How to Scrape Images from a Website With Python

pip install beautifulsoup4 selenium pandas

pip install Pillow requests

# Import the requests library to send HTTP requests
import requests
for b in results:
# Store the content from the URL to a variable
    image_content = requests.get(b).content

# The io library manages file-related in/out operations.
import io
# Create a byte object out of image_content and store it in the variable image_file
image_file = io.BytesIO(image_content)

# Use Pillow to convert the Python object to an RGB image
from PIL import Image
image = Image.open(image_file).convert("RGB")

# pathlib lets you point to specific directories. Use it to store the images in a folder.
from pathlib import Path
# hashlib allows you to get hashes. Let's use 'sha1' to name the images.
import hashlib
# Set a file_path variable that points to your directory.
# Create a file based on the sha1 hash of 'image_content'.
# Use .hexdigest to convert it into a string.
file_path = Path("/path/to/test", hashlib.sha1(image_content).hexdigest()[:10] + ".png")
image.save(file_path, "PNG", quality=80)

import hashlib
import io
from pathlib import Path
import pandas as pd
import requests
from bs4 import BeautifulSoup
from PIL import Image
from selenium import webdriver

driver = webdriver.Chrome()
driver.get("https://www.ebay.com/sch/i.html?_from=R40&_trksid=p2334524.m570.l1313&_nkw=laptop&_sacat=0&LH_TitleDesc=0&_osacat=0&_odkw=laptop")
driver.execute_script("window.scrollTo(0, document.body.scrollHeight);")
results = []
content = driver.page_source
soup = BeautifulSoup(content)


def gets_url(classes, location, source):
    results = []
    for a in soup.findAll(attrs={"class": classes}):
        name = a.find(location)
        if name not in results:
            results.append(name.get(source))
    return results


driver.quit()

if __name__ == "__main__":
    returned_results = gets_url("s-item__image-wrapper image-treatment", "img", "src")
    for b in returned_results:
        image_content = requests.get(b).content
        image_file = io.BytesIO(image_content)
        image = Image.open(image_file).convert("RGB")
        file_path = Path("/path/to/test", hashlib.sha1(image_content).hexdigest()[:10] + ".png")
        image.save(file_path, "PNG", quality=80)

import io
from pathlib import Path
import hashlib
import pandas as pd
import requests
from bs4 import BeautifulSoup
from PIL import Image
from selenium import webdriver


def get_content_from_url(url):
   driver = webdriver.Chrome()  # Add "executable_path=" if the driver is in a custom directory.
   driver.get(url)
   driver.execute_script("window.scrollTo(0, document.body.scrollHeight);")
   page_content = driver.page_source
   driver.quit()  # You don't need the browser instance for further steps.
   return page_content


def parse_image_urls(content, classes, location, source):
   soup = BeautifulSoup(content)
   results = []
   for a in soup.findAll(attrs={"class": classes}):
       name = a.find(location)
       if name not in results:
           results.append(name.get(source))
   return results


def save_urls_to_csv(image_urls):
   df = pd.DataFrame({"links": image_urls})
   df.to_csv("links.csv", index=False, encoding="utf-8")


def get_and_save_image_to_file(image_url, output_dir):
   response = requests.get(image_url, headers={"User-agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/113.0.0.0 Safari/537.36"})
   image_content = response.content
   image_file = io.BytesIO(image_content)
   image = Image.open(image_file).convert("RGB")
   filename = hashlib.sha1(image_content).hexdigest()[:10] + ".png"
   file_path = output_dir / filename
   image.save(file_path, "PNG", quality=80)


def main():
   url = "https://www.ebay.com/sch/i.html?_from=R40&_trksid=p2334524.m570.l1313&_nkw=laptop&_sacat=0&LH_TitleDesc=0&_osacat=0&_odkw=laptop"
   content = get_content_from_url(url)
   image_urls = parse_image_urls(
       content=content, classes="s-item__image-wrapper image-treatment", location="img", source="src",
   )
   save_urls_to_csv(image_urls)

   for image_url in image_urls:
       get_and_save_image_to_file(
           image_url, output_dir=Path("/path/to/test"),
       )


if __name__ == "__main__":  # Only executes if imported as a main file.
   main()