I have code for scrap image:
import requests, base64
from bs4 import BeautifulSoup
baseurl = "https://www.google.com/search?q=cat&sxsrf=APq-WBuyx07rsOeGlVQpTsxLt262WbhlfA:1650636332756&source=lnms&tbm=shop&sa=X&ved=2ahUKEwjQr5HC66f3AhXxxzgGHejKC9sQ_AUoAXoECAIQAw&biw=1920&bih=937&dpr=1"
headers = {"User-Agent" : "Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:99.0) Gecko/20100101 Firefox/99.0"}
r_images = requests.get(url=baseurl, headers=headers)
soup_for_image = BeautifulSoup(r_images.text, 'html.parser')
#find product images
productimages = []
product_images = soup_for_image.findAll('img')
for item in product_images:
# print(item['src'])
if "data:image/svg xml" not in item['src']:
productimages.append(item.get('src'))
print(productimages)
It will be fine if there is no header but, if I use request header, the result will be base64 image. So is there any way that I can scrap the image with the request headers?
CodePudding user response:
You can add cookie CONSENT and it works.
Maybe some selectors can change in the future.
import requests, base64
from bs4 import BeautifulSoup
baseurl = "https://www.google.com/search?q=cat&sxsrf=APq-WBuyx07rsOeGlVQpTsxLt262WbhlfA:1650636332756&source=lnms&tbm=shop&sa=X&ved=2ahUKEwjQr5HC66f3AhXxxzgGHejKC9sQ_AUoAXoECAIQAw&biw=1920&bih=937&dpr=1"
headers = {"cookie": "CONSENT=YES cb.20230531-04-p0.en FX 908"}
result = requests.get(url=baseurl, headers=headers)
soup = BeautifulSoup(result.text, 'html.parser')
allProducts = soup.findAll(class_="u30d4")
number = 0
for product in allProducts:
name = product.find(class_="rgHvZc")
if name is not None:
number = 1
print("Product number %d:" % number)
print("Name : " name.text)
productLink = product.find('a')
print("Link: " productLink["href"][7:])
img = product.find('img')
print("Image: " img["src"])
price = product.find(class_="HRLxBb")
print("Price " price.text)
I hope i was able to help you.