From 6aeba407db84a636fc2522b4f2344eac9e0c1fdb Mon Sep 17 00:00:00 2001 From: remitamine Date: Fri, 25 Sep 2015 10:52:48 +0100 Subject: [PATCH 1/2] [jukebox] remove extractor and handle it using generic extractor --- youtube_dl/extractor/__init__.py | 1 - youtube_dl/extractor/generic.py | 21 +++++++ youtube_dl/extractor/jukebox.py | 59 ------------------ youtube_dl/extractor/ultimedia.py | 99 +++++++++++++------------------ 4 files changed, 61 insertions(+), 119 deletions(-) delete mode 100644 youtube_dl/extractor/jukebox.py diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 7272859db..1813c7e1b 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -262,7 +262,6 @@ from .izlesene import IzleseneIE from .jadorecettepub import JadoreCettePubIE from .jeuxvideo import JeuxVideoIE from .jove import JoveIE -from .jukebox import JukeboxIE from .jpopsukitv import JpopsukiIE from .kaltura import KalturaIE from .kanalplay import KanalPlayIE diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py index 8881a8a23..4d1f75e63 100644 --- a/youtube_dl/extractor/generic.py +++ b/youtube_dl/extractor/generic.py @@ -50,6 +50,7 @@ from .dailymotion import DailymotionCloudIE from .onionstudios import OnionStudiosIE from .snagfilms import SnagFilmsEmbedIE from .screenwavemedia import ScreenwaveMediaIE +from .ultimedia import UltimediaIE class GenericIE(InfoExtractor): @@ -1029,6 +1030,21 @@ class GenericIE(InfoExtractor): 'ext': 'mp4', 'title': 'cinemasnob', }, + }, + # Ultimedia embed + { + 'url': 'http://www.jukebox.es/kosheen/videoclip,pride,r303r.html', + 'md5': '25551df6e7c7ab8096ceeeae048c5f64', + 'info_dict': { + 'id': 'r303r', + 'ext': 'mp4', + 'title': 'Kosheen - Pride (live)', + 'thumbnail': 're:^https?://.*\.jpg', + 'duration': 293, + 'upload_date': '20081103', + 'timestamp': 1225733392, + 'uploader_id': '33m03', + }, } ] @@ -1751,6 +1767,11 @@ class GenericIE(InfoExtractor): if mobj is not None: return self.url_result(unescapeHTML(mobj.group('url')), 'ScreenwaveMedia') + # Look for Ulltimedia embeds + ultimedia_url = UltimediaIE._extract_url(webpage) + if ultimedia_url: + return self.url_result(self._proto_relative_url(ultimedia_url), 'Ultimedia') + # Look for AdobeTVVideo embeds mobj = re.search( r']+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]', diff --git a/youtube_dl/extractor/jukebox.py b/youtube_dl/extractor/jukebox.py deleted file mode 100644 index da8068efc..000000000 --- a/youtube_dl/extractor/jukebox.py +++ /dev/null @@ -1,59 +0,0 @@ -from __future__ import unicode_literals - -import re - -from .common import InfoExtractor -from ..utils import ( - ExtractorError, - RegexNotFoundError, - unescapeHTML, -) - - -class JukeboxIE(InfoExtractor): - _VALID_URL = r'^http://www\.jukebox?\..+?\/.+[,](?P[a-z0-9\-]+)\.html' - _TEST = { - 'url': 'http://www.jukebox.es/kosheen/videoclip,pride,r303r.html', - 'info_dict': { - 'id': 'r303r', - 'ext': 'flv', - 'title': 'Kosheen-En Vivo Pride', - 'uploader': 'Kosheen', - }, - } - - def _real_extract(self, url): - video_id = self._match_id(url) - - html = self._download_webpage(url, video_id) - iframe_url = unescapeHTML(self._search_regex(r'