Update app.py

app.py

@@ -1,41 +1,50 @@
 from transformers import pipeline
 from youtube_transcript_api import YouTubeTranscriptApi
-#from IPython.display import YouTubeVideo
 import streamlit as st 
+import re
 
 def summarize(result):
     summarizer = pipeline('summarization')
     num_iters = int(len(result)/1000)
     summarized_text = []
     for i in range(0, num_iters + 1):
-      start = 0
-      start = i * 1000
-      end = (i + 1) * 1000
-      print("input text \n" + result[start:end])
-      out = summarizer(result[start:end])
-      out = out[0]
-      out = out['summary_text']
-      print("Summarized text\n"+out)
-      summarized_text.append(out)
+        start = 0
+        start = i * 1000
+        end = (i + 1) * 1000
+        print("input text \n" + result[start:end])
+        out = summarizer(result[start:end])
+        out = out[0]
+        out = out['summary_text']
+        print("Summarized text\n"+out)
+        summarized_text.append(out)
     st.write(summarized_text)
 
-def get_transcript(video_id):
-    #youtube_video = "https://www.youtube.com/watch?v=A4OmtyaBHFE"
-    #video_id = youtube_video.split("=")[1]
-    #video_id
-    #st.write(YouTubeVideo(video_id))
-    transcript = YouTubeTranscriptApi.get_transcript(video_id)
-    print(transcript[0:5])
-    
-    result = ""
-    for i in transcript:
-        result += ' ' + i['text']
-    #print(result)
-    print(len(result))
-    st.write(result) 
+def get_transcript(video_link):
+    video_id = extract_video_id(video_link)
+    if video_id:
+        transcript = YouTubeTranscriptApi.get_transcript(video_id)
+        result = ""
+        for i in transcript:
+            result += ' ' + i['text']
+        print(len(result))
+        st.write(result)
+        # If you want to summarize the transcript
+        summarize(result)
+    else:
+        st.write("Invalid YouTube video link")
+
+def extract_video_id(video_link):
+    # Regular expression to extract video ID from YouTube video link
+    regex = r"(?:https:\/\/)?(?:www\.)?(?:youtube\.com\/(?:[^\/\n\s]+\/\S+\/|(?:v|e(?:mbed)?)\/|\S*?[?&]v=)|youtu\.be\/)([a-zA-Z0-9_-]{11})"
+    matches = re.findall(regex, video_link)
+    if matches:
+        return matches[0]
+    else:
+        return None
 
 def main():
-    video_id=st.text_input("enter video id ") 
-    if video_id:
-        get_transcript(video_id)
-main()
+    video_link = st.text_input("Enter YouTube video link:")
+    if video_link:
+        get_transcript(video_link)
+
+main()