Is there a way I can Download images from any search engine with a code like this?

254 views Asked by At

I tried downloading images from bing to a directory but due to some reason the code just executes and gives me nothing.. not even an error.. I used the user-agent HTTP as well.. but it still doesnt seem to be working.. What should i do?

from bs4 import BeautifulSoup
import requests
from PIL import Image
from io import BytesIO

url = 'https://www.bing.com/search'
search = input("Search for: ")
headers = {'User-Agent': 'Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:80.0) Gecko/20100101 
Firefox/80.0'}
params = {"q": search}
r = requests.get(url, headers=headers, params=params)

soup = BeautifulSoup(r.text, "html.parser")
links = soup.findAll("a", {"class": "thumb"})

for item in links:
     img_obj = requests.get(item.attrs["href"])
     print("Getting", item.attrs["href"])
     title = item.attrs["href"].split("/")[-1]
     img = Image.open(BytesIO(img_obj.content))
     img.save("./scraped_images/" + title, img.format)
1

There are 1 answers

7
MendelG On BEST ANSWER

To get all images, you need to add /images to the link. Here's an example with modifications to your code:

from bs4 import BeautifulSoup
from PIL import Image
from io import BytesIO
import requests
import json

search = input("Search for: ")

url = "https://www.bing.com/images/search"

headers = {
    "User-Agent": "Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:80.0) Gecko/20100101 Firefox/80.0"
}
params = {"q": search, "form": "HDRSC2", "first": "1", "scenario": "ImageBasicHover"}
r = requests.get(url, headers=headers, params=params)

soup = BeautifulSoup(r.text, "html.parser")
links = soup.find_all("div", {"class": "img_cont hoff"})

for data in soup.find_all("a", {"class": "iusc"}):
    json_data = json.loads(data["m"])
    img_link = json_data["murl"]
    img_object = requests.get(img_link, headers=headers)
    title = img_link.split("/")[-1]

    print("Getting: ", img_link)
    print("Title: ", title + "\n")

    img = Image.open(BytesIO(img_object.content))
    img.save("./scraped_images/" + title)