Update app.py

app.py

@@ -1,5 +1,6 @@
 import gradio as gr
-from langchain.document_loaders import UnstructuredURLLoader
+# from langchain.document_loaders import UnstructuredURLLoader
+from langchain_community.document_loaders import WebBaseLoader
 import os
 from langchain import PromptTemplate, HuggingFaceHub, LLMChain
 from gtts import gTTS
@@ -12,13 +13,21 @@ api_key = os.getenv("HUGGINGFACE_API_TOKEN")
 
 os.environ['HUGGINGFACEHUB_API_TOKEN']  = api_key
 
-
-def get_summary_from_url(url):
-    loaders = UnstructuredURLLoader(urls=[url])
-    data = loaders.load()
-    question = data[0]
-    
-    template = """{question}"""
+def get_url_text(url_link):
+    try:
+        loader = WebBaseLoader(url_link)
+        loader.requests_per_second = 1
+        docs = loader.aload()
+        extracted_text = ""
+        for page in docs:
+            extracted_text += page.page_content
+        return extracted_text
+    except Exception as e:
+        print(f"Error fetching or processing URL: {e}")
+        return ""
+
+def get_answer(text):
+    template = """{text}"""
     prompt = PromptTemplate(template=template, input_variables=["question"])
     
     llm_chain = LLMChain(prompt=prompt,
@@ -35,7 +44,8 @@ def text_to_speech(text, language='en'):
     return "output.mp3"
 
 def summarize_and_convert_to_audio(url):
-    summary = get_summary_from_url(url)
+    text = get_url_text(url)
+    summary = get_answer(text)
     audio_file = text_to_speech(summary)
     return audio_file