Spaces:
Sleeping
Sleeping
Update app.py
Browse files
app.py
CHANGED
|
@@ -134,8 +134,6 @@ from collections import Counter
|
|
| 134 |
from googleapiclient.discovery import build
|
| 135 |
|
| 136 |
|
| 137 |
-
YOUTUBE_API_KEY = "AIzaSyD_SDF4lC3vpHVAMnBOcN2ZCTz7dRjUc98" # Replace with your actual API key
|
| 138 |
-
|
| 139 |
def extract_video_id(url):
|
| 140 |
match = re.search(r"(?:v=|\/)([0-9A-Za-z_-]{11})", url)
|
| 141 |
return match.group(1) if match else None
|
|
@@ -166,14 +164,10 @@ def extract_subtitle_info(text):
|
|
| 166 |
words = text.split()
|
| 167 |
common_words = Counter(words).most_common(10)
|
| 168 |
key_topics = ", ".join([word for word, count in common_words])
|
| 169 |
-
info = {
|
| 170 |
-
"key_topics": key_topics,
|
| 171 |
-
"sentence_count": len(sentences),
|
| 172 |
-
"word_count": len(words),
|
| 173 |
-
}
|
| 174 |
return info
|
| 175 |
except Exception as e:
|
| 176 |
-
return
|
| 177 |
|
| 178 |
def get_recommendations(keywords, max_results=5):
|
| 179 |
if not keywords:
|
|
@@ -207,12 +201,11 @@ def process_youtube_video(url, keywords):
|
|
| 207 |
thumbnail = None
|
| 208 |
summary = "No transcript available"
|
| 209 |
sentiment_label = "N/A"
|
| 210 |
-
subtitle_info = {}
|
| 211 |
recommendations = ""
|
| 212 |
|
| 213 |
video_id = extract_video_id(url)
|
| 214 |
if not video_id:
|
| 215 |
-
return None, "Invalid YouTube URL", "N/A",
|
| 216 |
|
| 217 |
thumbnail = f"https://img.youtube.com/vi/{video_id}/maxresdefault.jpg"
|
| 218 |
|
|
@@ -229,7 +222,6 @@ def process_youtube_video(url, keywords):
|
|
| 229 |
raise ValueError("Transcript is empty")
|
| 230 |
|
| 231 |
cleaned_text = clean_text_for_analysis(text)
|
| 232 |
-
subtitle_info = extract_subtitle_info(cleaned_text)
|
| 233 |
|
| 234 |
sentiment = TextBlob(cleaned_text).sentiment
|
| 235 |
sentiment_label = f"{'Positive' if sentiment.polarity > 0 else 'Negative' if sentiment.polarity < 0 else 'Neutral'} ({sentiment.polarity:.2f})"
|
|
@@ -244,13 +236,38 @@ def process_youtube_video(url, keywords):
|
|
| 244 |
if keywords.strip():
|
| 245 |
recommendations = get_recommendations(keywords)
|
| 246 |
|
| 247 |
-
return thumbnail, summary, sentiment_label,
|
| 248 |
|
| 249 |
except Exception as e:
|
| 250 |
-
return None, f"Error: {str(e)}", "N/A",
|
| 251 |
-
|
| 252 |
-
|
| 253 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 254 |
|
| 255 |
# Gradio Interface
|
| 256 |
with gr.Blocks(theme=gr.themes.Soft()) as app:
|
|
@@ -396,5 +413,4 @@ with gr.Blocks(theme=gr.themes.Soft()) as app:
|
|
| 396 |
)
|
| 397 |
|
| 398 |
if __name__ == "__main__":
|
| 399 |
-
app.launch()
|
| 400 |
-
|
|
|
|
| 134 |
from googleapiclient.discovery import build
|
| 135 |
|
| 136 |
|
|
|
|
|
|
|
| 137 |
def extract_video_id(url):
|
| 138 |
match = re.search(r"(?:v=|\/)([0-9A-Za-z_-]{11})", url)
|
| 139 |
return match.group(1) if match else None
|
|
|
|
| 164 |
words = text.split()
|
| 165 |
common_words = Counter(words).most_common(10)
|
| 166 |
key_topics = ", ".join([word for word, count in common_words])
|
| 167 |
+
info = f"Key topics discussed: {key_topics}. \nNumber of sentences: {len(sentences)}. \nTotal words: {len(words)}."
|
|
|
|
|
|
|
|
|
|
|
|
|
| 168 |
return info
|
| 169 |
except Exception as e:
|
| 170 |
+
return f"Error extracting subtitle information: {str(e)}"
|
| 171 |
|
| 172 |
def get_recommendations(keywords, max_results=5):
|
| 173 |
if not keywords:
|
|
|
|
| 201 |
thumbnail = None
|
| 202 |
summary = "No transcript available"
|
| 203 |
sentiment_label = "N/A"
|
|
|
|
| 204 |
recommendations = ""
|
| 205 |
|
| 206 |
video_id = extract_video_id(url)
|
| 207 |
if not video_id:
|
| 208 |
+
return None, "Invalid YouTube URL", "N/A", "", ""
|
| 209 |
|
| 210 |
thumbnail = f"https://img.youtube.com/vi/{video_id}/maxresdefault.jpg"
|
| 211 |
|
|
|
|
| 222 |
raise ValueError("Transcript is empty")
|
| 223 |
|
| 224 |
cleaned_text = clean_text_for_analysis(text)
|
|
|
|
| 225 |
|
| 226 |
sentiment = TextBlob(cleaned_text).sentiment
|
| 227 |
sentiment_label = f"{'Positive' if sentiment.polarity > 0 else 'Negative' if sentiment.polarity < 0 else 'Neutral'} ({sentiment.polarity:.2f})"
|
|
|
|
| 236 |
if keywords.strip():
|
| 237 |
recommendations = get_recommendations(keywords)
|
| 238 |
|
| 239 |
+
return thumbnail, summary, sentiment_label, recommendations
|
| 240 |
|
| 241 |
except Exception as e:
|
| 242 |
+
return None, f"Error: {str(e)}", "N/A", ""
|
| 243 |
+
|
| 244 |
+
|
| 245 |
+
# def get_recommendations(keywords, max_results=5):
|
| 246 |
+
# if not keywords:
|
| 247 |
+
# return "Please provide search keywords"
|
| 248 |
+
# try:
|
| 249 |
+
# response = requests.get(
|
| 250 |
+
# "https://www.googleapis.com/youtube/v3/search",
|
| 251 |
+
# params={
|
| 252 |
+
# "part": "snippet",
|
| 253 |
+
# "q": f"educational {keywords}",
|
| 254 |
+
# "type": "video",
|
| 255 |
+
# "maxResults": max_results,
|
| 256 |
+
# "relevanceLanguage": "en",
|
| 257 |
+
# "key": YOUTUBE_API_KEY
|
| 258 |
+
# }
|
| 259 |
+
# ).json()
|
| 260 |
+
|
| 261 |
+
# results = []
|
| 262 |
+
# for item in response.get("items", []):
|
| 263 |
+
# title = item["snippet"]["title"]
|
| 264 |
+
# channel = item["snippet"]["channelTitle"]
|
| 265 |
+
# video_id = item["id"]["videoId"]
|
| 266 |
+
# results.append(f"📺 {title}\n👤 {channel}\n🔗 https://youtube.com/watch?v={video_id}\n")
|
| 267 |
+
|
| 268 |
+
# return "\n".join(results) if results else "No recommendations found"
|
| 269 |
+
# except Exception as e:
|
| 270 |
+
# return f"Error: {str(e)}"
|
| 271 |
|
| 272 |
# Gradio Interface
|
| 273 |
with gr.Blocks(theme=gr.themes.Soft()) as app:
|
|
|
|
| 413 |
)
|
| 414 |
|
| 415 |
if __name__ == "__main__":
|
| 416 |
+
app.launch()
|
|
|