Thought I'd post some sample code in case others run into issues trying to parse the YouTube id from numerous url formats, or with parsing the YouTube video details from a playlist url.
from re import findallDEFAULT_HEADERS = {“User-Agent”: “Mozilla/5.0 (Windows NT 6.1; Win64; x64; rv:25.0) Gecko/20100101 Firefox/25.0”,
“Accept”: “application/json”}
TYPE_VIDEO = 100000
TYPE_PLAYLIST = 100001def id_from_url(url):
“”"Supply a YoutTube url and retrieve it’s Id. Supported formats are as follows:(random tags will automatically be removed)Playlist URL Types:
-------------------
https://www.youtube.com/p/19B0B5CCFEF1C0C9?hl=en_US
https://www.youtube.com/playlist?list=PL19B0B5CCFEF1C0C9
https://www.youtube.com/view_play_list?p=19B0B5CCFEF1C0C9
https://www.youtube.com/watch?v=1XP6Rpy7KCw&list=19B0B5CCFEF1C0C9Video URL Types:
----------------
https://www.youtube.com/v/XGSy3_Czz8k
https://www.youtube.com/e/XGSy3_Czz8k
https://www.youtube.com/embed/XGSy3_Czz8k
https://www.youtube.com/watch?v=XGSy3_Czz8k
https://www.youtube.com/get_video_info?video_id=XGSy3_Czz8k
“”"regexs = [(“PL”, “p=”, “&”), (“PL”, “list=”, “&”),
(“PL”, “p/”, “?”), ("", “v/”, “?”),
("", “e/”, “?”), ("", “embed/”, “?”),
("", “v=”, “&”), ("", “video_id=”, “&”)]
for regex in regexs:
y_id = None
media = TYPE_VIDEO
if regex[1] in url:
if url.endswith("/"):
url = url[:-1]
y_id = findall("%s(.*?)%s" % regex[1:], url + regex[2])[0]
if y_id.startswith(“PL”):
y_id = y_id[2:]
if regex[0] == “PL”:
media = TYPE_PLAYLIST
y_id = (regex[0] + y_id, media)
break
return y_iddef videos_from_playlist(y_id, indexed=True, plex=False, fallback_icon="", headers=DEFAULT_HEADERS):
“”“Supply a YouTube playlist id, return dictionary of playlist video data or Plex ObjectContainer
y_id: The YouTube playlist id
indexed: If True (default), the index position of the video
will be inserted at the beginning of the title
(eg: “(1/5) My Title”) If False, return “My Title”
plex: If False (default), function will return a dictionary
of video data. Otherwise supply a valid Plex ObjectContainer
and the video data will be added into VideoClipObject’s and
appended to your ObjectContainer
fallback_icon: If you are supplying an ObjectContainer then you MUST specify
a fallback icon in the event that there are none available
“””
if plex:
playlist = JSON.ObjectFromURL(“https://gdata.youtube.com/feeds/api/playlists/%s?v=2.1&alt=jsonc” % (y_id), headers=DEFAULT_HEADERS)
else:
from urllib2 import Request, urlopen
from json import load
c = urlopen(Request(“https://gdata.youtube.com/feeds/api/playlists/%s?v=2.1&alt=jsonc” % (y_id), headers=DEFAULT_HEADERS))
playlist = load©
c.close()play_items =
for index, item in enumerate(playlist[“data”][“items”]):
title = item[“video”][“title”]
url = “http://www.youtube.com/watch?v=%s&list=%s” % (item[“video”][“id”], y_id),
summary = item[“video”][“description”]
date = item[“video”][“uploaded”]
if indexed:
title = “(%s/%s) %s” % (index+1, len(playlist[“data”][“items”]), title)
try:
# test if hq thumb exists, if not use default quality… yuck…
if plex:
HTTP.Request(item[“video”][“thumbnail”][“hqDefault”])
else:
urlopen(item[“video”][“thumbnail”][“hqDefault”]).close()
thumb = item[“video”][“thumbnail”][“hqDefault”]
except Exception, error:
if “404” in str(error):
thumb = item[“video”][“thumbnail”][“sqDefault”]
if plex:
plex.add(VideoClipObject(
title = title,
url = url,
thumb = Resource.ContentsOfURLWithFallback(url=thumb, fallback=fallback_icon),
summary = summary,
originally_available_at = Datetime.ParseDate(date).date()
))
else:
play_items.append({“title”: title,
“url”: url,
“thumb”: thumb,
“summary”: summary,
“originally_available_at”: date})
if plex:
return plex
return play_itemsy_id, y_type = id_from_url(“https://www.youtube.com/playlist?list=PL19B0B5CCFEF1C0C9”)
print videos_from_playlist(y_id, plex=False)
