update du projet, xml collection enlevé et méthode fait maison ajouter

data/cover/curl.sh

@@ -0,0 +1,16 @@
+#!/bin/bash
+
+# Download the index page and convert local links to global links
+url="https://www.memo-dg.fr/"
+curl $url > index.html
+
+# Extract the image URLs from the downloaded HTML file
+cat index.html | grep img | grep -Po 'src="\K.*?(?=")' | sed 's/\?.*//' > links.txt
+
+# Download all the images using curl
+while read -r file; do
+    curl -s -O $file
+done < links.txt
+
+# Clean up
+rm index.html links.txt

data/cover/scrape.py

@@ -0,0 +1,39 @@
+import os
+import sys
+import requests
+from bs4 import BeautifulSoup
+from urllib.parse import urljoin, urlparse
+import urllib.request
+
+def main(url):
+    try:
+        response = requests.get(url, headers={"User-Agent": "Mozilla/5.0"})
+        response.raise_for_status()
+    except requests.exceptions.RequestException as e:
+        print(f"Error: {e}")
+        sys.exit(1)
+
+    soup = BeautifulSoup(response.text, 'html.parser')
+    images = soup.find_all('img')
+
+    if not os.path.exists("images"):
+        os.makedirs("images")
+
+    for image in images:
+        img_src = image.get('src')
+        img_url = urljoin(url, img_src)
+        local_filename = urlparse(img_url).path.split('/')[-1]
+
+        try:
+            urllib.request.urlretrieve(img_url, os.path.join("images", local_filename))
+            print(f"Downloaded {img_url}")
+        except Exception as e:
+            print(f"Error downloading {img_url}: {e}")
+
+if __name__ == "__main__":
+    if len(sys.argv) < 2:
+        print("Usage: python script.py <URL>")
+        sys.exit(1)
+
+    url = sys.argv[1]
+    main(url)