Web Scraping for Fun: Building Your Own GIF Scraper

pip install requests beautifulsoup4

import requests

url = "http://example.com/gifs" # Replace with a real URL if you're experimenting!

try:
    # Send an HTTP GET request to the URL
    response = requests.get(url)

    # Check if the request was successful (status code 200 means OK)
    if response.status_code == 200:
        print(f"Successfully fetched content from {url}")
        # The content of the web page is in response.text
        html_content = response.text
        # print(html_content[:500]) # Print first 500 characters to peek
    else:
        print(f"Failed to fetch content. Status code: {response.status_code}")

except requests.exceptions.RequestException as e:
    print(f"An error occurred: {e}")

from bs4 import BeautifulSoup

if 'html_content' in locals(): # Check if html_content exists
    # Create a BeautifulSoup object
    # 'html.parser' is a common and robust parser
    soup = BeautifulSoup(html_content, 'html.parser')
    print("HTML content parsed successfully.")
else:
    print("No HTML content to parse. Please run Step 1 first.")

if 'soup' in locals():
    gif_urls = []
    # Find all <img> tags in the HTML
    img_tags = soup.find_all('img')

    for img in img_tags:
        # Get the 'src' attribute of each image tag
        src = img.get('src')
        if src: # Check if src attribute exists
            # Check if the URL ends with '.gif' (case-insensitive)
            if src.lower().endswith('.gif'):
                # Some URLs might be relative (e.g., /images/foo.gif)
                # For simplicity, we'll assume absolute URLs or handle them later.
                # If it's a relative URL, you'd need to combine it with the base URL.
                if src.startswith('http'): # Ensure it's a full URL
                    gif_urls.append(src)
                else:
                    # Basic relative URL handling (might need more robust logic for complex sites)
                    base_url = url.split('/')[0] + '//' + url.split('/')[2]
                    gif_urls.append(f"{base_url}{src}")


    if gif_urls:
        print(f"Found {len(gif_urls)} GIF URLs:")
        for gif_url in gif_urls:
            print(f"- {gif_url}")
    else:
        print("No GIF URLs found on this page.")
else:
    print("No soup object. Please run Step 2 first.")

import os

if 'gif_urls' in locals() and gif_urls:
    download_folder = "downloaded_gifs"
    # Create the folder if it doesn't exist
    if not os.path.exists(download_folder):
        os.makedirs(download_folder)
        print(f"Created folder: {download_folder}")

    print(f"Starting to download {len(gif_urls)} GIFs...")
    for i, gif_url in enumerate(gif_urls):
        try:
            gif_response = requests.get(gif_url, stream=True) # stream=True for large files
            if gif_response.status_code == 200:
                # Extract filename from URL (or create a unique one)
                filename = os.path.join(download_folder, f"gif_{i+1}_{os.path.basename(gif_url).split('?')[0]}")
                # Ensure filename is unique and doesn't contain invalid characters
                filename = "".join([c for c in filename if c.isalnum() or c in (' ', '.', '_')]).rstrip()
                if not filename.lower().endswith('.gif'):
                    filename += '.gif'

                with open(filename, 'wb') as f:
                    for chunk in gif_response.iter_content(chunk_size=8192): # Download in chunks
                        f.write(chunk)
                print(f"Downloaded: {filename}")
            else:
                print(f"Failed to download {gif_url}. Status code: {gif_response.status_code}")
        except requests.exceptions.RequestException as e:
            print(f"Error downloading {gif_url}: {e}")
        except Exception as e:
            print(f"An unexpected error occurred for {gif_url}: {e}")

    print("GIF download process completed!")
else:
    print("No GIF URLs to download. Please ensure previous steps ran successfully.")

import requests
from bs4 import BeautifulSoup
import os

def scrape_gifs(url_to_scrape, download_folder="downloaded_gifs"):
    """
    Scrapes a given URL for GIF images and downloads them.
    """
    print(f"Starting GIF scraper for: {url_to_scrape}")

    # --- Step 1: Fetch the Web Page ---
    try:
        response = requests.get(url_to_scrape, timeout=10) # Added a timeout
        if response.status_code == 200:
            print("Successfully fetched content.")
            html_content = response.text
        else:
            print(f"Failed to fetch content. Status code: {response.status_code}")
            return
    except requests.exceptions.RequestException as e:
        print(f"An error occurred during fetching: {e}")
        return

    # --- Step 2: Parsing the HTML Content ---
    soup = BeautifulSoup(html_content, 'html.parser')
    print("HTML content parsed successfully.")

    # --- Step 3: Finding GIF Links ---
    gif_urls = []
    img_tags = soup.find_all('img')

    for img in img_tags:
        src = img.get('src')
        if src and src.lower().endswith('.gif'):
            # Basic check for absolute vs. relative URLs
            if src.startswith('http'):
                gif_urls.append(src)
            else:
                # Construct absolute URL for relative paths
                # This is a simplified approach and might need refinement for complex sites
                base_url_parts = url_to_scrape.split('/')
                base_domain = base_url_parts[0] + '//' + base_url_parts[2]
                if src.startswith('/'): # Root relative path
                    gif_urls.append(f"{base_domain}{src}")
                else: # Other relative paths (e.g., 'images/foo.gif' on current level)
                    # More advanced logic needed for robustness
                    gif_urls.append(f"{os.path.dirname(url_to_scrape)}/{src}")


    if not gif_urls:
        print("No GIF URLs found on this page.")
        return

    print(f"Found {len(gif_urls)} GIF URLs.")

    # --- Step 4: Downloading the GIFs ---
    if not os.path.exists(download_folder):
        os.makedirs(download_folder)
        print(f"Created folder: {download_folder}")

    print(f"Starting to download {len(gif_urls)} GIFs...")
    for i, gif_url in enumerate(gif_urls):
        try:
            gif_response = requests.get(gif_url, stream=True, timeout=10) # Added timeout
            if gif_response.status_code == 200:
                filename = os.path.join(download_folder, f"gif_{i+1}_{os.path.basename(gif_url).split('?')[0]}")
                # Clean filename to avoid issues with OS path restrictions
                filename = "".join([c for c in filename if c.isalnum() or c in (' ', '.', '_', '-')]).rstrip()
                if not filename.lower().endswith('.gif'):
                    filename += '.gif'

                # Ensure filename is not empty or too generic if URL parsing fails
                if len(filename) < 10 or "gif_" not in filename:
                    filename = os.path.join(download_folder, f"gif_download_{i+1}.gif")


                with open(filename, 'wb') as f:
                    for chunk in gif_response.iter_content(chunk_size=8192):
                        f.write(chunk)
                print(f"Downloaded: {filename}")
            else:
                print(f"Failed to download {gif_url}. Status code: {gif_response.status_code}")
        except requests.exceptions.RequestException as e:
            print(f"Error downloading {gif_url}: {e}")
        except Exception as e:
            print(f"An unexpected error occurred for {gif_url}: {e}")

    print("GIF download process completed!")

if __name__ == "__main__":
    # IMPORTANT: Replace this with a real URL you have permission to scrape!
    # For demonstration, you might want to create a simple HTML file locally
    # and point to it using a 'file:///' URL, or use a known public domain image site.
    target_url = "http://example.com/gifs" # CHANGE THIS!
    scrape_gifs(target_url)