diff options
| -rw-r--r-- | youtube_dl/extractor/__init__.py | 2 | ||||
| -rw-r--r-- | youtube_dl/extractor/ign.py | 70 |
2 files changed, 59 insertions, 13 deletions
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 491c5368f..c00d5a352 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -27,7 +27,7 @@ from .googlesearch import GoogleSearchIE from .hotnewhiphop import HotNewHipHopIE from .howcast import HowcastIE from .hypem import HypemIE -from .ign import IGNIE +from .ign import IGNIE, OneUPIE from .ina import InaIE from .infoq import InfoQIE from .instagram import InstagramIE diff --git a/youtube_dl/extractor/ign.py b/youtube_dl/extractor/ign.py index b3a850d74..62abab655 100644 --- a/youtube_dl/extractor/ign.py +++ b/youtube_dl/extractor/ign.py @@ -6,10 +6,21 @@ from ..utils import ( determine_ext, ) + class IGNIE(InfoExtractor): - _VALID_URL = r'http://www.ign.com/videos/.+/(?P<name>.+)' + """ + Extractor for some of the IGN sites, like www.ign.com, es.ign.com de.ign.com. + Some videos of it.ign.com are also supported + """ + + _VALID_URL = r'https?://.+?\.ign\.com/(?:videos|show_videos)(/.+)?/(?P<name_or_id>.+)' IE_NAME = u'ign.com' + _CONFIG_URL_TEMPLATE = 'http://www.ign.com/videos/configs/id/%s.config' + _DESCRIPTION_RE = [r'<span class="page-object-description">(.+?)</span>', + r'id="my_show_video">.*?<p>(.*?)</p>', + ] + _TEST = { u'url': u'http://www.ign.com/videos/2013/06/05/the-last-of-us-review', u'file': u'8f862beef863986b2785559b9e1aa599.mp4', @@ -20,16 +31,29 @@ class IGNIE(InfoExtractor): } } + def _find_video_id(self, webpage): + res_id = [r'data-video-id="(.+?)"', + r'<object id="vid_(.+?)"', + r'<meta name="og:image" content=".*/(.+?)-(.+?)/.+.jpg"', + ] + return self._search_regex(res_id, webpage, 'video id') + def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) - name = mobj.group('name') - config_url = url + '.config' - webpage = self._download_webpage(url, name) - config = json.loads(self._download_webpage(config_url, name, u'Downloading video info')) - - self.report_extraction(name) - description = self._html_search_regex(r'<span class="page-object-description">(.+?)</span>', - webpage, 'video description', flags=re.DOTALL) + name_or_id = mobj.group('name_or_id') + webpage = self._download_webpage(url, name_or_id) + 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) + 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')) media = config['playlist']['media'] video_url = media['url'] @@ -37,9 +61,31 @@ class IGNIE(InfoExtractor): 'url': video_url, 'ext': determine_ext(video_url), 'title': media['metadata']['title'], - 'description': description, - 'thumbnail': media['poster'][0]['url'].replace('{size}', 'small'), + '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/video/id/(?P<name_or_id>.+)' + IE_NAME = '1up.com' + + _DESCRIPTION_RE = r'<div id="vid_summary">(.+?)</div>' + + _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', + } + } + + 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 + return result |