2 from __future__ import unicode_literals
6 from .common import InfoExtractor
15 class HBOIE(InfoExtractor):
16 _VALID_URL = r'https?://(?:www\.)?hbo\.com/video/video\.html\?.*vid=(?P<id>[0-9]+)'
18 'url': 'http://www.hbo.com/video/video.html?autoplay=true&g=u&vid=1437839',
19 'md5': '1c33253f0c7782142c993c0ba62a8753',
23 'title': 'Ep. 64 Clip: Encryption',
53 def _real_extract(self, url):
54 video_id = self._match_id(url)
55 video_data = self._download_xml(
56 'http://render.lv3.hbo.com/data/content/global/videos/data/%s.xml' % video_id, video_id)
57 title = xpath_text(video_data, 'title', 'title', True)
60 for source in xpath_element(video_data, 'videos', 'sources', True):
61 if source.tag == 'size':
62 path = xpath_text(source, './/path')
65 width = source.attrib.get('width')
66 format_info = self._FORMATS_INFO.get(width, {})
67 height = format_info.get('height')
70 'format_id': 'http%s' % ('-%dp' % height if height else ''),
71 'width': format_info.get('width'),
74 rtmp = re.search(r'^(?P<url>rtmpe?://[^/]+/(?P<app>.+))/(?P<playpath>mp4:.+)$', path)
77 'url': rtmp.group('url'),
78 'play_path': rtmp.group('playpath'),
79 'app': rtmp.group('app'),
81 'format_id': fmt['format_id'].replace('http', 'rtmp'),
85 video_url = source.text
88 if source.tag == 'tarball':
89 formats.extend(self._extract_m3u8_formats(
90 video_url.replace('.tar', '/base_index_w8.m3u8'),
91 video_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False))
93 format_info = self._FORMATS_INFO.get(source.tag, {})
95 'format_id': 'http-%s' % source.tag,
97 'width': format_info.get('width'),
98 'height': format_info.get('height'),
100 self._sort_formats(formats, ('width', 'height', 'tbr', 'format_id'))
103 card_sizes = xpath_element(video_data, 'titleCardSizes')
104 if card_sizes is not None:
105 for size in card_sizes:
106 path = xpath_text(size, 'path')
109 width = int_or_none(size.get('width'))
119 'duration': parse_duration(xpath_element(video_data, 'duration/tv14')),
121 'thumbnails': thumbnails,