X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/a316b1d93c357b5edf19d5e3100526a94191c029..72d91f91be4810269f74cf296cab5dd61b84129c:/youtube_dl/extractor/ign.py diff --git a/youtube_dl/extractor/ign.py b/youtube_dl/extractor/ign.py index b1c8427..3aade9e 100644 --- a/youtube_dl/extractor/ign.py +++ b/youtube_dl/extractor/ign.py @@ -1,10 +1,8 @@ +from __future__ import unicode_literals + import re -import json from .common import InfoExtractor -from ..utils import ( - determine_ext, -) class IGNIE(InfoExtractor): @@ -13,29 +11,77 @@ class IGNIE(InfoExtractor): Some videos of it.ign.com are also supported """ - _VALID_URL = r'https?://.+?\.ign\.com/(?Pvideos|show_videos|articles)(/.+)?/(?P.+)' - IE_NAME = u'ign.com' + _VALID_URL = r'https?://.+?\.ign\.com/(?Pvideos|show_videos|articles|(?:[^/]*/feature))(/.+)?/(?P.+)' + IE_NAME = 'ign.com' _CONFIG_URL_TEMPLATE = 'http://www.ign.com/videos/configs/id/%s.config' - _DESCRIPTION_RE = [r'(.+?)', - r'id="my_show_video">.*?

(.*?)

', - ] - - _TEST = { - u'url': u'http://www.ign.com/videos/2013/06/05/the-last-of-us-review', - u'file': u'8f862beef863986b2785559b9e1aa599.mp4', - u'md5': u'eac8bdc1890980122c3b66f14bdd02e9', - u'info_dict': { - u'title': u'The Last of Us Review', - u'description': u'md5:c8946d4260a4d43a00d5ae8ed998870c', - } - } + _DESCRIPTION_RE = [ + r'(.+?)', + r'id="my_show_video">.*?

(.*?)

', + r']*id="(.+?)"', + ] return self._search_regex(res_id, webpage, 'video id') def _real_extract(self, url): @@ -43,53 +89,57 @@ class IGNIE(InfoExtractor): name_or_id = mobj.group('name_or_id') page_type = mobj.group('type') webpage = self._download_webpage(url, name_or_id) - if page_type == 'articles': - video_url = self._search_regex(r'var videoUrl = "(.+?)"', webpage, u'video url') - return self.url_result(video_url, ie='IGN') + if page_type != 'video': + multiple_urls = re.findall( + ']*value="[^"]*?url=(https?://www\.ign\.com/videos/.*?)["&]', + webpage) + if multiple_urls: + entries = [self.url_result(u, ie='IGN') for u in multiple_urls] + return { + '_type': 'playlist', + 'id': name_or_id, + 'entries': entries, + } + video_id = self._find_video_id(webpage) result = self._get_video_info(video_id) description = self._html_search_regex(self._DESCRIPTION_RE, - webpage, 'video description', - flags=re.DOTALL) + webpage, 'video description', flags=re.DOTALL) result['description'] = description return result def _get_video_info(self, video_id): config_url = self._CONFIG_URL_TEMPLATE % video_id - config = json.loads(self._download_webpage(config_url, video_id, - u'Downloading video info')) + config = self._download_json(config_url, video_id) media = config['playlist']['media'] - video_url = media['url'] - return {'id': media['metadata']['videoId'], - 'url': video_url, - 'ext': determine_ext(video_url), - 'title': media['metadata']['title'], - 'thumbnail': media['poster'][0]['url'].replace('{size}', 'grande'), - } + return { + 'id': media['metadata']['videoId'], + 'url': media['url'], + 'title': media['metadata']['title'], + 'thumbnail': media['poster'][0]['url'].replace('{size}', 'grande'), + } class OneUPIE(IGNIE): - """Extractor for 1up.com, it uses the ign videos system.""" - - _VALID_URL = r'https?://gamevideos.1up.com/(?Pvideo)/id/(?P.+)' + _VALID_URL = r'https?://gamevideos\.1up\.com/(?Pvideo)/id/(?P.+)\.html' IE_NAME = '1up.com' _DESCRIPTION_RE = r'
(.+?)
' - _TEST = { - u'url': u'http://gamevideos.1up.com/video/id/34976', - u'file': u'34976.mp4', - u'md5': u'68a54ce4ebc772e4b71e3123d413163d', - u'info_dict': { - u'title': u'Sniper Elite V2 - Trailer', - u'description': u'md5:5d289b722f5a6d940ca3136e9dae89cf', + _TESTS = [{ + 'url': 'http://gamevideos.1up.com/video/id/34976.html', + 'md5': '68a54ce4ebc772e4b71e3123d413163d', + 'info_dict': { + 'id': '34976', + 'ext': 'mp4', + 'title': 'Sniper Elite V2 - Trailer', + 'description': 'md5:5d289b722f5a6d940ca3136e9dae89cf', } - } + }] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) - id = mobj.group('name_or_id') result = super(OneUPIE, self)._real_extract(url) - result['id'] = id + result['id'] = mobj.group('name_or_id') return result