Update Milestone5API.py

Milestone5API.py

@@ -1,48 +1,48 @@
-import streamlit as st
-import subprocess
+from pytube import YouTube
+from youtube_transcript_api import YouTubeTranscriptApi
+import re
+import os
 
-def install_libraries():
+def download_video_transcript(video_url):
     try:
-        subprocess.check_call(['pip', 'install', 'pytube'])
-        subprocess.check_call(['pip', 'install', 'youtube_transcript_api'])
-        print("Libraries installed successfully!")
-    except subprocess.CalledProcessError as e:
-        print("Error during installation:", e)
+        video_id = re.search(r"(?<=v=)[\w-]+", video_url)
+        if video_id:
+            video_id = video_id.group()
+            yt = YouTube(video_url)
+            stream = yt.streams.get_highest_resolution()
 
-install_libraries()
+            print(f'Downloading {yt.title}...')
+            modified_title = yt.title.replace(" ", "_")
+            download_path = 'CS370_Milestone5/videos'  # Updated path to CS370_Milestone5 repository
+            captions_path = 'CS370_Milestone5/captions'  # Updated path to CS370_Milestone5 repository
 
-def main():
-    # Importing after ensuring dependencies are installed
-    import Milestone5API
-    
-    # Title 
-    st.title("Translate YouTube Video to French")
-    
-    url = st.text_input("Enter YouTube Video URL")
-    captions_list = []  # Initialize empty list for captions
-    
-    if url:
-        captions = Milestone5API.download_video_transcript(url)
-        if captions:
-            # Parse captions from the API response
-            for line in captions.split("\n"):
-                if line.strip():
-                    timestamp, text = line.split(" ", 1)
-                    captions_list.append({"Timestamp": timestamp, "Original": text})
-        else:
-            st.write("Provided URL did not contain captions")
-    
-        start_index = st.session_state.get('start_index', 0)
-        end_index = start_index + 6
+            # Create directories if they don't exist
+            os.makedirs(download_path, exist_ok=True)
+            os.makedirs(captions_path, exist_ok=True)
+
+            video_file = f'{download_path}/{modified_title}.mp4'
+            stream.download(output_path=download_path, filename=modified_title + '.mp4')
+            print('Download completed!')
+
+            transcript_list = YouTubeTranscriptApi.list_transcripts(video_id)
+            transcript = transcript_list.find_generated_transcript(['en']).fetch()
 
-        st.write(
-            "<link rel='stylesheet' href='styles.css'>", unsafe_allow_html=True
-        )
-        st.write(
-            "<table><tr><th class='timestamp'>Timestamp</th><th class='original'>Original</th></tr>",
-            unsafe_allow_html=True,
-        )
-        
-        for i in range(start_index, min(end_index, len(captions_list))):
-            st.write(
-                f"<tr><td class=
+            captions = ""
+            for i, line in enumerate(transcript):
+                start_time = line['start']
+                formatted_time = f"{int(start_time // 60):02d}:{int(start_time % 60):02d}"
+                captions += f"{formatted_time} {line['text']}\n"
+
+            with open(f'{captions_path}/{modified_title}.txt', 'w', encoding='utf-8') as file:
+                file.write(captions)
+            
+            # Delete video file after captions are saved
+            os.remove(video_file)
+            
+            return captions
+        else:
+            print("Video ID not found in URL.")
+            return None
+    except Exception as e:
+        print("Error:", e)
+        return None