pacnpal/Pac-cogs
1
0
Fork 0
mirror of https://github.com/pacnpal/Pac-cogs.git synced 2025-12-20 10:51:05 -05:00
Code Issues Packages Projects Releases Wiki Activity

fix: Improve URL validation and extraction - Use suitable() method for URL validation - Add word-based URL detection - Fix URL extraction errors

Browse Source
This commit is contained in:
pacnpal
2024-11-15 00:55:27 +00:00
parent da9a6e40f9
commit 1bd8980f6f
1 changed files with 11 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files

18
videoarchiver/processor.py
View File

@@ -257,7 +257,8 @@ class VideoProcessor:
settings = await self.config.get_guild_settings(message.guild.id) settings = await self.config.get_guild_settings(message.guild.id)
# Check if message is in a monitored channel # Check if message is in a monitored channel
if message.channel.id not in settings["monitored_channels"]: monitored_channels = settings.get("monitored_channels", [])
if monitored_channels and message.channel.id not in monitored_channels:
return return
# Find all video URLs in message with improved pattern matching # Find all video URLs in message with improved pattern matching
@@ -282,13 +283,16 @@ class VideoProcessor:
"""Extract video URLs from message content with improved pattern matching""" """Extract video URLs from message content with improved pattern matching"""
urls = [] urls = []
try: try:
# Create a YoutubeDL instance to get extractors
with yt_dlp.YoutubeDL() as ydl: with yt_dlp.YoutubeDL() as ydl:
for ie in ydl._ies: # Split content into words and check each for URLs
if ie._VALID_URL: words = content.split()
# Use more specific pattern matching for word in words:
pattern = f"(?P<url>{ie._VALID_URL})" # Try each extractor
matches = re.finditer(pattern, content, re.IGNORECASE) for ie in ydl._ies:
urls.extend(match.group("url") for match in matches) if ie.suitable(word):
urls.append(word)
break # Stop once we find a matching extractor
except Exception as e: except Exception as e:
logger.error(f"URL extraction error: {str(e)}") logger.error(f"URL extraction error: {str(e)}")
return list(set(urls)) # Remove duplicates return list(set(urls)) # Remove duplicates