Lade till requests

.gitignore

@@ -162,3 +162,4 @@ cython_debug/
 
 # Exclude venv from smartassist
 smartassist/smartassist_dev_venv
+.DS_Store

web/download_images_gpt4o.py

@@ -0,0 +1,76 @@
+import os
+import requests
+from bs4 import BeautifulSoup
+from urllib.parse import urljoin, urlparse
+import base64
+import re
+
+def download_image(url, folder_path):
+    if not os.path.isdir(folder_path):
+        os.makedirs(folder_path)
+    
+    try:
+        response = requests.get(url, stream=True)
+        response.raise_for_status()  # Kontrollera om förfrågan lyckades
+    except requests.RequestException as e:
+        print(f"Failed to retrieve image {url}: {e}")
+        return
+
+    filename = os.path.join(folder_path, os.path.basename(urlparse(url).path))
+    with open(filename, 'wb') as file:
+        for chunk in response.iter_content(1024):
+            file.write(chunk)
+    print(f"Downloaded: {filename}")
+
+def save_base64_image(data_url, folder_path, count):
+    if not os.path.isdir(folder_path):
+        os.makedirs(folder_path)
+    
+    match = re.match(r'data:image/(?P<ext>[^;]+);base64,(?P<data>.+)', data_url)
+    if match:
+        ext = match.group('ext')
+        data = match.group('data')
+        img_data = base64.b64decode(data)
+        filename = os.path.join(folder_path, f'image_{count}.{ext}')
+        with open(filename, 'wb') as file:
+            file.write(img_data)
+        print(f"Downloaded: {filename}")
+    else:
+        print(f"Invalid base64 image data: {data_url}")
+
+def download_all_images(html_content, base_url, folder_path):
+    soup = BeautifulSoup(html_content, 'html.parser')
+    img_tags = soup.find_all('img')
+    
+    count = 0
+    for img in img_tags:
+        img_url = img.get('src')
+        if not img_url:
+            continue
+
+        if img_url.startswith(('http://', 'https://')):
+            img_url = urljoin(base_url, img_url)
+            print(f"Attempting to download image: {img_url}")
+            download_image(img_url, folder_path)
+        elif img_url.startswith('data:image/'):
+            print(f"Attempting to save base64 image: {img_url[:30]}...")  # Print only the start of the data URL
+            count += 1
+            save_base64_image(img_url, folder_path, count)
+        else:
+            print(f"Ignoring non-http URL: {img_url}")
+
+def main():
+    url = input("Enter the URL of the webpage: ")
+    folder_path = os.path.expanduser("~/Downloads/downloaded_images")
+    
+    try:
+        response = requests.get(url)
+        response.raise_for_status()  # Kontrollera om förfrågan lyckades
+    except requests.RequestException as e:
+        print(f"Failed to retrieve webpage {url}: {e}")
+        return
+
+    download_all_images(response.content, url, folder_path)
+
+if __name__ == "__main__":
+    main()

web/ladda_hem_bilder.py

@@ -0,0 +1,62 @@
+import os
+import re
+from bs4 import BeautifulSoup
+import requests
+from urllib.parse import urljoin
+import base64
+
+def ladda_ner_bilder(url):
+    # Hämta HTML-sidan
+    svar = requests.get(url)
+    soup = BeautifulSoup(svar.text, 'html.parser')
+
+    # Hitta alla bilder
+    bilder = []
+    for img in soup.find_all('img'):
+        src = img.get('src')
+        if src:
+            bilder.append(src)
+
+    # Hantera inline-bilder i base64
+    INLINE_BILD_MÖNSTER = r'data:image/(.*?);base64,(.*)'
+    matcher = re.compile(INLINE_BILD_MÖNSTER)
+    for match in matcher.finditer(svar.text):
+        bild_typ = match.group(1)
+        bild_data = match.group(2)
+        bilder.append(f"data:{bild_typ};base64,{bild_data}")
+
+    # Ladda ner bilderna
+    bild_katalog = os.path.expanduser("~/Downloads/bilder")
+    if not os.path.exists(bild_katalog):
+        os.makedirs(bild_katalog)
+
+    for bild_url in bilder:
+        if not bild_url.startswith('http'):
+            bild_url = urljoin(url, bild_url)
+
+        if bild_url.startswith('data:'):
+            # Dekodera base64-strängen och spara den som en bild
+            format, data = bild_url.split(';base64,')
+            data = base64.b64decode(data)
+            filnamn = 'inline_' + str(len(bilder)) + '.gif'
+            with open(os.path.join(bild_katalog, filnamn), 'wb') as f:
+                f.write(data)
+        else:
+            svar = requests.get(bild_url)
+            if svar.status_code == 200:
+                filnamn = os.path.basename(bild_url).split('?')[0]
+                with open(os.path.join(bild_katalog, filnamn), 'wb') as f:
+                    f.write(svar.content)
+            print(f"Bilden {filnamn} har laddats ner till {bild_katalog}.")
+
+def main():
+    url = input("Ange URL till sidan från vilken du vill hämta bilder: ")
+    if not url.startswith('http'):
+        url = 'http://' + url
+    try:
+        ladda_ner_bilder(url)
+    except Exception as e:
+        print(f"Fel inträffade: {e}")
+
+if __name__ == "__main__":
+    main()

web/requirements_web.txt

@@ -0,0 +1,2 @@
+BeautifulSoup4
+requests