From 8a1ba3c32f12e3fc4921a65be043d692e14eb586 Mon Sep 17 00:00:00 2001
From: AKmahim <mdmahimhossen134@gmail.com>
Date: Mon, 10 Feb 2025 01:56:33 +0600
Subject: [PATCH] added new program to download all image from a website url

---
 .gitignore                        |  4 ++-
 download-website-image/.gitignore |  1 +
 download-website-image/app.py     | 52 +++++++++++++++++++++++++++++++
 3 files changed, 56 insertions(+), 1 deletion(-)
 create mode 100644 download-website-image/.gitignore
 create mode 100644 download-website-image/app.py

diff --git a/.gitignore b/.gitignore
index 16580d9..95167dd 100644
--- a/.gitignore
+++ b/.gitignore
@@ -1,4 +1,6 @@
 *.csv
 *.xlsx
 *.json
-*.env
\ No newline at end of file
+*.env
+env
+
diff --git a/download-website-image/.gitignore b/download-website-image/.gitignore
new file mode 100644
index 0000000..c291c09
--- /dev/null
+++ b/download-website-image/.gitignore
@@ -0,0 +1 @@
+images
diff --git a/download-website-image/app.py b/download-website-image/app.py
new file mode 100644
index 0000000..0f694c9
--- /dev/null
+++ b/download-website-image/app.py
@@ -0,0 +1,52 @@
+import os
+import requests
+from bs4 import BeautifulSoup
+from urllib.parse import urljoin, urlparse
+
+def download_images(url, folder="images"):
+    # Create folder if it doesn't exist
+    os.makedirs(folder, exist_ok=True)
+
+    # Get page content
+    response = requests.get(url)
+    if response.status_code != 200:
+        print(f"Failed to retrieve URL: {url}")
+        return
+    
+    # Parse HTML
+    soup = BeautifulSoup(response.text, "html.parser")
+    
+    # Find all image tags
+    img_tags = soup.find_all("img")
+    if not img_tags:
+        print("No images found on the page.")
+        return
+    
+    for img in img_tags:
+        img_url = img.get("src")
+        if not img_url:
+            continue
+        
+        # Convert relative URLs to absolute
+        img_url = urljoin(url, img_url)
+        
+        # Get image filename
+        parsed_url = urlparse(img_url)
+        img_name = os.path.basename(parsed_url.path)
+
+        if not img_name:
+            continue
+        
+        # Download image
+        img_data = requests.get(img_url).content
+        img_path = os.path.join(folder, img_name)
+
+        # Save image
+        with open(img_path, "wb") as f:
+            f.write(img_data)
+        
+        print(f"Downloaded: {img_name}")
+
+# Example usage
+website_url = "https://themeholy.com/html/agenxe/demo/index.html"  # Replace with your target URL
+download_images(website_url)