1 from __future__ import unicode_literals
5 from .common import InfoExtractor
13 class MLBIE(InfoExtractor):
14 _VALID_URL = r'https?://m\.mlb\.com/(?:.*?/)?video/(?:topic/[\da-z_-]+/)?v(?P<id>n?\d+)'
17 'url': 'http://m.mlb.com/sea/video/topic/51231442/v34698933/nymsea-ackley-robs-a-home-run-with-an-amazing-catch/?c_id=sea',
18 'md5': 'ff56a598c2cf411a9a38a69709e97079',
22 'title': "Ackley's spectacular catch",
23 'description': 'md5:7f5a981eb4f3cbc8daf2aeffa2215bf0',
25 'timestamp': 1405980600,
26 'upload_date': '20140721',
27 'thumbnail': 're:^https?://.*\.jpg$',
31 'url': 'http://m.mlb.com/video/topic/81536970/v34496663/mianym-stanton-practices-for-the-home-run-derby',
32 'md5': 'd9c022c10d21f849f49c05ae12a8a7e9',
36 'title': 'Stanton prepares for Derby',
37 'description': 'md5:d00ce1e5fd9c9069e9c13ab4faedfa57',
39 'timestamp': 1405105800,
40 'upload_date': '20140711',
41 'thumbnail': 're:^https?://.*\.jpg$',
45 'url': 'http://m.mlb.com/video/topic/vtp_hrd_sponsor/v34578115/hrd-cespedes-wins-2014-gillette-home-run-derby',
46 'md5': '0e6e73d509321e142409b695eadd541f',
50 'title': 'Cespedes repeats as Derby champ',
51 'description': 'md5:08df253ce265d4cf6fb09f581fafad07',
53 'timestamp': 1405399936,
54 'upload_date': '20140715',
55 'thumbnail': 're:^https?://.*\.jpg$',
59 'url': 'http://m.mlb.com/video/v34577915/bautista-on-derby-captaining-duties-his-performance',
60 'md5': 'b8fd237347b844365d74ea61d4245967',
64 'title': 'Bautista on Home Run Derby',
65 'description': 'md5:b80b34031143d0986dddc64a8839f0fb',
67 'timestamp': 1405390722,
68 'upload_date': '20140715',
69 'thumbnail': 're:^https?://.*\.jpg$',
74 def _real_extract(self, url):
75 mobj = re.match(self._VALID_URL, url)
76 video_id = mobj.group('id')
78 detail = self._download_xml(
79 'http://m.mlb.com/gen/multimedia/detail/%s/%s/%s/%s.xml'
80 % (video_id[-3], video_id[-2], video_id[-1], video_id), video_id)
82 title = detail.find('./headline').text
83 description = detail.find('./big-blurb').text
84 duration = parse_duration(detail.find('./duration').text)
85 timestamp = parse_iso8601(detail.attrib['date'][:-5])
87 thumbnail = find_xpath_attr(
88 detail, './thumbnailScenarios/thumbnailScenario', 'type', '45').text
91 for media_url in detail.findall('./url'):
92 playback_scenario = media_url.attrib['playback_scenario']
94 'url': media_url.text,
95 'format_id': playback_scenario,
97 m = re.search(r'(?P<vbr>\d+)K_(?P<width>\d+)X(?P<height>\d+)', playback_scenario)
100 'vbr': int(m.group('vbr')) * 1000,
101 'width': int(m.group('width')),
102 'height': int(m.group('height')),
106 self._sort_formats(formats)
111 'description': description,
112 'duration': duration,
113 'timestamp': timestamp,
115 'thumbnail': thumbnail,