2 from __future__ import unicode_literals
6 from .common import InfoExtractor
7 from ..compat import compat_str
16 class HBOBaseIE(InfoExtractor):
56 def _extract_from_id(self, video_id):
57 video_data = self._download_xml(
58 'http://render.lv3.hbo.com/data/content/global/videos/data/%s.xml' % video_id, video_id)
59 title = xpath_text(video_data, 'title', 'title', True)
62 for source in xpath_element(video_data, 'videos', 'sources', True):
63 if source.tag == 'size':
64 path = xpath_text(source, './/path')
67 width = source.attrib.get('width')
68 format_info = self._FORMATS_INFO.get(width, {})
69 height = format_info.get('height')
72 'format_id': 'http%s' % ('-%dp' % height if height else ''),
73 'width': format_info.get('width'),
76 rtmp = re.search(r'^(?P<url>rtmpe?://[^/]+/(?P<app>.+))/(?P<playpath>mp4:.+)$', path)
79 'url': rtmp.group('url'),
80 'play_path': rtmp.group('playpath'),
81 'app': rtmp.group('app'),
83 'format_id': fmt['format_id'].replace('http', 'rtmp'),
87 video_url = source.text
90 if source.tag == 'tarball':
91 formats.extend(self._extract_m3u8_formats(
92 video_url.replace('.tar', '/base_index_w8.m3u8'),
93 video_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False))
94 elif source.tag == 'hls':
95 m3u8_formats = self._extract_m3u8_formats(
96 video_url.replace('.tar', '/base_index.m3u8'),
97 video_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False)
98 for f in m3u8_formats:
99 if f.get('vcodec') == 'none' and not f.get('tbr'):
100 f['tbr'] = int_or_none(self._search_regex(
101 r'-(\d+)k/', f['url'], 'tbr', default=None))
102 formats.extend(m3u8_formats)
103 elif source.tag == 'dash':
104 formats.extend(self._extract_mpd_formats(
105 video_url.replace('.tar', '/manifest.mpd'),
106 video_id, mpd_id='dash', fatal=False))
108 format_info = self._FORMATS_INFO.get(source.tag, {})
110 'format_id': 'http-%s' % source.tag,
112 'width': format_info.get('width'),
113 'height': format_info.get('height'),
115 self._sort_formats(formats)
118 card_sizes = xpath_element(video_data, 'titleCardSizes')
119 if card_sizes is not None:
120 for size in card_sizes:
121 path = xpath_text(size, 'path')
124 width = int_or_none(size.get('width'))
134 'duration': parse_duration(xpath_text(video_data, 'duration/tv14')),
136 'thumbnails': thumbnails,
140 class HBOIE(HBOBaseIE):
142 _VALID_URL = r'https?://(?:www\.)?hbo\.com/video/video\.html\?.*vid=(?P<id>[0-9]+)'
144 'url': 'http://www.hbo.com/video/video.html?autoplay=true&g=u&vid=1437839',
145 'md5': '2c6a6bc1222c7e91cb3334dad1746e5a',
149 'title': 'Ep. 64 Clip: Encryption',
150 'thumbnail': r're:https?://.*\.jpg$',
155 def _real_extract(self, url):
156 video_id = self._match_id(url)
157 return self._extract_from_id(video_id)
160 class HBOEpisodeIE(HBOBaseIE):
161 IE_NAME = 'hbo:episode'
162 _VALID_URL = r'https?://(?:www\.)?hbo\.com/(?P<path>(?!video)(?:(?:[^/]+/)+video|watch-free-episodes)/(?P<id>[0-9a-z-]+))(?:\.html)?'
165 'url': 'http://www.hbo.com/girls/episodes/5/52-i-love-you-baby/video/ep-52-inside-the-episode.html?autoplay=true',
166 'md5': '61ead79b9c0dfa8d3d4b07ef4ac556fb',
169 'display_id': 'ep-52-inside-the-episode',
171 'title': 'Ep. 52: Inside the Episode',
172 'thumbnail': r're:https?://.*\.jpg$',
176 'url': 'http://www.hbo.com/game-of-thrones/about/video/season-5-invitation-to-the-set.html?autoplay=true',
177 'only_matching': True,
179 'url': 'http://www.hbo.com/watch-free-episodes/last-week-tonight-with-john-oliver',
180 'only_matching': True,
183 def _real_extract(self, url):
184 path, display_id = re.match(self._VALID_URL, url).groups()
186 content = self._download_json(
187 'http://www.hbo.com/api/content/' + path, display_id)['content']
189 video_id = compat_str((content.get('parsed', {}).get(
190 'common:FullBleedVideo', {}) or content['selectedEpisode'])['videoId'])
192 info_dict = self._extract_from_id(video_id)
193 info_dict['display_id'] = display_id