tyler/syllabus
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Update download.py

Browse Source
This commit is contained in:
TylerCG 2025-04-25 23:04:34 -04:00
parent 082576061e
commit ad24e0827e
1 changed files with 35 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

41
app/download.py
View File

@ -1,6 +1,15 @@
from fastapi.responses import JSONResponse
import os, yt_dlp, json, requests
from bs4 import BeautifulSoup
import re
# Define your patterns
reject_patterns = [
re.compile(r'(?i).*behind.?the.?scenes.*'),
re.compile(r'(?i).*trailer.*'),
re.compile(r'(?i).*recap.*'),
re.compile(r'(?i).*last.looks.*'),
]
class grab():
def season(url):
@ -57,12 +66,13 @@ class dropout():
'home': directory
},
'cookiefile': '/data/dropout.cookies.txt',
'reject_title': [
r'(?i).*behind.?the.?scenes.*', # Reject titles with "behind the scenes" (case-insensitive)
r'(?i).*trailer.*', # Reject titles with "trailer" (case-insensitive)
r'(?i).*recap.*', # Reject titles with "recap" (case-insensitive)
r'(?i).*last.looks.*' # Reject titles with "last looks" (case-insensitive)
],
'match_filter': yt_dlp.utils.match_filter_func("title !~= '(?i).*behind.?the.?scenes.*|.*trailer.*|.*recap.*|.*last.looks.*'"),
# 'reject_title': [
# r'(?i).*behind.?the.?scenes.*', # Reject titles with "behind the scenes" (case-insensitive)
# r'(?i).*trailer.*', # Reject titles with "trailer" (case-insensitive)
# r'(?i).*recap.*', # Reject titles with "recap" (case-insensitive)
# r'(?i).*last.looks.*' # Reject titles with "last looks" (case-insensitive)
# ],
'outtmpl': show + ' - S'+f"{int(season):02}"+'E'+episode+' - %(title)s.%(ext)s',
'noplaylist': True,
# Additional options for downloading subtitles
@ -71,6 +81,25 @@ class dropout():
}
with yt_dlp.YoutubeDL(dl_ops) as ydl:
ydl.download([url])
# ydl_opts = {
# 'quiet': True, # Turn off download progress messages
# 'skip_download': True, # Don't download anything
# 'cookiefile': '/data/dropout.cookies.txt',
# }
# with yt_dlp.YoutubeDL(ydl_opts) as ydl:
# info = ydl.extract_info(url, download=False)
# print(f"Playlist Title: {info.get('title')}")
# print(f"Uploader: {info.get('uploader')}")
# print(f"Number of videos: {len(info.get('entries', []))}")
# print()
# for i, entry in enumerate(info['entries'], 1):
# print(f"{i}. {entry.get('title')}")
# print(f" URL: {entry.get('webpage_url')}")
# print(f" Duration: {entry.get('duration')} seconds")
# print()