69 lines
1.9 KiB
Python
69 lines
1.9 KiB
Python
|
#!/usr/bin/python3
|
||
|
|
|
||
|
|
from utils import *
|
||
|
|
from download_page import download
|
||
|
|
|
||
|
|
# portable code to get filename
|
||
|
|
import os
|
||
|
|
platform = os.path.basename(__file__)
|
||
|
|
if platform.endswith(".py"):
|
||
|
|
platform = platform[:(-3)]
|
||
|
|
|
||
|
|
channel_url = "https://www.youtube.com/feeds/videos.xml?channel_id="
|
||
|
|
|
||
|
|
def extract_from_url (url, verbosity):
|
||
|
|
# useful function for stripping ID out of URL
|
||
|
|
def get_id (url, prefix):
|
||
|
|
if prefix in url:
|
||
|
|
ident = url[url.index(prefix) + len(prefix):]
|
||
|
|
for symbol in ["/", "?", "&"]:
|
||
|
|
if symbol in ident:
|
||
|
|
ident = ident[:ident.index(symbol)]
|
||
|
|
return ident
|
||
|
|
else:
|
||
|
|
return None
|
||
|
|
|
||
|
|
# attempt to get feed for playlist
|
||
|
|
ident = get_id (url, "youtube.com/playlist?list=")
|
||
|
|
if ident is None:
|
||
|
|
ident = get_id (url, "&list=")
|
||
|
|
if not ident is None:
|
||
|
|
return "https://www.youtube.com/feeds/videos.xml?playlist_id=" + ident
|
||
|
|
|
||
|
|
# attempt to get feed based on channel ID
|
||
|
|
ident = get_id (url, "youtube.com/channel/")
|
||
|
|
if not ident is None:
|
||
|
|
return channel_url + ident
|
||
|
|
|
||
|
|
# attempt to get feed based on username
|
||
|
|
ident = get_id (url, "youtube.com/user/")
|
||
|
|
if not ident is None:
|
||
|
|
return "https://www.youtube.com/feeds/videos.xml?user=" + ident
|
||
|
|
|
||
|
|
return None
|
||
|
|
|
||
|
|
def extract_from_page (page, verbosity):
|
||
|
|
ident = search (page, '<link rel="canonical" href="https://www.youtube.com/channel/', '">')
|
||
|
|
if not ident is None:
|
||
|
|
return channel_url + ident
|
||
|
|
|
||
|
|
ident = search (page, '<meta itemprop="channelId" content="','">')
|
||
|
|
if not ident is None:
|
||
|
|
return channel_url + ident
|
||
|
|
|
||
|
|
ident = search (page, '"channelId":"','"')
|
||
|
|
if not ident is None:
|
||
|
|
return channel_url + ident
|
||
|
|
|
||
|
|
def extract (url, page=None, network=False, verbosity=3, args={}):
|
||
|
|
feed = extract_from_url (url, verbosity)
|
||
|
|
if not feed is None:
|
||
|
|
return feed
|
||
|
|
else:
|
||
|
|
notify ("Unable to get feed from URL alone", verbosity, platform)
|
||
|
|
if network == True:
|
||
|
|
page = download (platform, url, args, verbosity)
|
||
|
|
feed = extract_from_page (page, verbosity)
|
||
|
|
if not feed is None:
|
||
|
|
return feed
|