Removed string input from console

code/web_scraper_allegro.py

@@ -63,9 +63,7 @@ def get_api_token():
         print("Info: API Token loaded from .env file.")
         return token
     
-    print("Warning: APIFY_TOKEN not found in .env file.")
-    token = input("Please enter your Apify API Token: ").strip()
-    return token
+    return AttributeError("API Token is required but not provided.")
 
 def get_allegro_data(url):
     apify_token = get_api_token()

code/web_scraper_ebay.py

@@ -66,8 +66,8 @@ def get_api_token():
         print("Info: API Token loaded from .env file.")
         return token
     
-    print("Warning: APIFY_TOKEN not found in .env file.")
-    return input("Please enter your Apify API Token: ").strip()
+    return AttributeError("API Token is required but not provided.")
+
 
 def get_ebay_data(url):
     apify_token = get_api_token()

code/web_scraper_olx.py

@@ -1,55 +1,96 @@
-# scrape_olx_offer.py
 import requests
 from bs4 import BeautifulSoup
+import json
 
-def scrape_olx_offer(url: str):
-    """Zwraca dane aukcji bez zapisywania na dysk"""
+
+# --- FUNCTIONS ---
+def sanitize_name(text):
+    """Sanitizes text by removing Polish characters and special symbols for a folder name."""
+    polish_chars = {
+        "ą": "a",
+        "ć": "c",
+        "ę": "e",
+        "ł": "l",
+        "ń": "n",
+        "ó": "o",
+        "ś": "s",
+        "ź": "z",
+        "ż": "z",
+    }
+
+    text = text.lower()
+    result = ""
+
+    for char in text:
+        if char in polish_chars:
+            result += polish_chars[char]
+        elif char.isalnum():
+            result += char
+        else:
+            result += "_"
+
+    # Remove double underscores
+    while "__" in result:
+        result = result.replace("__", "_")
+
+    return result.strip("_")
+
+
+def get_olx_data(url):
+    """Fetches OLX offer data and returns it as a dictionary with title, description, parameters, and image URLs."""
+    # --- CONFIGURATION ---
     headers = {
         "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/115.0.0.0 Safari/537.36"
     }
-    
-    print(f"🔍 OLX: {url}")
+
     response = requests.get(url, headers=headers)
-    
+
     if response.status_code != 200:
-        raise ValueError(f"OLX error: {response.status_code}")
-    
+        return {"error": f"Connection error. Status code: {response.status_code}"}
+
     soup = BeautifulSoup(response.content, "html.parser")
-    
-    # TITLE
+
+    # --- GATHERING DATA ---
+
+    # Title
     title_element = soup.find("h4", class_="css-1au435n")
     title = title_element.get_text().strip() if title_element else "untitled"
-    
-    # DESCRIPTION
+
+    # Description
     description_element = soup.find("div", class_="css-19duwlz")
-    description = description_element.get_text(separator="\n").strip() if description_element else "No description"
-    
-    # PARAMETERS
+    description = (
+        description_element.get_text(separator="\n").strip()
+        if description_element
+        else "No description"
+    )
+
+    # Parameters
     parameter_list = []
-    parameters_container = soup.find("div", attrs={"data-testid": "ad-parameters-container"})
+    parameters_container = soup.find(
+        "div", attrs={"data-testid": "ad-parameters-container"}
+    )
     if parameters_container:
         params = parameters_container.find_all("p", class_="css-13x8d99")
         for p in params:
             parameter_list.append(p.get_text().strip())
-    
-    # IMAGES
+
+    # Image Links
     images = soup.select('img[data-testid^="swiper-image"]')
-    unique_links = set()
-    for img in images:
-        link = img.get("src")
-        if link:
-            unique_links.add(link)
-    
+    unique_links = list(set(img.get("src") for img in images if img.get("src")))
+
+    # --- RETURNING DICTIONARY ---
     return {
-        "platform": "olx",
-        "url": url,
         "title": title,
+        "sanitized_title": sanitize_name(title),
+        "url": url,
         "description": description,
         "parameters": parameter_list,
-        "image_urls": list(unique_links)
+        "image_urls": unique_links,
+        "image_count": len(unique_links),
     }
 
-if __name__ == "__main__":
-    url = input("OLX URL: ")
-    result = scrape_olx_offer(url)
-    print(result)
+
+# --- USAGE ---
+link = input("Enter the OLX offer link: ")
+data = get_olx_data(link)
+print(json.dumps(data, indent=4, ensure_ascii=False))