blog post about how to scrape Google Images.
Disclaimer, I work for SerpApi.
