youtube_dl/extractor/lego.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..compat import compat_str
   8 from ..utils import (
   9     unescapeHTML,
  10     parse_duration,
  11     get_element_by_class,
  12 )
  13
  14
  15 class LEGOIE(InfoExtractor):
  16     _VALID_URL = r'https?://(?:www\.)?lego\.com/(?P<locale>[^/]+)/(?:[^/]+/)*videos/(?:[^/]+/)*[^/?#]+-(?P<id>[0-9a-f]+)'
  17     _TESTS = [{
  18         'url': 'http://www.lego.com/en-us/videos/themes/club/blocumentary-kawaguchi-55492d823b1b4d5e985787fa8c2973b1',
  19         'md5': 'f34468f176cfd76488767fc162c405fa',
  20         'info_dict': {
  21             'id': '55492d823b1b4d5e985787fa8c2973b1',
  22             'ext': 'mp4',
  23             'title': 'Blocumentary Great Creations: Akiyuki Kawaguchi',
  24             'description': 'Blocumentary Great Creations: Akiyuki Kawaguchi',
  25         },
  26     }, {
  27         # geo-restricted but the contentUrl contain a valid url
  28         'url': 'http://www.lego.com/nl-nl/videos/themes/nexoknights/episode-20-kingdom-of-heroes-13bdc2299ab24d9685701a915b3d71e7##sp=399',
  29         'md5': '4c3fec48a12e40c6e5995abc3d36cc2e',
  30         'info_dict': {
  31             'id': '13bdc2299ab24d9685701a915b3d71e7',
  32             'ext': 'mp4',
  33             'title': 'Aflevering 20 - Helden van het koninkrijk',
  34             'description': 'md5:8ee499aac26d7fa8bcb0cedb7f9c3941',
  35         },
  36     }, {
  37         # special characters in title
  38         'url': 'http://www.lego.com/en-us/starwars/videos/lego-star-wars-force-surprise-9685ee9d12e84ff38e84b4e3d0db533d',
  39         'info_dict': {
  40             'id': '9685ee9d12e84ff38e84b4e3d0db533d',
  41             'ext': 'mp4',
  42             'title': 'Force Surprise – LEGO® Star Wars™ Microfighters',
  43             'description': 'md5:9c673c96ce6f6271b88563fe9dc56de3',
  44         },
  45         'params': {
  46             'skip_download': True,
  47         },
  48     }]
  49     _BITRATES = [256, 512, 1024, 1536, 2560]
  50
  51     def _real_extract(self, url):
  52         locale, video_id = re.match(self._VALID_URL, url).groups()
  53         webpage = self._download_webpage(url, video_id)
  54         title = get_element_by_class('video-header', webpage).strip()
  55         progressive_base = 'https://lc-mediaplayerns-live-s.legocdn.com/'
  56         streaming_base = 'http://legoprod-f.akamaihd.net/'
  57         content_url = self._html_search_meta('contentUrl', webpage)
  58         path = self._search_regex(
  59             r'(?:https?:)?//[^/]+/(?:[iz]/s/)?public/(.+)_[0-9,]+\.(?:mp4|webm)',
  60             content_url, 'video path', default=None)
  61         if not path:
  62             player_url = self._proto_relative_url(self._search_regex(
  63                 r'<iframe[^>]+src="((?:https?)?//(?:www\.)?lego\.com/[^/]+/mediaplayer/video/[^"]+)',
  64                 webpage, 'player url', default=None))
  65             if not player_url:
  66                 base_url = self._proto_relative_url(self._search_regex(
  67                     r'data-baseurl="([^"]+)"', webpage, 'base url',
  68                     default='http://www.lego.com/%s/mediaplayer/video/' % locale))
  69                 player_url = base_url + video_id
  70             player_webpage = self._download_webpage(player_url, video_id)
  71             video_data = self._parse_json(unescapeHTML(self._search_regex(
  72                 r"video='([^']+)'", player_webpage, 'video data')), video_id)
  73             progressive_base = self._search_regex(
  74                 r'data-video-progressive-url="([^"]+)"',
  75                 player_webpage, 'progressive base', default='https://lc-mediaplayerns-live-s.legocdn.com/')
  76             streaming_base = self._search_regex(
  77                 r'data-video-streaming-url="([^"]+)"',
  78                 player_webpage, 'streaming base', default='http://legoprod-f.akamaihd.net/')
  79             item_id = video_data['ItemId']
  80
  81             net_storage_path = video_data.get('NetStoragePath') or '/'.join([item_id[:2], item_id[2:4]])
  82             base_path = '_'.join([item_id, video_data['VideoId'], video_data['Locale'], compat_str(video_data['VideoVersion'])])
  83             path = '/'.join([net_storage_path, base_path])
  84         streaming_path = ','.join(map(lambda bitrate: compat_str(bitrate), self._BITRATES))
  85
  86         formats = self._extract_akamai_formats(
  87             '%si/s/public/%s_,%s,.mp4.csmil/master.m3u8' % (streaming_base, path, streaming_path), video_id)
  88         m3u8_formats = list(filter(
  89             lambda f: f.get('protocol') == 'm3u8_native' and f.get('vcodec') != 'none',
  90             formats))
  91         if len(m3u8_formats) == len(self._BITRATES):
  92             self._sort_formats(m3u8_formats)
  93             for bitrate, m3u8_format in zip(self._BITRATES, m3u8_formats):
  94                 progressive_base_url = '%spublic/%s_%d.' % (progressive_base, path, bitrate)
  95                 mp4_f = m3u8_format.copy()
  96                 mp4_f.update({
  97                     'url': progressive_base_url + 'mp4',
  98                     'format_id': m3u8_format['format_id'].replace('hls', 'mp4'),
  99                     'protocol': 'http',
 100                 })
 101                 web_f = {
 102                     'url': progressive_base_url + 'webm',
 103                     'format_id': m3u8_format['format_id'].replace('hls', 'webm'),
 104                     'width': m3u8_format['width'],
 105                     'height': m3u8_format['height'],
 106                     'tbr': m3u8_format.get('tbr'),
 107                     'ext': 'webm',
 108                 }
 109                 formats.extend([web_f, mp4_f])
 110         else:
 111             for bitrate in self._BITRATES:
 112                 for ext in ('web', 'mp4'):
 113                     formats.append({
 114                         'format_id': '%s-%s' % (ext, bitrate),
 115                         'url': '%spublic/%s_%d.%s' % (progressive_base, path, bitrate, ext),
 116                         'tbr': bitrate,
 117                         'ext': ext,
 118                     })
 119         self._sort_formats(formats)
 120
 121         return {
 122             'id': video_id,
 123             'title': title,
 124             'description': self._html_search_meta('description', webpage),
 125             'thumbnail': self._html_search_meta('thumbnail', webpage),
 126             'duration': parse_duration(self._html_search_meta('duration', webpage)),
 127             'formats': formats,
 128         }