To scrape the full-res image URL with requests and beautifulsoup you need to scrape data from the page source code via regex.
Find all tags:
soup.select('script')
Match images data via regex:
matched_images_data = ''.join(re.findall(r"AF_initDataCallback\(([^<]+)\);", str(all_script_tags)))
Match desired images (full res size) via regex from JSON string:
matched_google_full_resolution_images = re.findall(r"(?:'|,),\[\"(https:|http.*?)\",\d+,\d+\]",
matched_images_data)
Extract and decode them using bytes() and decode():
for fixed_full_res_image in matched_google_full_resolution_images:
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')
If you need to save them, you have two easy options via urllib.request.urlretrieve or requests:
To save images via urllib.request.urlretrieve(url, filename) (more in-depth):
import urllib.request
# often times it will throw 404 error, to avoid it we need to pass user-agent
opener=urllib.request.build_opener()
opener.addheaders=[('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')]
urllib.request.install_opener(opener)
urllib.request.urlretrieve(original_size_img, f'LOCAL_FOLDER_NAME/YOUR_IMAGE_NAME.jpg') # you can skip folder path and it will save them in current working directory
To save images via requests (code taken from this answer):
import requests
url = "YOUR_IMG.jpg"
response = requests.get(url)
if response.status_code == 200:
with open("/YOUR/PATH/TO_IMAGE/sample_img.jpg", 'wb') as f:
f.write(response.content)
Code to scrape and download full-res images, and full example in the online IDE:
import requests, lxml, re, json, urllib.request
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": "pexels cat",
"tbm": "isch",
"hl": "en",
"ijn": "0",
}
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('\nDownloading Google Full 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)
# ------------------------------------------------
# Download original images
# print(f'Downloading {index} image...')
opener=urllib.request.build_opener()
opener.addheaders=[('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')]
urllib.request.install_opener(opener)
urllib.request.urlretrieve(original_size_img, f'Images/original_size_img_{index}.jpg')
get_images_data()
-------------
'''
Google Images Metadata:
9,000+ Best Cat Photos · 100% Free Download · Pexels Stock Photos
pexels.com
https://www.pexels.com/search/cat/
...
Google Image Thumbnails:
https://encrypted-tbn0.gstatic.com/images?q=tbn:ANd9GcR2cZsuRkkLWXOIsl9BZzbeaCcI0qav7nenDvvqi-YSm4nVJZYyljRsJZv6N5vS8hMNU_w&usqp=CAU
...
Full Resolution Images:
https://images.pexels.com/photos/1170986/pexels-photo-1170986.jpeg?cs=srgb&dl=pexels-evg-culture-1170986.jpg&fm=jpg
https://images.pexels.com/photos/3777622/pexels-photo-3777622.jpeg?auto=compress&cs=tinysrgb&dpr=1&w=500
...
'''
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 don't have to deal with regex to match and extract needed data from the source code of the page, instead, you only need to iterate over structured JSON and get what you want.
Code to integrate:
import os, urllib.request, json # json for pretty output
from serpapi import GoogleSearch
def get_google_images():
params = {
"api_key": os.getenv("API_KEY"),
"engine": "google",
"q": "pexels cat",
"tbm": "isch"
}
search = GoogleSearch(params)
results = search.get_dict()
# print(json.dumps(results['suggested_searches'], indent=2, ensure_ascii=False))
print(json.dumps(results['images_results'], indent=2, ensure_ascii=False))
# -----------------------
# Downloading images
for index, image in enumerate(results['images_results']):
# print(f'Downloading {index} image...')
opener=urllib.request.build_opener()
opener.addheaders=[('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')]
urllib.request.install_opener(opener)
urllib.request.urlretrieve(image['original'], f'SerpApi_Images/original_size_img_{index}.jpg')
get_google_images()
---------------
'''
[
...
{
"position": 100, # img number
"thumbnail": "https://encrypted-tbn0.gstatic.com/images?q=tbn:ANd9GcRR1FCGhFsr_qZoxPvQBDjVn17e_8bA5PB8mg&usqp=CAU",
"source": "pexels.com",
"title": "Close-up of Cat · Free Stock Photo",
"link": "https://www.pexels.com/photo/close-up-of-cat-320014/",
"original": "https://images.pexels.com/photos/2612982/pexels-photo-2612982.jpeg?auto=compress&cs=tinysrgb&dpr=1&w=500",
"is_product": false
}
]
'''
P.S - I wrote a bit more in-depth blog post about how to scrape Google Images.
Disclaimer, I work for SerpApi.
