X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fmtv.py;h=4521451ac933baabce786c76813e3e8407298b65;hb=5cef4ff09b8e77daab03b1cca508a941b5fd5fa0;hp=485c1fd7d02dd6920de2fae7d8dbca4d76bdf475;hpb=e4f320a4d044b690721016e36972cd547ee787d3;p=youtube-dl diff --git a/youtube_dl/extractor/mtv.py b/youtube_dl/extractor/mtv.py index 485c1fd7d..4521451ac 100644 --- a/youtube_dl/extractor/mtv.py +++ b/youtube_dl/extractor/mtv.py @@ -6,9 +6,13 @@ from .common import InfoExtractor from ..utils import ( compat_urllib_parse, ExtractorError, + find_xpath_attr, fix_xml_ampersands, + url_basename, + RegexNotFoundError, ) + def _media_xml_tag(tag): return '{http://search.yahoo.com/mrss/}%s' % tag @@ -63,6 +67,7 @@ class MTVServicesInfoExtractor(InfoExtractor): mediagen_url = re.sub(r'&[^=]*?={.*?}(?=(&|$))', '', mediagen_url) if 'acceptMethods' not in mediagen_url: mediagen_url += '&acceptMethods=fms' + mediagen_doc = self._download_xml(mediagen_url, video_id, 'Downloading video urls') @@ -72,8 +77,22 @@ class MTVServicesInfoExtractor(InfoExtractor): else: description = None + title_el = None + if title_el is None: + title_el = find_xpath_attr( + itemdoc, './/{http://search.yahoo.com/mrss/}category', + 'scheme', 'urn:mtvn:video_title') + if title_el is None: + title_el = itemdoc.find('.//{http://search.yahoo.com/mrss/}title') + if title_el is None: + title_el = itemdoc.find('.//title') + title = title_el.text + if title is None: + raise ExtractorError('Could not find video title') + title = title.strip() + return { - 'title': itemdoc.find('title').text, + 'title': title, 'formats': self._extract_video_formats(mediagen_doc), 'id': video_id, 'thumbnail': self._get_thumbnail_url(uri, itemdoc), @@ -89,6 +108,22 @@ class MTVServicesInfoExtractor(InfoExtractor): 'Downloading info', transform_source=fix_xml_ampersands) return [self._get_video_info(item) for item in idoc.findall('.//item')] + def _real_extract(self, url): + title = url_basename(url) + webpage = self._download_webpage(url, title) + try: + # the url can be http://media.mtvnservices.com/fb/{mgid}.swf + # or http://media.mtvnservices.com/{mgid} + og_url = self._og_search_video_url(webpage) + mgid = url_basename(og_url) + if mgid.endswith('.swf'): + mgid = mgid[:-4] + except RegexNotFoundError: + mgid = self._search_regex( + [r'data-mgid="(.*?)"', r'swfobject.embedSWF\(".*?(mgid:.*?)"'], + webpage, u'mgid') + return self._get_videos_info(mgid) + class MTVIE(MTVServicesInfoExtractor): _VALID_URL = r'''(?x)^https?:// @@ -141,3 +176,17 @@ class MTVIE(MTVServicesInfoExtractor): uri = self._html_search_regex(r'/uri/(.*?)\?', webpage, 'uri') return self._get_videos_info(uri) + + +class MTVIggyIE(MTVServicesInfoExtractor): + IE_NAME = 'mtviggy.com' + _VALID_URL = r'https?://www\.mtviggy\.com/videos/.+' + _TEST = { + 'url': 'http://www.mtviggy.com/videos/arcade-fire-behind-the-scenes-at-the-biggest-music-experiment-yet/', + 'info_dict': { + 'id': '984696', + 'ext': 'mp4', + 'title': 'Arcade Fire: Behind the Scenes at the Biggest Music Experiment Yet', + } + } + _FEED_URL = 'http://all.mtvworldverticals.com/feed-xml/'