Update app.py

app.py

@@ -20,13 +20,22 @@ async def stealthy_scraper(url):
     """Fetches HTML content using StealthyFetcher (already async internally)."""
     # Use await if async_fetch is available, otherwise keep .fetch
     html = await stealthy_fetcher.async_fetch(url)  #Corrected to async_fetch
-    return html
+    return html.html_content
 
 
 async def scraper(url):
     """Fetches HTML content using AsyncFetcher."""
     html = await async_fetcher.get(url)  # Use await for async operations
-    return html
+    return html.html_content
+    
+
+async def text_scraper(url):
+    """Fetches HTML content using AsyncFetcher and than extract text."""
+    html = await async_fetcher.get(url)  # Use await for async operations
+    text = html.get_all_text()
+    text = re.sub(r'\n+', ' ', text) 
+    text = re.sub(r'\s+', ' ', text)
+    return text
 
 
 async def convert_html_to_md(html):
@@ -43,12 +52,6 @@ async def convert_html_to_md(html):
     await asyncio.to_thread(os.remove, temp_file_path)
     return x
 
-async def convert_html_to_text(html):
-    """Converts HTML to Text using re."""
-    html = re.sub(r'\n+', ' ', html) 
-    html = re.sub(r'\s+', ' ', html)
-    return html
-
 
 @app.get("/read/{url:path}", response_class=PlainTextResponse)
 async def get_markdown_get(request: Request, url: str):
@@ -60,13 +63,14 @@ async def get_markdown_get(request: Request, url: str):
         if not full_url.startswith(('http://', 'https://')):
             full_url = f"http://{full_url}"
 
-        markdown_output = await convert_html_to_md(await scraper(full_url).html_content)
+        markdown_output = await convert_html_to_md(await scraper(full_url).)
         return PlainTextResponse(markdown_output)
     except Exception as e:
         raise HTTPException(status_code=500, detail=f"Error processing URL: {e}")
+        
 
 @app.get("/read/text/{url:path}", response_class=PlainTextResponse)
-async def get_markdown_get(request: Request, url: str):
+async def get_text_get(request: Request, url: str):
     """Handles GET requests to /read/{url}, returning Markdown content."""
     try:
         full_url = str(request.url)
@@ -75,7 +79,7 @@ async def get_markdown_get(request: Request, url: str):
         if not full_url.startswith(('http://', 'https://')):
             full_url = f"http://{full_url}"
 
-        markdown_output = await convert_html_to_md(await scraper(full_url).get_all_text())
+        markdown_output = await text_scraper(url)
         return PlainTextResponse(markdown_output)
     except Exception as e:
         raise HTTPException(status_code=500, detail=f"Error processing URL: {e}")