Dev official

Backend/AnalysisWorker.py

@@ -0,0 +1,114 @@
+# Backend/AnalysisWorker.py
+from PySide6.QtCore import QObject, Signal
+from PySide6.QtGui import QImage
+import time
+
+from Analysis.SentimentAnalysis import run_sentiment_summary
+from Analysis.WordCloud import WordCloudAnalyzer
+
+class AnalysisWorker(QObject):
+    """
+    Threaded worker to run analysis (sentiment summary + wordcloud) on a list of sentences.
+    Emits progress updates for the splash and returns QImage results.
+    """
+
+    progress_updated = Signal(str)
+    progress_percentage = Signal(int)
+    finished = Signal()
+    sentiment_ready = Signal(QImage)
+    wordcloud_ready = Signal(QImage)
+
+    def __init__(self, sentences: list[str], sentiment_size: tuple = (1600, 520),
+                 wordcloud_size: tuple = (2800, 1680), max_words: int = 200):
+        super().__init__()
+        self.sentences = sentences or []
+        self.sent_w, self.sent_h = sentiment_size
+        self.wc_w, self.wc_h = wordcloud_size
+        self.max_words = max_words
+        self._cancelled = False
+
+    def cancel(self):
+        self._cancelled = True
+
+    def run(self) -> None:
+        try:
+            total_stages = 4
+            stage = 0
+
+            # Stage 1: loading/extract count
+            stage += 1
+            self.progress_updated.emit("Preparing sentences for analysis...")
+            self.progress_percentage.emit(int((stage/total_stages)*100 * 0.02))  # small percent
+
+            sentences = self.sentences
+            n = len(sentences)
+            if self._cancelled:
+                self.progress_updated.emit("Analysis cancelled.")
+                self.finished.emit()
+                return
+
+            # Stage 2: Sentiment (iterate sentences — dynamic progress)
+            stage += 1
+            self.progress_updated.emit("Running sentiment analysis...")
+            # We'll update percent dynamically across this stage (weight: 45%)
+            sentiment_stage_weight = 45
+            base = int(((stage-1)/total_stages) * 100)
+            if n == 0:
+                self.progress_percentage.emit(base + 1)
+            else:
+                # process in micro-batches to allow progress updates
+                batch = max(1, n // 20)
+                processed = 0
+                # build text list chunked — run_sentiment_summary expects sentences list
+                # but it's not incremental; to show progress we compute compound in loop using VADER directly would be needed.
+                # For simplicity and to avoid importing internals, call run_sentiment_summary once but fake granular progress.
+                # Show incremental progress while computing
+                for i in range(0, n, batch):
+                    if self._cancelled:
+                        self.progress_updated.emit("Analysis cancelled.")
+                        self.finished.emit()
+                        return
+                    # small sleep to let UI update if heavy
+                    time.sleep(0.01)
+                    processed += min(batch, n - i)
+                    frac = processed / n
+                    pct = base + int(frac * sentiment_stage_weight)
+                    self.progress_percentage.emit(min(pct, 99))
+
+                # Now compute final sentiment image
+                sentiment_img = run_sentiment_summary(sentences, width=self.sent_w, height=self.sent_h)
+                self.sentiment_ready.emit(sentiment_img)
+
+            # Stage 3: Wordcloud (weight: 45%)
+            stage += 1
+            self.progress_updated.emit("Generating word cloud...")
+            wc_base = int(((stage-1)/total_stages) * 100)
+            # Quick progress ticks while generating
+            # generate_wordcloud is blocking; show small animation ticks before/after
+            for tick in range(3):
+                if self._cancelled:
+                    self.progress_updated.emit("Analysis cancelled.")
+                    self.finished.emit()
+                    return
+                time.sleep(0.05)
+                self.progress_percentage.emit(wc_base + int((tick+1) * (40/3)))
+
+            wc_img = WordCloudAnalyzer(max_words=self.max_words).generate_wordcloud(sentences, width=self.wc_w, height=self.wc_h)
+            self.wordcloud_ready.emit(wc_img)
+            self.progress_percentage.emit(95)
+
+            # Stage 4: Finalizing
+            stage += 1
+            self.progress_updated.emit("Finalizing results...")
+            time.sleep(0.05)
+            self.progress_percentage.emit(100)
+            self.progress_updated.emit("Analysis complete.")
+            self.finished.emit()
+
+        except Exception as e:
+            # best-effort error reporting
+            try:
+                self.progress_updated.emit(f"Analysis error: {str(e)}")
+            except Exception:
+                pass
+            self.finished.emit()

Backend/ScrapeComments.py

@@ -31,30 +31,52 @@ def __init__(self, video_details: Dict[str, List[str]]) -> None:
     def run(self) -> None:
         """
         Executes the comment fetching process.
+        Shows video title / channel name instead of raw IDs when available.
         """
         try:
             total_videos = sum(len(v_list) for v_list in self.video_details.values())
             processed_count = 0
-            
+
             self.progress_updated.emit("Starting comment scrape...")
             self.progress_percentage.emit(0)
 
+            # helper to get title from DB
+            def _get_title(vid, ch):
+                try:
+                    rows = self.fetcher.db.fetch("VIDEO", where="video_id=?", params=(vid,))
+                    if rows:
+                        return rows[0].get("title") or vid
+                except Exception:
+                    pass
+                return vid
+
+            def _get_channel_name(ch):
+                try:
+                    rows = self.fetcher.db.fetch("CHANNEL", where="channel_id=?", params=(ch,))
+                    if rows:
+                        return rows[0].get("channel_name") or str(ch)
+                except Exception:
+                    pass
+                return str(ch)
+
             for channel_id, video_id_list in self.video_details.items():
+                channel_name = _get_channel_name(channel_id)
                 for video_id in video_id_list:
-                    self.progress_updated.emit(f"Fetching comments for {video_id}...")
-
+                    video_title = _get_title(video_id, channel_id)
+                    self.progress_updated.emit(f"Fetching comments for: \"{video_title}\" (channel: {channel_name})")
+
                     # Perform fetch
                     result = self.fetcher._fetch(video_id, channel_id)
-                    
+
                     processed_count += 1
                     percentage = int((processed_count / total_videos) * 100)
                     self.progress_percentage.emit(percentage)
-                    
+
                     if result.get("filepath"):
                         count = result.get("comment_count", 0)
-                        self.progress_updated.emit(f"Saved {count} comments for {video_id}")
+                        self.progress_updated.emit(f"Saved {count} comments for \"{video_title}\"")
                     else:
-                        self.progress_updated.emit(f"Skipped: {video_id} ({result.get('remarks')})")
+                        self.progress_updated.emit(f"Skipped: \"{video_title}\" ({result.get('remarks')})")
 
             self.progress_updated.emit("Comment scraping completed!")
             self.progress_percentage.emit(100)
@@ -66,6 +88,7 @@ def run(self) -> None:
             self.finished.emit()
 
 
+
 class CommentFetcher:
     """
     A class to fetch YouTube video comments with threads using yt-dlp.

Backend/ScrapeTranscription.py

@@ -32,31 +32,49 @@ def __init__(self, video_details: dict[str, list], languages: list = ["en"]) ->
     def run(self) -> None:
         """
         Executes the transcript fetching process.
+        Shows human-friendly names (video title) in progress messages when available.
         """
         try:
             total_videos = sum(len(v_list) for v_list in self.video_details.values())
             processed_count = 0
-            
+
             self.progress_updated.emit("Starting transcript scrape...")
             self.progress_percentage.emit(0)
 
             language_option = ["en"]
 
+            # helper to get title from DB
+            def _get_title(vid, ch):
+                try:
+                    rows = self.fetcher.db.fetch("VIDEO", where="video_id=?", params=(vid,))
+                    if rows:
+                        return rows[0].get("title") or vid
+                except Exception:
+                    pass
+                return vid
+
             for channel_id, video_id_list in self.video_details.items():
+                # try get channel name
+                try:
+                    ch_rows = self.fetcher.db.fetch("CHANNEL", where="channel_id=?", params=(channel_id,))
+                    channel_name = ch_rows[0].get("channel_name") if ch_rows else str(channel_id)
+                except Exception:
+                    channel_name = str(channel_id)
+
                 for video_id in video_id_list:
-                    self.progress_updated.emit(f"Fetching transcript for {video_id}...")
-
+                    video_title = _get_title(video_id, channel_id)
+                    self.progress_updated.emit(f"Fetching transcript for: \"{video_title}\"")
                     # Perform fetch
                     result = self.fetcher._fetch(video_id, channel_id, language_option)
-                    
+
                     processed_count += 1
                     percentage = int((processed_count / total_videos) * 100)
                     self.progress_percentage.emit(percentage)
-                    
+
                     if result.get("filepath"):
-                        self.progress_updated.emit(f"Saved: {video_id}")
+                        self.progress_updated.emit(f"Saved: \"{video_title}\"")
                     else:
-                        self.progress_updated.emit(f"Skipped: {video_id} ({result.get('remarks')})")
+                        self.progress_updated.emit(f"Skipped: \"{video_title}\" ({result.get('remarks')})")
 
             self.progress_updated.emit("Transcript scraping completed!")
             self.progress_percentage.emit(100)