From 133480a05d7a1840e0d5a59e48d55f73fc70ddcf Mon Sep 17 00:00:00 2001
From: jeffser <jeffrysamuer@gmail.com>
Date: Wed, 25 Dec 2024 19:26:02 -0600
Subject: [PATCH] Removed PyTube dependency and fixed youtube integration

---
 com.jeffser.Alpaca.json | 14 --------------
 src/generic_actions.py  |  4 +++-
 src/window.py           | 22 +++++++---------------
 3 files changed, 10 insertions(+), 30 deletions(-)

diff --git a/com.jeffser.Alpaca.json b/com.jeffser.Alpaca.json
index d3320f8f..41b09060 100644
--- a/com.jeffser.Alpaca.json
+++ b/com.jeffser.Alpaca.json
@@ -99,20 +99,6 @@
 		}
 	    ]
 	},
-	{
-	    "name": "python3-pytube",
-	    "buildsystem": "simple",
-	    "build-commands": [
-		"pip3 install --verbose --exists-action=i --no-index --find-links=\"file://${PWD}\" --prefix=${FLATPAK_DEST} \"pytube\" --no-build-isolation"
-	    ],
-	    "sources": [
-		{
-		    "type": "file",
-		    "url": "https://files.pythonhosted.org/packages/51/64/bcf8632ed2b7a36bbf84a0544885ffa1d0b4bcf25cc0903dba66ec5fdad9/pytube-15.0.0-py3-none-any.whl",
-		    "sha256": "07b9904749e213485780d7eb606e5e5b8e4341aa4dccf699160876da00e12d78"
-		}
-	    ]
-	},
 	{
 	    "name": "python3-youtube-transcript-api",
 	    "buildsystem": "simple",
diff --git a/src/generic_actions.py b/src/generic_actions.py
index 29bbab1a..bafebe08 100644
--- a/src/generic_actions.py
+++ b/src/generic_actions.py
@@ -5,6 +5,7 @@
 
 import os, requests
 from youtube_transcript_api import YouTubeTranscriptApi
+from youtube_transcript_api.formatters import TextFormatter
 from html2text import html2text
 from .internal import cache_dir
 
@@ -40,7 +41,8 @@ def attach_youtube(video_title:str, video_author:str, watch_url:str, video_url:s
     else:
         transcript = YouTubeTranscriptApi.get_transcript(video_id, languages=[caption_name])
 
-    result_text += '\n'.join([t['text'] for t in transcript])
+    result_text += TextFormatter().format_transcript(transcript)
+    #result_text += '\n'.join([t['text'] for t in transcript])
 
     if not os.path.exists(os.path.join(cache_dir, 'tmp/youtube')):
         os.makedirs(os.path.join(cache_dir, 'tmp/youtube'))
diff --git a/src/window.py b/src/window.py
index 7bb4d79b..c1234110 100644
--- a/src/window.py
+++ b/src/window.py
@@ -19,14 +19,13 @@
 """
 Handles the main window
 """
-import json, threading, os, re, base64, gettext, uuid, shutil, logging, time
+import json, threading, os, re, base64, gettext, uuid, shutil, logging, time, requests
 import odf.opendocument as odfopen
 import odf.table as odftable
 from io import BytesIO
 from PIL import Image
 from pypdf import PdfReader
 from datetime import datetime
-from pytube import YouTube
 
 import gi
 gi.require_version('GtkSource', '5')
@@ -875,17 +874,10 @@ def current_chat_actions(self, action, user_data):
 
     def youtube_detected(self, video_url):
         try:
-            tries=0
-            while True:
-                try:
-                    yt = YouTube(video_url)
-                    video_title = yt.title
-                    break
-                except Exception as e:
-                    tries+=1
-                    if tries == 4:
-                        raise Exception(e)
-            transcriptions = generic_actions.get_youtube_transcripts(yt.video_id)
+            response = requests.get('https://noembed.com/embed?url={}'.format(video_url))
+            data = json.loads(response.text)
+
+            transcriptions = generic_actions.get_youtube_transcripts(data['url'].split('=')[1])
             if len(transcriptions) == 0:
                 self.show_toast(_("This video does not have any transcriptions"), self.main_overlay)
                 return
@@ -895,8 +887,8 @@ def youtube_detected(self, video_url):
 
             dialog_widget.simple_dropdown(
                 _('Attach YouTube Video?'),
-                _('{}\n\nPlease select a transcript to include').format(video_title),
-                lambda caption_name, yt=yt, video_url=video_url: generic_actions.attach_youtube(yt.title, yt.author, yt.watch_url, video_url, yt.video_id, caption_name),
+                _('{}\n\nPlease select a transcript to include').format(data['title']),
+                lambda caption_name, data=data, video_url=video_url: generic_actions.attach_youtube(data['title'], data['author_name'], data['url'], video_url, data['url'].split('=')[1], caption_name),
                 transcriptions
             )
         except Exception as e: