Create app.py

app.py

@@ -0,0 +1,173 @@
+import cv2
+import pytesseract
+import numpy as np
+from dataclasses import dataclass
+from typing import List
+
+# -----------------------------
+# CONFIGURATION
+# -----------------------------
+
+OCR_LANG_MAP = {
+    "english": "eng",
+    "japanese": "jpn",
+    "korean": "kor",
+    "chinese_simplified": "chi_sim",
+    "chinese_traditional": "chi_tra",
+    "thai": "tha"
+}
+
+FRAME_SAMPLE_RATE = 1  # OCR every N frames (1 = every frame)
+TEXT_STABILITY_FRAMES = 3  # frames needed to confirm subtitle change
+
+# -----------------------------
+# DATA STRUCTURES
+# -----------------------------
+
+@dataclass
+class SubtitleLine:
+    text: str
+    start_time: float
+    end_time: float
+    status: str  # entered | active | exited
+
+
+# -----------------------------
+# UTILITY FUNCTIONS
+# -----------------------------
+
+def sec_to_srt_time(seconds: float) -> str:
+    ms = int((seconds % 1) * 1000)
+    s = int(seconds) % 60
+    m = (int(seconds) // 60) % 60
+    h = int(seconds) // 3600
+    return f"{h:02}:{m:02}:{s:02},{ms:03}"
+
+
+def clean_text(text: str) -> str:
+    return text.strip().replace("\n", " ")
+
+
+# -----------------------------
+# OCR ENGINE
+# -----------------------------
+
+def ocr_image(image, lang_code):
+    gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
+    gray = cv2.threshold(gray, 150, 255, cv2.THRESH_BINARY)[1]
+
+    config = "--psm 6"
+    text = pytesseract.image_to_string(gray, lang=lang_code, config=config)
+    return clean_text(text)
+
+
+# -----------------------------
+# MAIN VIDEO OCR FUNCTION
+# -----------------------------
+
+def extract_subtitles(
+    video_path: str,
+    x: int, y: int, w: int, h: int,
+    start_time: float,
+    end_time: float,
+    language: str
+) -> List[SubtitleLine]:
+
+    cap = cv2.VideoCapture(video_path)
+    fps = cap.get(cv2.CAP_PROP_FPS)
+
+    start_frame = int(start_time * fps)
+    end_frame = int(end_time * fps)
+
+    cap.set(cv2.CAP_PROP_POS_FRAMES, start_frame)
+
+    lang_code = OCR_LANG_MAP[language]
+
+    subtitles = []
+    last_text = ""
+    stable_count = 0
+    active_sub = None
+
+    frame_idx = start_frame
+
+    while cap.isOpened() and frame_idx <= end_frame:
+        ret, frame = cap.read()
+        if not ret:
+            break
+
+        if frame_idx % FRAME_SAMPLE_RATE != 0:
+            frame_idx += 1
+            continue
+
+        crop = frame[y:y+h, x:x+w]
+        text = ocr_image(crop, lang_code)
+
+        current_time = frame_idx / fps
+
+        if text and text != last_text:
+            stable_count += 1
+        else:
+            stable_count = 0
+
+        if stable_count >= TEXT_STABILITY_FRAMES:
+            # Exit previous subtitle
+            if active_sub:
+                active_sub.end_time = current_time
+                active_sub.status = "exited"
+                subtitles.append(active_sub)
+
+            # Enter new subtitle
+            active_sub = SubtitleLine(
+                text=text,
+                start_time=current_time,
+                end_time=current_time,
+                status="entered"
+            )
+            last_text = text
+            stable_count = 0
+
+        if active_sub:
+            active_sub.status = "active"
+            active_sub.end_time = current_time
+
+        frame_idx += 1
+
+    # Close last subtitle
+    if active_sub:
+        active_sub.status = "exited"
+        subtitles.append(active_sub)
+
+    cap.release()
+    return subtitles
+
+
+# -----------------------------
+# EXPORT SRT
+# -----------------------------
+
+def export_srt(subtitles: List[SubtitleLine], output_path: str):
+    with open(output_path, "w", encoding="utf-8") as f:
+        for i, sub in enumerate(subtitles, 1):
+            f.write(f"{i}\n")
+            f.write(
+                f"{sec_to_srt_time(sub.start_time)} --> "
+                f"{sec_to_srt_time(sub.end_time)}\n"
+            )
+            f.write(f"{sub.text}\n\n")
+
+
+# -----------------------------
+# EXAMPLE USAGE
+# -----------------------------
+
+if __name__ == "__main__":
+    subs = extract_subtitles(
+        video_path="input.mp4",
+        x=200, y=400, w=800, h=150,      # subtitle box
+        start_time=10.0,
+        end_time=120.0,
+        language="chinese_simplified"
+    )
+
+    export_srt(subs, "output.srt")
+    print("✅ Subtitle extraction completed.")