X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fmiomio.py;h=170ebd9eb9e285f91e4b8bd85c05b13f745039a8;hb=5c2266df4b9aeb7881ed8c026a038e2a25e43734;hp=11608f73026929f605156a1d20ad7269d2ccafb3;hpb=416b9c29f7a03ac004631ffdf38bb6ed39da4650;p=youtube-dl diff --git a/youtube_dl/extractor/miomio.py b/youtube_dl/extractor/miomio.py index 11608f730..170ebd9eb 100644 --- a/youtube_dl/extractor/miomio.py +++ b/youtube_dl/extractor/miomio.py @@ -7,6 +7,8 @@ from .common import InfoExtractor from ..utils import ( xpath_text, int_or_none, + ExtractorError, + sanitized_Request, ) @@ -14,13 +16,14 @@ class MioMioIE(InfoExtractor): IE_NAME = 'miomio.tv' _VALID_URL = r'https?://(?:www\.)?miomio\.tv/watch/cc(?P[0-9]+)' _TESTS = [{ - 'url': 'http://www.miomio.tv/watch/cc179734/', - 'md5': '48de02137d0739c15b440a224ad364b9', + # "type=video" in flashvars + 'url': 'http://www.miomio.tv/watch/cc88912/', + 'md5': '317a5f7f6b544ce8419b784ca8edae65', 'info_dict': { - 'id': '179734', + 'id': '88912', 'ext': 'flv', - 'title': '手绘动漫鬼泣但丁全程画法', - 'duration': 354, + 'title': '【SKY】字幕 铠武昭和VS平成 假面骑士大战FEAT战队 魔星字幕组 字幕', + 'duration': 5923, }, }, { 'url': 'http://www.miomio.tv/watch/cc184024/', @@ -29,6 +32,14 @@ class MioMioIE(InfoExtractor): 'title': '《动漫同人插画绘制》', }, 'playlist_mincount': 86, + 'skip': 'This video takes time too long for retrieving the URL', + }, { + 'url': 'http://www.miomio.tv/watch/cc173113/', + 'info_dict': { + 'id': '173113', + 'title': 'The New Macbook 2015 上手试玩与简评' + }, + 'playlist_mincount': 2, }] def _real_extract(self, url): @@ -41,23 +52,26 @@ class MioMioIE(InfoExtractor): mioplayer_path = self._search_regex( r'src="(/mioplayer/[^"]+)"', webpage, 'ref_path') + http_headers = {'Referer': 'http://www.miomio.tv%s' % mioplayer_path} + xml_config = self._search_regex( - r'flashvars="type=sina&(.+?)&', + r'flashvars="type=(?:sina|video)&(.+?)&', webpage, 'xml config') - + # skipping the following page causes lags and eventually connection drop-outs self._request_webpage( 'http://www.miomio.tv/mioplayer/mioplayerconfigfiles/xml.php?id=%s&r=%s' % (id, random.randint(100, 999)), video_id) - # the following xml contains the actual configuration information on the video file(s) - vid_config = self._download_xml( + vid_config_request = sanitized_Request( 'http://www.miomio.tv/mioplayer/mioplayerconfigfiles/sina.php?{0}'.format(xml_config), - video_id) + headers=http_headers) - http_headers = { - 'Referer': 'http://www.miomio.tv%s' % mioplayer_path, - } + # the following xml contains the actual configuration information on the video file(s) + vid_config = self._download_xml(vid_config_request, video_id) + + if not int_or_none(xpath_text(vid_config, 'timelength')): + raise ExtractorError('Unable to load videos!', expected=True) entries = [] for f in vid_config.findall('./durl'):