youtube_dl/extractor/mlb.py

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6 from ..utils import (
   7     parse_duration,
   8     parse_iso8601,
   9 )
  10
  11
  12 class MLBIE(InfoExtractor):
  13     _VALID_URL = r'https?://m\.mlb\.com/(?:(?:.*?/)?video/(?:topic/[\da-z_-]+/)?v|shared/video/embed/embed\.html\?.*?\bcontent_id=)(?P<id>n?\d+)'
  14     _TESTS = [
  15         {
  16             'url': 'http://m.mlb.com/sea/video/topic/51231442/v34698933/nymsea-ackley-robs-a-home-run-with-an-amazing-catch/?c_id=sea',
  17             'md5': 'ff56a598c2cf411a9a38a69709e97079',
  18             'info_dict': {
  19                 'id': '34698933',
  20                 'ext': 'mp4',
  21                 'title': "Ackley's spectacular catch",
  22                 'description': 'md5:7f5a981eb4f3cbc8daf2aeffa2215bf0',
  23                 'duration': 66,
  24                 'timestamp': 1405980600,
  25                 'upload_date': '20140721',
  26                 'thumbnail': 're:^https?://.*\.jpg$',
  27             },
  28         },
  29         {
  30             'url': 'http://m.mlb.com/video/topic/81536970/v34496663/mianym-stanton-practices-for-the-home-run-derby',
  31             'md5': 'd9c022c10d21f849f49c05ae12a8a7e9',
  32             'info_dict': {
  33                 'id': '34496663',
  34                 'ext': 'mp4',
  35                 'title': 'Stanton prepares for Derby',
  36                 'description': 'md5:d00ce1e5fd9c9069e9c13ab4faedfa57',
  37                 'duration': 46,
  38                 'timestamp': 1405105800,
  39                 'upload_date': '20140711',
  40                 'thumbnail': 're:^https?://.*\.jpg$',
  41             },
  42         },
  43         {
  44             'url': 'http://m.mlb.com/video/topic/vtp_hrd_sponsor/v34578115/hrd-cespedes-wins-2014-gillette-home-run-derby',
  45             'md5': '0e6e73d509321e142409b695eadd541f',
  46             'info_dict': {
  47                 'id': '34578115',
  48                 'ext': 'mp4',
  49                 'title': 'Cespedes repeats as Derby champ',
  50                 'description': 'md5:08df253ce265d4cf6fb09f581fafad07',
  51                 'duration': 488,
  52                 'timestamp': 1405399936,
  53                 'upload_date': '20140715',
  54                 'thumbnail': 're:^https?://.*\.jpg$',
  55             },
  56         },
  57         {
  58             'url': 'http://m.mlb.com/video/v34577915/bautista-on-derby-captaining-duties-his-performance',
  59             'md5': 'b8fd237347b844365d74ea61d4245967',
  60             'info_dict': {
  61                 'id': '34577915',
  62                 'ext': 'mp4',
  63                 'title': 'Bautista on Home Run Derby',
  64                 'description': 'md5:b80b34031143d0986dddc64a8839f0fb',
  65                 'duration': 52,
  66                 'timestamp': 1405390722,
  67                 'upload_date': '20140715',
  68                 'thumbnail': 're:^https?://.*\.jpg$',
  69             },
  70         },
  71         {
  72             'url': 'http://m.mlb.com/shared/video/embed/embed.html?content_id=35692085&topic_id=6479266&width=400&height=224&property=mlb',
  73             'only_matching': True,
  74         },
  75     ]
  76
  77     def _real_extract(self, url):
  78         mobj = re.match(self._VALID_URL, url)
  79         video_id = mobj.group('id')
  80
  81         detail = self._download_xml(
  82             'http://m.mlb.com/gen/multimedia/detail/%s/%s/%s/%s.xml'
  83             % (video_id[-3], video_id[-2], video_id[-1], video_id), video_id)
  84
  85         title = detail.find('./headline').text
  86         description = detail.find('./big-blurb').text
  87         duration = parse_duration(detail.find('./duration').text)
  88         timestamp = parse_iso8601(detail.attrib['date'][:-5])
  89
  90         thumbnails = [{
  91             'url': thumbnail.text,
  92         } for thumbnail in detail.findall('./thumbnailScenarios/thumbnailScenario')]
  93
  94         formats = []
  95         for media_url in detail.findall('./url'):
  96             playback_scenario = media_url.attrib['playback_scenario']
  97             fmt = {
  98                 'url': media_url.text,
  99                 'format_id': playback_scenario,
 100             }
 101             m = re.search(r'(?P<vbr>\d+)K_(?P<width>\d+)X(?P<height>\d+)', playback_scenario)
 102             if m:
 103                 fmt.update({
 104                     'vbr': int(m.group('vbr')) * 1000,
 105                     'width': int(m.group('width')),
 106                     'height': int(m.group('height')),
 107                 })
 108             formats.append(fmt)
 109
 110         self._sort_formats(formats)
 111
 112         return {
 113             'id': video_id,
 114             'title': title,
 115             'description': description,
 116             'duration': duration,
 117             'timestamp': timestamp,
 118             'formats': formats,
 119             'thumbnails': thumbnails,
 120         }