Spaces:
Sleeping
Sleeping
Update app.py
#4
by
Muktibhuyan
- opened
app.py
CHANGED
|
@@ -6,11 +6,23 @@ import shutil
|
|
| 6 |
from pathlib import Path
|
| 7 |
import re
|
| 8 |
import uuid
|
|
|
|
|
|
|
|
|
|
| 9 |
session_data = {}
|
| 10 |
|
| 11 |
class YouTubeDownloader:
|
| 12 |
def __init__(self):
|
| 13 |
self.download_dir = tempfile.mkdtemp()
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 14 |
|
| 15 |
def is_valid_youtube_url(self, url):
|
| 16 |
youtube_regex = re.compile(
|
|
@@ -19,214 +31,523 @@ class YouTubeDownloader:
|
|
| 19 |
)
|
| 20 |
return youtube_regex.match(url) is not None
|
| 21 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 22 |
def format_video_info(self, video_info):
|
| 23 |
-
"""
|
| 24 |
if not video_info:
|
| 25 |
return "β No video information available."
|
| 26 |
-
|
| 27 |
-
#
|
| 28 |
duration = video_info.get('duration', 0)
|
| 29 |
duration_str = f"{duration//3600}:{(duration%3600)//60:02d}:{duration%60:02d}" if duration else "Unknown"
|
| 30 |
|
| 31 |
-
# Format upload date
|
| 32 |
upload_date = video_info.get('upload_date', '')
|
| 33 |
-
|
| 34 |
-
|
| 35 |
-
else:
|
| 36 |
-
formatted_date = upload_date or "Unknown"
|
| 37 |
-
|
| 38 |
-
# Format numbers
|
| 39 |
def format_number(num):
|
| 40 |
-
if num
|
|
|
|
|
|
|
|
|
|
|
|
|
| 41 |
return f"{num/1_000_000:.1f}M"
|
| 42 |
elif num >= 1_000:
|
| 43 |
return f"{num/1_000:.1f}K"
|
| 44 |
-
|
| 45 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 46 |
|
| 47 |
-
#
|
| 48 |
-
|
| 49 |
-
|
| 50 |
-
{'='*50}
|
| 51 |
-
|
| 52 |
-
π BASIC INFORMATION:
|
| 53 |
-
β’ Title: {video_info.get('title', 'Unknown')}
|
| 54 |
-
β’ Channel: {video_info.get('channel', 'Unknown')}
|
| 55 |
-
β’ Uploader: {video_info.get('uploader', 'Unknown')}
|
| 56 |
-
β’ Upload Date: {formatted_date}
|
| 57 |
-
β’ Duration: {duration_str}
|
| 58 |
-
|
| 59 |
-
π STATISTICS:
|
| 60 |
-
β’ Views: {format_number(video_info.get('view_count', 0))}
|
| 61 |
-
β’ Likes: {format_number(video_info.get('like_count', 0))}
|
| 62 |
-
β’ Comments: {format_number(video_info.get('comment_count', 0))}
|
| 63 |
-
β’ Channel Followers: {format_number(video_info.get('channel_followers', 0))}
|
| 64 |
-
|
| 65 |
-
π·οΈ CATEGORIES & TAGS:
|
| 66 |
-
β’ Categories: {', '.join(video_info.get('categories', [])) or 'None'}
|
| 67 |
-
β’ Tags: {', '.join(video_info.get('tags', [])[:10]) or 'None'}
|
| 68 |
-
{('β’ More tags...' if len(video_info.get('tags', [])) > 10 else '')}
|
| 69 |
-
|
| 70 |
-
π DESCRIPTION:
|
| 71 |
-
{video_info.get('description', 'No description available')[:500]}
|
| 72 |
-
{'...' if len(video_info.get('description', '')) > 500 else ''}
|
| 73 |
-
|
| 74 |
-
π VIDEO URL:
|
| 75 |
-
{video_info.get('webpage_url', 'Unknown')}
|
| 76 |
-
"""
|
| 77 |
|
| 78 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 79 |
|
| 80 |
-
|
| 81 |
-
|
| 82 |
-
|
|
|
|
| 83 |
|
| 84 |
-
|
| 85 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 86 |
|
| 87 |
-
|
| 88 |
-
|
| 89 |
-
|
| 90 |
-
|
| 91 |
-
|
| 92 |
-
|
| 93 |
-
|
| 94 |
-
ydl_opts['cookiefile'] = cookiefile
|
| 95 |
|
| 96 |
-
|
| 97 |
-
|
| 98 |
-
|
| 99 |
-
|
| 100 |
-
|
| 101 |
-
|
| 102 |
-
|
| 103 |
-
|
| 104 |
-
|
| 105 |
-
|
| 106 |
-
'upload_date': info.get('upload_date', ''),
|
| 107 |
-
'uploader': info.get('uploader', 'Unknown'),
|
| 108 |
-
'channel': info.get('channel', 'Unknown'),
|
| 109 |
-
'channel_followers': info.get('channel_follower_count', 0),
|
| 110 |
-
'tags': info.get('tags', []),
|
| 111 |
-
'categories': info.get('categories', []),
|
| 112 |
-
'thumbnail': info.get('thumbnail', ''),
|
| 113 |
-
'webpage_url': info.get('webpage_url', url)
|
| 114 |
-
}
|
| 115 |
-
progress(1.0, desc="Information retrieved!")
|
| 116 |
-
return video_info, "β
Video information retrieved successfully"
|
| 117 |
-
except yt_dlp.DownloadError as e:
|
| 118 |
-
error_msg = str(e)
|
| 119 |
-
if "Video unavailable" in error_msg:
|
| 120 |
-
return None, "β Video is unavailable or private"
|
| 121 |
-
elif "age-restricted" in error_msg.lower():
|
| 122 |
-
return None, "β Video is age-restricted"
|
| 123 |
-
else:
|
| 124 |
-
return None, f"β Failed to get video info: {error_msg}"
|
| 125 |
-
except Exception as e:
|
| 126 |
-
return None, f"β An unexpected error occurred: {str(e)}"
|
| 127 |
|
| 128 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 129 |
if not url or not url.strip():
|
| 130 |
return None, "β Please enter a YouTube URL"
|
| 131 |
-
|
| 132 |
if not self.is_valid_youtube_url(url):
|
| 133 |
-
return None, "β Invalid YouTube URL
|
| 134 |
-
|
| 135 |
try:
|
| 136 |
-
progress(0.1, desc="Initializing
|
|
|
|
| 137 |
ydl_opts = {
|
| 138 |
-
'format': 'best[ext=mp4]/best',
|
| 139 |
-
'outtmpl': os.path.join(self.download_dir, '%(title)s.%(ext)s'),
|
| 140 |
'noplaylist': True,
|
|
|
|
|
|
|
|
|
|
|
|
|
| 141 |
}
|
| 142 |
-
|
|
|
|
| 143 |
ydl_opts['cookiefile'] = cookiefile
|
| 144 |
-
|
| 145 |
-
|
|
|
|
|
|
|
| 146 |
with yt_dlp.YoutubeDL(ydl_opts) as ydl:
|
| 147 |
-
|
| 148 |
-
|
| 149 |
-
|
| 150 |
-
|
| 151 |
-
|
| 152 |
-
|
| 153 |
-
|
| 154 |
-
|
| 155 |
-
|
| 156 |
-
downloaded_file = downloaded_files[0]
|
| 157 |
-
file_size = downloaded_file.stat().st_size / (1024 * 1024)
|
| 158 |
-
progress(1.0, desc="Download completed!")
|
| 159 |
-
success_message = f"β
Successfully downloaded: {video_title}\n"
|
| 160 |
-
success_message += f"π File size: {file_size:.1f} MB\n"
|
| 161 |
-
success_message += f"β±οΈ Duration: {duration//60}:{duration%60:02d}" if duration else ""
|
| 162 |
-
return str(downloaded_file), success_message
|
| 163 |
-
else:
|
| 164 |
-
return None, "β Download completed but file not found"
|
| 165 |
-
except yt_dlp.DownloadError as e:
|
| 166 |
-
error_msg = str(e)
|
| 167 |
-
if "Video unavailable" in error_msg:
|
| 168 |
-
return None, "β Video is unavailable or private"
|
| 169 |
-
elif "age-restricted" in error_msg.lower():
|
| 170 |
-
return None, "β Video is age-restricted and cannot be downloaded"
|
| 171 |
-
elif "copyright" in error_msg.lower():
|
| 172 |
-
return None, "β Video cannot be downloaded due to copyright restrictions"
|
| 173 |
-
else:
|
| 174 |
-
return None, f"β Download failed: {error_msg}"
|
| 175 |
except Exception as e:
|
| 176 |
-
return None, f"β
|
| 177 |
-
|
| 178 |
-
def cleanup(self):
|
| 179 |
-
try:
|
| 180 |
-
shutil.rmtree(self.download_dir, ignore_errors=True)
|
| 181 |
-
except:
|
| 182 |
-
pass
|
| 183 |
|
|
|
|
| 184 |
downloader = YouTubeDownloader()
|
| 185 |
|
| 186 |
-
def
|
| 187 |
-
|
| 188 |
-
|
| 189 |
-
|
| 190 |
-
|
| 191 |
-
|
| 192 |
-
|
| 193 |
-
|
| 194 |
-
|
| 195 |
-
|
| 196 |
-
|
| 197 |
-
|
| 198 |
-
|
| 199 |
-
|
| 200 |
-
|
| 201 |
-
|
| 202 |
-
|
| 203 |
-
|
| 204 |
-
|
| 205 |
-
|
| 206 |
-
|
| 207 |
-
|
| 208 |
-
success_message = f"{download_message}\n\nVideo downloaded successfully! Click 'Show Analysis Results' to see detailed information."
|
| 209 |
-
return success_message, gr.File(value=file_path, visible=True), gr.Button(visible=True), gr.State(video_info)
|
| 210 |
-
elif file_path:
|
| 211 |
-
return f"{download_message}\n\nVideo downloaded but analysis data unavailable.", gr.File(value=file_path, visible=True), gr.Button(visible=False), gr.State("")
|
| 212 |
-
else:
|
| 213 |
-
return f"β Download failed:\n{download_message}", gr.File(visible=False), gr.Button(visible=False), gr.State(None)
|
| 214 |
-
|
| 215 |
-
def show_analysis(video_info):
|
| 216 |
-
print("[DEBUG] Received session_id:", session_id)
|
| 217 |
-
video_info = session_data.get(session_id)
|
| 218 |
-
if video_info:
|
| 219 |
-
return downloader.format_video_info(video_info), gr.Textbox(visible=True)
|
| 220 |
-
return "β No analysis data available.", gr.Textbox(visible=True)
|
| 221 |
-
|
| 222 |
-
download_btn.click(handle_download, inputs=[url_input, cookies_input], outputs=[status_output, file_output, analysis_btn, video_info_state])
|
| 223 |
-
analysis_btn.click(show_analysis, inputs=[video_info_state], outputs=[analysis_output])
|
| 224 |
-
url_input.submit(handle_download, inputs=[url_input, cookies_input], outputs=[status_output, file_output, analysis_btn, video_info_state])
|
| 225 |
|
| 226 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 227 |
|
| 228 |
if __name__ == "__main__":
|
| 229 |
demo = create_interface()
|
| 230 |
import atexit
|
| 231 |
atexit.register(downloader.cleanup)
|
| 232 |
-
demo.launch(
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6 |
from pathlib import Path
|
| 7 |
import re
|
| 8 |
import uuid
|
| 9 |
+
import json
|
| 10 |
+
from datetime import datetime
|
| 11 |
+
|
| 12 |
session_data = {}
|
| 13 |
|
| 14 |
class YouTubeDownloader:
|
| 15 |
def __init__(self):
|
| 16 |
self.download_dir = tempfile.mkdtemp()
|
| 17 |
+
|
| 18 |
+
def cleanup(self):
|
| 19 |
+
"""Clean up temporary directories and files"""
|
| 20 |
+
try:
|
| 21 |
+
if hasattr(self, 'download_dir') and os.path.exists(self.download_dir):
|
| 22 |
+
shutil.rmtree(self.download_dir)
|
| 23 |
+
print(f"β
Cleaned up temporary directory: {self.download_dir}")
|
| 24 |
+
except Exception as e:
|
| 25 |
+
print(f"β οΈ Warning: Could not clean up temporary directory: {e}")
|
| 26 |
|
| 27 |
def is_valid_youtube_url(self, url):
|
| 28 |
youtube_regex = re.compile(
|
|
|
|
| 31 |
)
|
| 32 |
return youtube_regex.match(url) is not None
|
| 33 |
|
| 34 |
+
def analyze_content_type(self, video_info):
|
| 35 |
+
"""Analyze video content to determine type"""
|
| 36 |
+
title = video_info.get('title', '').lower()
|
| 37 |
+
description = video_info.get('description', '').lower()
|
| 38 |
+
tags = ' '.join(video_info.get('tags', [])).lower()
|
| 39 |
+
|
| 40 |
+
content_indicators = {
|
| 41 |
+
'educational': ['tutorial', 'how to', 'learn', 'guide', 'explained', 'lesson', 'course', 'tips'],
|
| 42 |
+
'promotional': ['ad', 'promo', 'launch', 'brand', 'sponsored', 'commercial', 'product'],
|
| 43 |
+
'entertainment': ['funny', 'comedy', 'challenge', 'reaction', 'prank', 'meme', 'fun'],
|
| 44 |
+
'review': ['review', 'unboxing', 'comparison', 'vs', 'test', 'rating'],
|
| 45 |
+
'vlog': ['vlog', 'daily', 'routine', 'day in', 'life', 'personal'],
|
| 46 |
+
'music': ['music', 'song', 'cover', 'remix', 'beats', 'audio'],
|
| 47 |
+
'news': ['news', 'breaking', 'update', 'report', 'latest', 'current']
|
| 48 |
+
}
|
| 49 |
+
|
| 50 |
+
metadata = f"{title} {description} {tags}"
|
| 51 |
+
|
| 52 |
+
for category, keywords in content_indicators.items():
|
| 53 |
+
if any(keyword in metadata for keyword in keywords):
|
| 54 |
+
return category.title()
|
| 55 |
+
|
| 56 |
+
return "General"
|
| 57 |
+
|
| 58 |
+
def analyze_emotion(self, video_info):
|
| 59 |
+
"""Analyze emotional tone of the video"""
|
| 60 |
+
title = video_info.get('title', '').lower()
|
| 61 |
+
description = video_info.get('description', '').lower()
|
| 62 |
+
|
| 63 |
+
emotion_indicators = {
|
| 64 |
+
'energetic': ['excited', 'amazing', 'incredible', 'wow', 'awesome', 'fantastic', 'energy'],
|
| 65 |
+
'positive': ['happy', 'love', 'great', 'good', 'wonderful', 'perfect', 'best'],
|
| 66 |
+
'calm': ['calm', 'peaceful', 'relaxing', 'soothing', 'gentle', 'quiet'],
|
| 67 |
+
'serious': ['important', 'serious', 'warning', 'critical', 'urgent', 'breaking'],
|
| 68 |
+
'inspirational': ['inspire', 'motivate', 'change', 'transform', 'achieve', 'success']
|
| 69 |
+
}
|
| 70 |
+
|
| 71 |
+
metadata = f"{title} {description}"
|
| 72 |
+
|
| 73 |
+
for emotion, keywords in emotion_indicators.items():
|
| 74 |
+
if any(keyword in metadata for keyword in keywords):
|
| 75 |
+
return emotion.title()
|
| 76 |
+
|
| 77 |
+
return "Neutral"
|
| 78 |
+
|
| 79 |
+
def analyze_music_style(self, video_info):
|
| 80 |
+
"""Analyze background music style"""
|
| 81 |
+
title = video_info.get('title', '').lower()
|
| 82 |
+
description = video_info.get('description', '').lower()
|
| 83 |
+
tags = ' '.join(video_info.get('tags', [])).lower()
|
| 84 |
+
|
| 85 |
+
metadata = f"{title} {description} {tags}"
|
| 86 |
+
|
| 87 |
+
music_styles = {
|
| 88 |
+
'upbeat': ['upbeat', 'energetic', 'fast', 'dance', 'pop', 'electronic', 'rock'],
|
| 89 |
+
'calm': ['calm', 'soft', 'soothing', 'ambient', 'peaceful', 'meditation', 'acoustic'],
|
| 90 |
+
'cinematic': ['cinematic', 'dramatic', 'epic', 'orchestral', 'soundtrack'],
|
| 91 |
+
'lo-fi': ['lo-fi', 'chill', 'study', 'relaxing beats'],
|
| 92 |
+
'classical': ['classical', 'piano', 'orchestra', 'symphony']
|
| 93 |
+
}
|
| 94 |
+
|
| 95 |
+
for style, keywords in music_styles.items():
|
| 96 |
+
if any(keyword in metadata for keyword in keywords):
|
| 97 |
+
return style.title()
|
| 98 |
+
|
| 99 |
+
# Check if it's likely a music video
|
| 100 |
+
if any(word in metadata for word in ['music', 'song', 'audio', 'beats']):
|
| 101 |
+
return "Music Content"
|
| 102 |
+
|
| 103 |
+
return "Background Music Present" if 'music' in metadata else "Minimal/No Music"
|
| 104 |
+
|
| 105 |
+
def detect_influencers(self, video_info):
|
| 106 |
+
"""Enhanced influencer detection"""
|
| 107 |
+
# Expanded list of known personalities
|
| 108 |
+
known_personalities = {
|
| 109 |
+
# Indian Film Industry
|
| 110 |
+
"Kartik Aaryan": ["kartik aaryan", "kartik", "aaryan"],
|
| 111 |
+
"Deepika Padukone": ["deepika padukone", "deepika"],
|
| 112 |
+
"Alia Bhatt": ["alia bhatt", "alia"],
|
| 113 |
+
"Ranveer Singh": ["ranveer singh", "ranveer"],
|
| 114 |
+
"Kiara Advani": ["kiara advani", "kiara"],
|
| 115 |
+
"Janhvi Kapoor": ["janhvi kapoor", "janhvi"],
|
| 116 |
+
"Ananya Panday": ["ananya panday", "ananya"],
|
| 117 |
+
"Salman Khan": ["salman khan", "salman"],
|
| 118 |
+
"Shahrukh Khan": ["shahrukh khan", "srk", "shah rukh"],
|
| 119 |
+
"Amitabh Bachchan": ["amitabh bachchan", "amitabh", "big b"],
|
| 120 |
+
"Katrina Kaif": ["katrina kaif", "katrina"],
|
| 121 |
+
|
| 122 |
+
# Sports Personalities
|
| 123 |
+
"Virat Kohli": ["virat kohli", "virat"],
|
| 124 |
+
"MS Dhoni": ["ms dhoni", "dhoni"],
|
| 125 |
+
"Rohit Sharma": ["rohit sharma", "rohit"],
|
| 126 |
+
|
| 127 |
+
# International Celebrities
|
| 128 |
+
"Taylor Swift": ["taylor swift", "taylor"],
|
| 129 |
+
"Kylie Jenner": ["kylie jenner", "kylie"],
|
| 130 |
+
"Elon Musk": ["elon musk", "elon"],
|
| 131 |
+
|
| 132 |
+
# YouTubers/Content Creators
|
| 133 |
+
"MrBeast": ["mrbeast", "mr beast"],
|
| 134 |
+
"PewDiePie": ["pewdiepie", "felix"],
|
| 135 |
+
"CarryMinati": ["carryminati", "carry", "ajey nagar"],
|
| 136 |
+
"Ashish Chanchlani": ["ashish chanchlani", "ashish"],
|
| 137 |
+
"Bhuvan Bam": ["bhuvan bam", "bb ki vines"],
|
| 138 |
+
"Prajakta Koli": ["prajakta koli", "mostlysane"],
|
| 139 |
+
|
| 140 |
+
# Tech Personalities
|
| 141 |
+
"Sundar Pichai": ["sundar pichai", "sundar"],
|
| 142 |
+
|
| 143 |
+
# Beauty/Fashion Influencers
|
| 144 |
+
"James Charles": ["james charles"],
|
| 145 |
+
"Nikkie Tutorials": ["nikkie tutorials", "nikkietutorials"]
|
| 146 |
+
}
|
| 147 |
+
|
| 148 |
+
# Combine all searchable text
|
| 149 |
+
searchable_text = " ".join([
|
| 150 |
+
video_info.get('title', ''),
|
| 151 |
+
video_info.get('description', ''),
|
| 152 |
+
video_info.get('uploader', ''),
|
| 153 |
+
video_info.get('channel', ''),
|
| 154 |
+
' '.join(video_info.get('tags', []))
|
| 155 |
+
]).lower()
|
| 156 |
+
|
| 157 |
+
detected_personalities = []
|
| 158 |
+
|
| 159 |
+
for personality, aliases in known_personalities.items():
|
| 160 |
+
if any(alias in searchable_text for alias in aliases):
|
| 161 |
+
detected_personalities.append(personality)
|
| 162 |
+
|
| 163 |
+
# Additional indicators
|
| 164 |
+
influencer_indicators = [
|
| 165 |
+
"influencer", "creator", "brand ambassador", "celebrity", "star",
|
| 166 |
+
"featured", "guest", "interview", "collaboration", "collab"
|
| 167 |
+
]
|
| 168 |
+
|
| 169 |
+
has_influencer_indicators = any(indicator in searchable_text for indicator in influencer_indicators)
|
| 170 |
+
|
| 171 |
+
if detected_personalities:
|
| 172 |
+
return f"TRUE - Detected: {', '.join(detected_personalities)}"
|
| 173 |
+
elif has_influencer_indicators:
|
| 174 |
+
return "TRUE - Likely influencer/celebrity present (check video for confirmation)"
|
| 175 |
+
else:
|
| 176 |
+
return "FALSE - No known personalities detected"
|
| 177 |
+
|
| 178 |
+
def generate_scene_breakdown(self, video_info):
|
| 179 |
+
"""Generate enhanced scene-by-scene breakdown"""
|
| 180 |
+
duration = video_info.get('duration', 0)
|
| 181 |
+
title = video_info.get('title', '').lower()
|
| 182 |
+
description = video_info.get('description', '').lower()
|
| 183 |
+
|
| 184 |
+
if not duration:
|
| 185 |
+
return ["**[Duration Unknown]**: Unable to generate timestamped breakdown - video duration not available"]
|
| 186 |
+
|
| 187 |
+
# Determine segment length based on video duration
|
| 188 |
+
if duration <= 30:
|
| 189 |
+
segment_length = 2 # 2-second segments for very short videos
|
| 190 |
+
elif duration <= 60:
|
| 191 |
+
segment_length = 5 # 5-second segments for short videos
|
| 192 |
+
elif duration <= 300: # 5 minutes
|
| 193 |
+
segment_length = 10 # 10-second segments
|
| 194 |
+
elif duration <= 900: # 15 minutes
|
| 195 |
+
segment_length = 15 # 15-second segments
|
| 196 |
+
else:
|
| 197 |
+
segment_length = 30 # 30-second segments for long videos
|
| 198 |
+
|
| 199 |
+
scenes = []
|
| 200 |
+
|
| 201 |
+
# Generate contextual scene descriptions based on video type
|
| 202 |
+
video_type = self.analyze_content_type(video_info).lower()
|
| 203 |
+
|
| 204 |
+
# Scene templates based on video type
|
| 205 |
+
scene_templates = {
|
| 206 |
+
'educational': [
|
| 207 |
+
"Introduction and topic overview",
|
| 208 |
+
"Main content explanation with examples",
|
| 209 |
+
"Detailed demonstration or walkthrough",
|
| 210 |
+
"Key points summary and tips",
|
| 211 |
+
"Conclusion and call-to-action"
|
| 212 |
+
],
|
| 213 |
+
'promotional': [
|
| 214 |
+
"Brand/product introduction",
|
| 215 |
+
"Key features showcase",
|
| 216 |
+
"Benefits and advantages highlight",
|
| 217 |
+
"Social proof or testimonials",
|
| 218 |
+
"Call-to-action and closing"
|
| 219 |
+
],
|
| 220 |
+
'entertainment': [
|
| 221 |
+
"Opening hook and introduction",
|
| 222 |
+
"Main entertainment content",
|
| 223 |
+
"Peak moment or climax",
|
| 224 |
+
"Reaction or commentary",
|
| 225 |
+
"Closing and engagement request"
|
| 226 |
+
],
|
| 227 |
+
'review': [
|
| 228 |
+
"Product/service introduction",
|
| 229 |
+
"First impressions and unboxing",
|
| 230 |
+
"Detailed feature analysis",
|
| 231 |
+
"Pros and cons discussion",
|
| 232 |
+
"Final verdict and recommendation"
|
| 233 |
+
],
|
| 234 |
+
'vlog': [
|
| 235 |
+
"Daily routine introduction",
|
| 236 |
+
"Activity or event coverage",
|
| 237 |
+
"Personal commentary and thoughts",
|
| 238 |
+
"Interaction with others",
|
| 239 |
+
"Day wrap-up and reflection"
|
| 240 |
+
]
|
| 241 |
+
}
|
| 242 |
+
|
| 243 |
+
templates = scene_templates.get(video_type, [
|
| 244 |
+
"Opening sequence",
|
| 245 |
+
"Main content delivery",
|
| 246 |
+
"Supporting information",
|
| 247 |
+
"Engagement moment",
|
| 248 |
+
"Conclusion"
|
| 249 |
+
])
|
| 250 |
+
|
| 251 |
+
segment_count = min(duration // segment_length + 1, len(templates) * 2)
|
| 252 |
+
|
| 253 |
+
for i in range(segment_count):
|
| 254 |
+
start_time = i * segment_length
|
| 255 |
+
end_time = min(start_time + segment_length - 1, duration)
|
| 256 |
+
|
| 257 |
+
# Format timestamps
|
| 258 |
+
start_formatted = f"{start_time//60}:{start_time%60:02d}"
|
| 259 |
+
end_formatted = f"{end_time//60}:{end_time%60:02d}"
|
| 260 |
+
|
| 261 |
+
# Select appropriate template
|
| 262 |
+
template_index = min(i, len(templates) - 1)
|
| 263 |
+
base_description = templates[template_index]
|
| 264 |
+
|
| 265 |
+
# Add contextual details
|
| 266 |
+
if i == 0:
|
| 267 |
+
description = f"{base_description} - Video begins with title card/intro"
|
| 268 |
+
elif i == segment_count - 1:
|
| 269 |
+
description = f"{base_description} - Video concludes with end screen/outro"
|
| 270 |
+
else:
|
| 271 |
+
description = f"{base_description} - Continued content delivery"
|
| 272 |
+
|
| 273 |
+
# Add visual and audio cues
|
| 274 |
+
if 'music' in title or 'song' in title:
|
| 275 |
+
description += " [Music/audio content]"
|
| 276 |
+
elif 'tutorial' in title or 'how to' in title:
|
| 277 |
+
description += " [Instructional content with visual demonstrations]"
|
| 278 |
+
|
| 279 |
+
scenes.append(f"**[{start_formatted}-{end_formatted}]**: {description}")
|
| 280 |
+
|
| 281 |
+
return scenes
|
| 282 |
+
|
| 283 |
def format_video_info(self, video_info):
|
| 284 |
+
"""Enhanced video information formatting"""
|
| 285 |
if not video_info:
|
| 286 |
return "β No video information available."
|
| 287 |
+
|
| 288 |
+
# Basic information processing
|
| 289 |
duration = video_info.get('duration', 0)
|
| 290 |
duration_str = f"{duration//3600}:{(duration%3600)//60:02d}:{duration%60:02d}" if duration else "Unknown"
|
| 291 |
|
|
|
|
| 292 |
upload_date = video_info.get('upload_date', '')
|
| 293 |
+
formatted_date = f"{upload_date[:4]}-{upload_date[4:6]}-{upload_date[6:8]}" if len(upload_date) == 8 else upload_date or "Unknown"
|
| 294 |
+
|
|
|
|
|
|
|
|
|
|
|
|
|
| 295 |
def format_number(num):
|
| 296 |
+
if num is None or num == 0:
|
| 297 |
+
return "0"
|
| 298 |
+
if num >= 1_000_000_000:
|
| 299 |
+
return f"{num/1_000_000_000:.1f}B"
|
| 300 |
+
elif num >= 1_000_000:
|
| 301 |
return f"{num/1_000_000:.1f}M"
|
| 302 |
elif num >= 1_000:
|
| 303 |
return f"{num/1_000:.1f}K"
|
| 304 |
+
return str(num)
|
| 305 |
+
|
| 306 |
+
# Enhanced analysis
|
| 307 |
+
scene_descriptions = self.generate_scene_breakdown(video_info)
|
| 308 |
+
music_style = self.analyze_music_style(video_info)
|
| 309 |
+
influencer_detection = self.detect_influencers(video_info)
|
| 310 |
+
video_type = self.analyze_content_type(video_info)
|
| 311 |
+
emotion = self.analyze_emotion(video_info)
|
| 312 |
+
|
| 313 |
+
# Additional metadata
|
| 314 |
+
thumbnail_url = video_info.get('thumbnail', '')
|
| 315 |
+
language = video_info.get('language', 'Unknown')
|
| 316 |
+
availability = video_info.get('availability', 'public')
|
| 317 |
|
| 318 |
+
# Categories and tags processing
|
| 319 |
+
categories = video_info.get('categories', [])
|
| 320 |
+
tags = video_info.get('tags', [])
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 321 |
|
| 322 |
+
# Engagement metrics
|
| 323 |
+
view_count = video_info.get('view_count', 0)
|
| 324 |
+
like_count = video_info.get('like_count', 0)
|
| 325 |
+
comment_count = video_info.get('comment_count', 0)
|
| 326 |
+
|
| 327 |
+
engagement_rate = 0
|
| 328 |
+
if view_count > 0 and like_count is not None:
|
| 329 |
+
engagement_rate = (like_count / view_count) * 100
|
| 330 |
|
| 331 |
+
# Generate comprehensive report
|
| 332 |
+
report = f"""
|
| 333 |
+
π¬ COMPREHENSIVE VIDEO ANALYSIS REPORT
|
| 334 |
+
{'='*60}
|
| 335 |
|
| 336 |
+
π BASIC INFORMATION
|
| 337 |
+
{'β'*30}
|
| 338 |
+
πΉ **Title:** {video_info.get('title', 'Unknown')}
|
| 339 |
+
πΊ **Channel:** {video_info.get('channel', 'Unknown')}
|
| 340 |
+
π€ **Uploader:** {video_info.get('uploader', 'Unknown')}
|
| 341 |
+
π
**Upload Date:** {formatted_date}
|
| 342 |
+
β±οΈ **Duration:** {duration_str}
|
| 343 |
+
π **Language:** {language}
|
| 344 |
+
π **Availability:** {availability.title()}
|
| 345 |
|
| 346 |
+
π PERFORMANCE METRICS
|
| 347 |
+
{'β'*30}
|
| 348 |
+
π **Views:** {format_number(view_count)}
|
| 349 |
+
π **Likes:** {format_number(like_count)}
|
| 350 |
+
π¬ **Comments:** {format_number(comment_count)}
|
| 351 |
+
π₯ **Channel Subscribers:** {format_number(video_info.get('channel_followers', 0))}
|
| 352 |
+
π **Engagement Rate:** {engagement_rate:.2f}%
|
|
|
|
| 353 |
|
| 354 |
+
π·οΈ CONTENT CLASSIFICATION
|
| 355 |
+
{'β'*30}
|
| 356 |
+
π **Categories:** {', '.join(categories) if categories else 'None specified'}
|
| 357 |
+
π **Primary Tags:** {', '.join(tags[:8]) if tags else 'None specified'}
|
| 358 |
+
{('π **Additional Tags:** ' + ', '.join(tags[8:16]) + ('...' if len(tags) > 16 else '')) if len(tags) > 8 else ''}
|
| 359 |
+
|
| 360 |
+
π VIDEO DESCRIPTION
|
| 361 |
+
{'β'*30}
|
| 362 |
+
{video_info.get('description', 'No description available')[:800]}
|
| 363 |
+
{'...\n[Description truncated - Full description available in original video]' if len(video_info.get('description', '')) > 800 else ''}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 364 |
|
| 365 |
+
π¬ DETAILED SCENE-BY-SCENE BREAKDOWN
|
| 366 |
+
{'β'*40}
|
| 367 |
+
{chr(10).join(scene_descriptions)}
|
| 368 |
+
|
| 369 |
+
π΅ **Background Music Style:** {music_style}
|
| 370 |
+
|
| 371 |
+
π€ **Influencer Present:** {influencer_detection}
|
| 372 |
+
|
| 373 |
+
π₯ **Video Type:** {video_type}
|
| 374 |
+
|
| 375 |
+
π **Overall Emotion:** {emotion}
|
| 376 |
+
|
| 377 |
+
π± TECHNICAL DETAILS
|
| 378 |
+
{'β'*30}
|
| 379 |
+
π **Video URL:** {video_info.get('webpage_url', 'Unknown')}
|
| 380 |
+
πΌοΈ **Thumbnail:** {thumbnail_url if thumbnail_url else 'Not available'}
|
| 381 |
+
π± **Video ID:** {video_info.get('id', 'Unknown')}
|
| 382 |
+
|
| 383 |
+
β‘ QUICK INSIGHTS
|
| 384 |
+
{'β'*30}
|
| 385 |
+
β’ **Content Quality:** {'High' if view_count > 100000 else 'Medium' if view_count > 10000 else 'Growing'}
|
| 386 |
+
β’ **Audience Engagement:** {'High' if engagement_rate > 5 else 'Medium' if engagement_rate > 1 else 'Low'}
|
| 387 |
+
β’ **Viral Potential:** {'High' if view_count > 1000000 and engagement_rate > 3 else 'Medium' if view_count > 100000 else 'Standard'}
|
| 388 |
+
β’ **Content Freshness:** {'Recent' if upload_date and upload_date >= '20240101' else 'Older Content'}
|
| 389 |
+
|
| 390 |
+
{'='*60}
|
| 391 |
+
π Analysis completed at: {datetime.now().strftime('%Y-%m-%d %H:%M:%S')}
|
| 392 |
+
"""
|
| 393 |
+
return report.strip()
|
| 394 |
+
|
| 395 |
+
def get_video_info(self, url, progress=gr.Progress(), cookiefile=None):
|
| 396 |
+
"""Extract video information with enhanced error handling"""
|
| 397 |
if not url or not url.strip():
|
| 398 |
return None, "β Please enter a YouTube URL"
|
| 399 |
+
|
| 400 |
if not self.is_valid_youtube_url(url):
|
| 401 |
+
return None, "β Invalid YouTube URL format"
|
| 402 |
+
|
| 403 |
try:
|
| 404 |
+
progress(0.1, desc="Initializing YouTube extractor...")
|
| 405 |
+
|
| 406 |
ydl_opts = {
|
|
|
|
|
|
|
| 407 |
'noplaylist': True,
|
| 408 |
+
'extract_flat': False,
|
| 409 |
+
'writesubtitles': False,
|
| 410 |
+
'writeautomaticsub': False,
|
| 411 |
+
'ignoreerrors': True,
|
| 412 |
}
|
| 413 |
+
|
| 414 |
+
if cookiefile and os.path.exists(cookiefile):
|
| 415 |
ydl_opts['cookiefile'] = cookiefile
|
| 416 |
+
progress(0.3, desc="Loading cookies for authentication...")
|
| 417 |
+
|
| 418 |
+
progress(0.5, desc="Extracting video metadata...")
|
| 419 |
+
|
| 420 |
with yt_dlp.YoutubeDL(ydl_opts) as ydl:
|
| 421 |
+
info = ydl.extract_info(url, download=False)
|
| 422 |
+
|
| 423 |
+
progress(0.9, desc="Processing video information...")
|
| 424 |
+
progress(1.0, desc="β
Analysis complete!")
|
| 425 |
+
|
| 426 |
+
return info, "β
Video information extracted successfully"
|
| 427 |
+
|
| 428 |
+
except yt_dlp.DownloadError as e:
|
| 429 |
+
return None, f"β YouTube Download Error: {str(e)}"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 430 |
except Exception as e:
|
| 431 |
+
return None, f"β Unexpected Error: {str(e)}"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 432 |
|
| 433 |
+
# Initialize global downloader
|
| 434 |
downloader = YouTubeDownloader()
|
| 435 |
|
| 436 |
+
def analyze_with_cookies(url, cookies_file, progress=gr.Progress()):
|
| 437 |
+
"""Main analysis function with progress tracking"""
|
| 438 |
+
try:
|
| 439 |
+
progress(0.05, desc="Starting analysis...")
|
| 440 |
+
|
| 441 |
+
cookiefile = None
|
| 442 |
+
if cookies_file and os.path.exists(cookies_file):
|
| 443 |
+
cookiefile = cookies_file
|
| 444 |
+
progress(0.1, desc="Cookies file loaded successfully")
|
| 445 |
+
|
| 446 |
+
info, msg = downloader.get_video_info(url, progress=progress, cookiefile=cookiefile)
|
| 447 |
+
|
| 448 |
+
if info:
|
| 449 |
+
progress(0.95, desc="Generating comprehensive report...")
|
| 450 |
+
formatted_info = downloader.format_video_info(info)
|
| 451 |
+
progress(1.0, desc="β
Complete!")
|
| 452 |
+
return formatted_info
|
| 453 |
+
else:
|
| 454 |
+
return f"β Analysis Failed: {msg}"
|
| 455 |
+
|
| 456 |
+
except Exception as e:
|
| 457 |
+
return f"β System Error: {str(e)}"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 458 |
|
| 459 |
+
def create_interface():
|
| 460 |
+
"""Create and configure the Gradio interface"""
|
| 461 |
+
with gr.Blocks(
|
| 462 |
+
theme=gr.themes.Soft(),
|
| 463 |
+
title="π₯ YouTube Video Analyzer Pro",
|
| 464 |
+
css="""
|
| 465 |
+
.gradio-container {
|
| 466 |
+
max-width: 1200px !important;
|
| 467 |
+
}
|
| 468 |
+
.main-header {
|
| 469 |
+
text-align: center;
|
| 470 |
+
background: linear-gradient(90deg, #ff6b6b, #4ecdc4);
|
| 471 |
+
-webkit-background-clip: text;
|
| 472 |
+
-webkit-text-fill-color: transparent;
|
| 473 |
+
font-size: 2.5em;
|
| 474 |
+
font-weight: bold;
|
| 475 |
+
margin-bottom: 20px;
|
| 476 |
+
}
|
| 477 |
+
.description-text {
|
| 478 |
+
text-align: center;
|
| 479 |
+
font-size: 1.1em;
|
| 480 |
+
color: #666;
|
| 481 |
+
margin-bottom: 30px;
|
| 482 |
+
}
|
| 483 |
+
"""
|
| 484 |
+
) as interface:
|
| 485 |
+
|
| 486 |
+
gr.HTML("""
|
| 487 |
+
<div class="main-header">
|
| 488 |
+
π₯ YouTube Video Analyzer Pro
|
| 489 |
+
</div>
|
| 490 |
+
<div class="description-text">
|
| 491 |
+
Get comprehensive analysis of any YouTube video with detailed scene breakdowns,
|
| 492 |
+
influencer detection, emotion analysis, and performance metrics.
|
| 493 |
+
Upload cookies.txt to access age-restricted or private videos.
|
| 494 |
+
</div>
|
| 495 |
+
""")
|
| 496 |
+
|
| 497 |
+
with gr.Row():
|
| 498 |
+
with gr.Column(scale=2):
|
| 499 |
+
url_input = gr.Textbox(
|
| 500 |
+
label="π YouTube URL",
|
| 501 |
+
placeholder="Paste your YouTube video URL here...",
|
| 502 |
+
lines=1
|
| 503 |
+
)
|
| 504 |
+
|
| 505 |
+
with gr.Column(scale=1):
|
| 506 |
+
cookies_input = gr.File(
|
| 507 |
+
label="πͺ Upload cookies.txt (Optional)",
|
| 508 |
+
file_types=[".txt"],
|
| 509 |
+
type="filepath"
|
| 510 |
+
)
|
| 511 |
+
|
| 512 |
+
analyze_btn = gr.Button(
|
| 513 |
+
"π Analyze Video",
|
| 514 |
+
variant="primary",
|
| 515 |
+
size="lg"
|
| 516 |
+
)
|
| 517 |
+
|
| 518 |
+
output = gr.Textbox(
|
| 519 |
+
label="π Comprehensive Analysis Report",
|
| 520 |
+
lines=35,
|
| 521 |
+
max_lines=50,
|
| 522 |
+
show_copy_button=True
|
| 523 |
+
)
|
| 524 |
+
|
| 525 |
+
analyze_btn.click(
|
| 526 |
+
fn=analyze_with_cookies,
|
| 527 |
+
inputs=[url_input, cookies_input],
|
| 528 |
+
outputs=output,
|
| 529 |
+
show_progress=True
|
| 530 |
+
)
|
| 531 |
+
|
| 532 |
+
# Add examples
|
| 533 |
+
gr.Examples(
|
| 534 |
+
examples=[
|
| 535 |
+
["https://www.youtube.com/watch?v=dQw4w9WgXcQ"],
|
| 536 |
+
["https://youtu.be/jNQXAC9IVRw"],
|
| 537 |
+
],
|
| 538 |
+
inputs=url_input,
|
| 539 |
+
label="π― Try these examples:"
|
| 540 |
+
)
|
| 541 |
+
|
| 542 |
+
return interface
|
| 543 |
|
| 544 |
if __name__ == "__main__":
|
| 545 |
demo = create_interface()
|
| 546 |
import atexit
|
| 547 |
atexit.register(downloader.cleanup)
|
| 548 |
+
demo.launch(
|
| 549 |
+
server_name="0.0.0.0",
|
| 550 |
+
server_port=7860,
|
| 551 |
+
share=False,
|
| 552 |
+
show_error=True
|
| 553 |
+
)
|