2 from __future__ import unicode_literals
6 from .common import InfoExtractor
15 class HBOBaseIE(InfoExtractor):
43 def _extract_from_id(self, video_id):
44 video_data = self._download_xml(
45 'http://render.lv3.hbo.com/data/content/global/videos/data/%s.xml' % video_id, video_id)
46 title = xpath_text(video_data, 'title', 'title', True)
49 for source in xpath_element(video_data, 'videos', 'sources', True):
50 if source.tag == 'size':
51 path = xpath_text(source, './/path')
54 width = source.attrib.get('width')
55 format_info = self._FORMATS_INFO.get(width, {})
56 height = format_info.get('height')
59 'format_id': 'http%s' % ('-%dp' % height if height else ''),
60 'width': format_info.get('width'),
63 rtmp = re.search(r'^(?P<url>rtmpe?://[^/]+/(?P<app>.+))/(?P<playpath>mp4:.+)$', path)
66 'url': rtmp.group('url'),
67 'play_path': rtmp.group('playpath'),
68 'app': rtmp.group('app'),
70 'format_id': fmt['format_id'].replace('http', 'rtmp'),
74 video_url = source.text
77 if source.tag == 'tarball':
78 formats.extend(self._extract_m3u8_formats(
79 video_url.replace('.tar', '/base_index_w8.m3u8'),
80 video_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False))
82 format_info = self._FORMATS_INFO.get(source.tag, {})
84 'format_id': 'http-%s' % source.tag,
86 'width': format_info.get('width'),
87 'height': format_info.get('height'),
89 self._sort_formats(formats, ('width', 'height', 'tbr', 'format_id'))
92 card_sizes = xpath_element(video_data, 'titleCardSizes')
93 if card_sizes is not None:
94 for size in card_sizes:
95 path = xpath_text(size, 'path')
98 width = int_or_none(size.get('width'))
108 'duration': parse_duration(xpath_text(video_data, 'duration/tv14')),
110 'thumbnails': thumbnails,
114 class HBOIE(HBOBaseIE):
115 _VALID_URL = r'https?://(?:www\.)?hbo\.com/video/video\.html\?.*vid=(?P<id>[0-9]+)'
117 'url': 'http://www.hbo.com/video/video.html?autoplay=true&g=u&vid=1437839',
118 'md5': '1c33253f0c7782142c993c0ba62a8753',
122 'title': 'Ep. 64 Clip: Encryption',
123 'thumbnail': r're:https?://.*\.jpg$',
128 def _real_extract(self, url):
129 video_id = self._match_id(url)
130 return self._extract_from_id(video_id)
133 class HBOEpisodeIE(HBOBaseIE):
134 _VALID_URL = r'https?://(?:www\.)?hbo\.com/(?!video)([^/]+/)+video/(?P<id>[0-9a-z-]+)\.html'
137 'url': 'http://www.hbo.com/girls/episodes/5/52-i-love-you-baby/video/ep-52-inside-the-episode.html?autoplay=true',
138 'md5': '689132b253cc0ab7434237fc3a293210',
141 'display_id': 'ep-52-inside-the-episode',
143 'title': 'Ep. 52: Inside the Episode',
144 'thumbnail': r're:https?://.*\.jpg$',
148 'url': 'http://www.hbo.com/game-of-thrones/about/video/season-5-invitation-to-the-set.html?autoplay=true',
149 'only_matching': True,
152 def _real_extract(self, url):
153 display_id = self._match_id(url)
155 webpage = self._download_webpage(url, display_id)
157 video_id = self._search_regex(
158 r'(?P<q1>[\'"])videoId(?P=q1)\s*:\s*(?P<q2>[\'"])(?P<video_id>\d+)(?P=q2)',
159 webpage, 'video ID', group='video_id')
161 info_dict = self._extract_from_id(video_id)
162 info_dict['display_id'] = display_id