]>
Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/lego.py
2 from __future__
import unicode_literals
6 from .common
import InfoExtractor
7 from ..compat
import compat_str
15 class LEGOIE(InfoExtractor
):
16 _VALID_URL
= r
'https?://(?:www\.)?lego\.com/(?P<locale>[^/]+)/(?:[^/]+/)*videos/(?:[^/]+/)*[^/?#]+-(?P<id>[0-9a-f]+)'
18 'url': 'http://www.lego.com/en-us/videos/themes/club/blocumentary-kawaguchi-55492d823b1b4d5e985787fa8c2973b1',
19 'md5': 'f34468f176cfd76488767fc162c405fa',
21 'id': '55492d823b1b4d5e985787fa8c2973b1',
23 'title': 'Blocumentary Great Creations: Akiyuki Kawaguchi',
24 'description': 'Blocumentary Great Creations: Akiyuki Kawaguchi',
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',
31 'id': '13bdc2299ab24d9685701a915b3d71e7',
33 'title': 'Aflevering 20 - Helden van het koninkrijk',
34 'description': 'md5:8ee499aac26d7fa8bcb0cedb7f9c3941',
37 # special characters in title
38 'url': 'http://www.lego.com/en-us/starwars/videos/lego-star-wars-force-surprise-9685ee9d12e84ff38e84b4e3d0db533d',
40 'id': '9685ee9d12e84ff38e84b4e3d0db533d',
42 'title': 'Force Surprise – LEGO® Star Wars™ Microfighters',
43 'description': 'md5:9c673c96ce6f6271b88563fe9dc56de3',
46 'skip_download': True,
49 _BITRATES
= [256, 512, 1024, 1536, 2560]
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)
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))
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']
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
))
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',
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()
97 'url': progressive_base_url
+ 'mp4',
98 'format_id': m3u8_format
['format_id'].replace('hls', 'mp4'),
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'),
109 formats
.extend([web_f
, mp4_f
])
111 for bitrate
in self
._BITRATES
:
112 for ext
in ('web', 'mp4'):
114 'format_id': '%s-%s' % (ext
, bitrate
),
115 'url': '%spublic/%s_%d.%s' % (progressive_base
, path
, bitrate
, ext
),
119 self
._sort
_formats
(formats
)
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
)),