File size: 2,188 Bytes
29e530e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7c2a9df
 
 
29e530e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
import cv2
import requests
import tempfile
import os
from urllib.parse import urlparse, parse_qs
import yt_dlp

class VideoParser:
    def __init__(self):
        self.temp_dir = tempfile.mkdtemp()
    
    def download_youtube_video(self, url: str) -> str:
        """Download YouTube video and return local path"""
        ydl_opts = {
            'format': 'best[height<=720]',
            'outtmpl': os.path.join(self.temp_dir, '%(title)s.%(ext)s'),
            'quiet': True,
            'cookiesfrombrowser': ('chrome',),
            'extractor_args': {'youtube': {'skip': ['dash', 'hls']}}
        }
        
        with yt_dlp.YoutubeDL(ydl_opts) as ydl:
            info = ydl.extract_info(url, download=True)
            return ydl.prepare_filename(info)
    
    def analyze_video_frames(self, video_path: str, sample_rate: int = 30):
        """Analyze video frames for object detection/counting"""
        cap = cv2.VideoCapture(video_path)
        frame_count = 0
        results = []
        
        while cap.isOpened():
            ret, frame = cap.read()
            if not ret:
                break
                
            if frame_count % sample_rate == 0:
                # Basic frame analysis - you'd integrate with object detection here
                results.append({
                    'frame': frame_count,
                    'timestamp': frame_count / cap.get(cv2.CAP_PROP_FPS),
                    'frame_data': frame
                })
            
            frame_count += 1
        
        cap.release()
        return results
    
    def extract_audio(self, video_path: str) -> str:
        """Extract audio from video for speech analysis"""
        audio_path = video_path.rsplit('.', 1)[0] + '.wav'
        
        # Use ffmpeg to extract audio
        import subprocess
        subprocess.run([
            'ffmpeg', '-i', video_path, '-vn', '-acodec', 'pcm_s16le', 
            '-ar', '16000', '-ac', '1', audio_path, '-y'
        ], capture_output=True)
        
        return audio_path
    
    def cleanup(self):
        """Clean up temporary files"""
        import shutil
        shutil.rmtree(self.temp_dir, ignore_errors=True)