Spaces:
Running
Running
Commit
·
4cd8c66
1
Parent(s):
116ad44
no yout
Browse files- link_processor.py +35 -54
link_processor.py
CHANGED
@@ -1,9 +1,11 @@
|
|
1 |
from pathlib import Path
|
2 |
import yt_dlp
|
|
|
3 |
import streamlit as st
|
|
|
|
|
4 |
import re
|
5 |
import os
|
6 |
-
from random import choice
|
7 |
|
8 |
|
9 |
class LinkDownloader:
|
@@ -12,78 +14,57 @@ class LinkDownloader:
|
|
12 |
self.output_dir.mkdir(parents=True, exist_ok=True)
|
13 |
|
14 |
def sanitize_filename(self, title):
|
|
|
|
|
15 |
clean_name = re.sub(r'[^a-zA-Z0-9.]', '_', title)
|
|
|
16 |
if len(clean_name) > 50:
|
17 |
clean_name = clean_name[:50]
|
18 |
return clean_name
|
19 |
|
20 |
def download_from_url(self, url):
|
|
|
21 |
try:
|
|
|
22 |
temp_filename = 'downloaded_video.%(ext)s'
|
23 |
temp_filepath = str(self.output_dir / temp_filename)
|
24 |
|
25 |
-
#
|
26 |
-
user_agents = [
|
27 |
-
'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36',
|
28 |
-
'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/92.0.4515.107 Safari/537.36',
|
29 |
-
'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/90.0.4430.212 Safari/537.36'
|
30 |
-
]
|
31 |
-
|
32 |
-
# Configure yt-dlp options with robust settings
|
33 |
ydl_opts = {
|
34 |
-
'format': '
|
35 |
'outtmpl': temp_filepath,
|
36 |
-
'quiet':
|
37 |
-
'no_warnings':
|
38 |
-
'extract_audio':
|
39 |
-
'postprocessors': [{
|
40 |
-
'key': 'FFmpegExtractAudio',
|
41 |
-
'preferredcodec': 'mp3',
|
42 |
-
}],
|
43 |
-
# Add robust options
|
44 |
-
'nocheckcertificate': True,
|
45 |
-
'user_agent': choice(user_agents),
|
46 |
-
'referer': 'https://www.youtube.com/',
|
47 |
-
'sleep_interval': 1, # Add small delay between requests
|
48 |
-
'max_sleep_interval': 5,
|
49 |
-
'socket_timeout': 30,
|
50 |
-
'retries': 10, # Increase retry attempts
|
51 |
-
'ignoreerrors': True,
|
52 |
-
'geo_bypass': True,
|
53 |
-
'geo_bypass_country': 'US'
|
54 |
}
|
55 |
|
56 |
-
|
57 |
-
|
58 |
-
|
59 |
-
info = ydl.extract_info(url, download=False)
|
60 |
-
if info is None:
|
61 |
-
raise Exception("Could not extract audio information")
|
62 |
|
63 |
-
|
|
|
|
|
|
|
|
|
|
|
64 |
|
65 |
-
|
66 |
-
|
67 |
-
actual_filepath = str(self.output_dir / f"downloaded_video.{ext}")
|
68 |
|
69 |
-
|
70 |
-
|
71 |
-
|
72 |
-
actual_filepath = str(possible_files[0])
|
73 |
-
else:
|
74 |
-
raise FileNotFoundError("No downloaded files found")
|
75 |
|
76 |
-
|
77 |
-
|
|
|
|
|
78 |
|
79 |
-
|
80 |
-
|
81 |
-
st.error("This video is not available for download.")
|
82 |
-
else:
|
83 |
-
st.error("Download failed. Please try a different video.")
|
84 |
-
return None
|
85 |
|
86 |
except Exception as e:
|
87 |
-
st.error("
|
88 |
-
print(f"
|
89 |
return None
|
|
|
1 |
from pathlib import Path
|
2 |
import yt_dlp
|
3 |
+
import tempfile
|
4 |
import streamlit as st
|
5 |
+
from video_processor import VideoProcessor
|
6 |
+
from audio_processor import AudioProcessor
|
7 |
import re
|
8 |
import os
|
|
|
9 |
|
10 |
|
11 |
class LinkDownloader:
|
|
|
14 |
self.output_dir.mkdir(parents=True, exist_ok=True)
|
15 |
|
16 |
def sanitize_filename(self, title):
|
17 |
+
"""Sanitize filename by removing special characters and limiting length"""
|
18 |
+
# Replace special characters with underscore
|
19 |
clean_name = re.sub(r'[^a-zA-Z0-9.]', '_', title)
|
20 |
+
# Limit length
|
21 |
if len(clean_name) > 50:
|
22 |
clean_name = clean_name[:50]
|
23 |
return clean_name
|
24 |
|
25 |
def download_from_url(self, url):
|
26 |
+
"""Download video from URL using yt-dlp"""
|
27 |
try:
|
28 |
+
# Create a temporary filename template
|
29 |
temp_filename = 'downloaded_video.%(ext)s'
|
30 |
temp_filepath = str(self.output_dir / temp_filename)
|
31 |
|
32 |
+
# Configure yt-dlp options
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
33 |
ydl_opts = {
|
34 |
+
'format': 'best',
|
35 |
'outtmpl': temp_filepath,
|
36 |
+
'quiet': False, # Enable output for debugging
|
37 |
+
'no_warnings': False,
|
38 |
+
'extract_audio': False,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
39 |
}
|
40 |
|
41 |
+
st.info("Starting video download...")
|
42 |
+
print(f"Download directory: {self.output_dir}")
|
43 |
+
print(f"Download template: {temp_filepath}")
|
|
|
|
|
|
|
44 |
|
45 |
+
# Download the video
|
46 |
+
with yt_dlp.YoutubeDL(ydl_opts) as ydl:
|
47 |
+
# Extract info first
|
48 |
+
info = ydl.extract_info(url, download=False)
|
49 |
+
# Get the actual extension
|
50 |
+
ext = info.get('ext', 'mp4')
|
51 |
|
52 |
+
# Download the video
|
53 |
+
ydl.download([url])
|
|
|
54 |
|
55 |
+
# Construct the actual file path
|
56 |
+
actual_filepath = str(self.output_dir / f"downloaded_video.{ext}")
|
57 |
+
print(f"Expected downloaded file: {actual_filepath}")
|
|
|
|
|
|
|
58 |
|
59 |
+
# Verify file exists
|
60 |
+
if not os.path.exists(actual_filepath):
|
61 |
+
print(f"Files in directory: {os.listdir(self.output_dir)}")
|
62 |
+
raise FileNotFoundError(f"Downloaded file not found at {actual_filepath}")
|
63 |
|
64 |
+
print(f"File size: {os.path.getsize(actual_filepath)} bytes")
|
65 |
+
return actual_filepath
|
|
|
|
|
|
|
|
|
66 |
|
67 |
except Exception as e:
|
68 |
+
st.error(f"Error during download: {str(e)}")
|
69 |
+
print(f"Download error details: {str(e)}")
|
70 |
return None
|