]> jfr.im git - yt-dlp.git/blame - youtube_dl/extractor/lego.py
release 2016.10.07
[yt-dlp.git] / youtube_dl / extractor / lego.py
CommitLineData
185744f9
RA
1# coding: utf-8
2from __future__ import unicode_literals
3
4from .common import InfoExtractor
5from ..compat import compat_str
6from ..utils import (
7 unescapeHTML,
8 int_or_none,
9)
10
11
12class LEGOIE(InfoExtractor):
13 _VALID_URL = r'https?://(?:www\.)?lego\.com/(?:[^/]+/)*videos/(?:[^/]+/)*[^/?#]+-(?P<id>[0-9a-f]+)'
14 _TEST = {
15 'url': 'http://www.lego.com/en-us/videos/themes/club/blocumentary-kawaguchi-55492d823b1b4d5e985787fa8c2973b1',
16 'md5': 'f34468f176cfd76488767fc162c405fa',
17 'info_dict': {
18 'id': '55492d823b1b4d5e985787fa8c2973b1',
19 'ext': 'mp4',
20 'title': 'Blocumentary Great Creations: Akiyuki Kawaguchi',
21 }
22 }
23 _BITRATES = [256, 512, 1024, 1536, 2560]
24
25 def _real_extract(self, url):
26 video_id = self._match_id(url)
27 webpage = self._download_webpage(
28 'http://www.lego.com/en-US/mediaplayer/video/' + video_id, video_id)
29 title = self._search_regex(r'<title>(.+?)</title>', webpage, 'title')
30 video_data = self._parse_json(unescapeHTML(self._search_regex(
31 r"video='([^']+)'", webpage, 'video data')), video_id)
32 progressive_base = self._search_regex(
33 r'data-video-progressive-url="([^"]+)"',
34 webpage, 'progressive base', default='https://lc-mediaplayerns-live-s.legocdn.com/')
35 streaming_base = self._search_regex(
36 r'data-video-streaming-url="([^"]+)"',
37 webpage, 'streaming base', default='http://legoprod-f.akamaihd.net/')
38 item_id = video_data['ItemId']
39
40 net_storage_path = video_data.get('NetStoragePath') or '/'.join([item_id[:2], item_id[2:4]])
41 base_path = '_'.join([item_id, video_data['VideoId'], video_data['Locale'], compat_str(video_data['VideoVersion'])])
42 path = '/'.join([net_storage_path, base_path])
43 streaming_path = ','.join(map(lambda bitrate: compat_str(bitrate), self._BITRATES))
44
45 formats = self._extract_akamai_formats(
46 '%si/s/public/%s_,%s,.mp4.csmil/master.m3u8' % (streaming_base, path, streaming_path), video_id)
47 m3u8_formats = list(filter(
48 lambda f: f.get('protocol') == 'm3u8_native' and f.get('vcodec') != 'none' and f.get('resolution') != 'multiple',
49 formats))
50 if len(m3u8_formats) == len(self._BITRATES):
51 self._sort_formats(m3u8_formats)
52 for bitrate, m3u8_format in zip(self._BITRATES, m3u8_formats):
53 progressive_base_url = '%spublic/%s_%d.' % (progressive_base, path, bitrate)
54 mp4_f = m3u8_format.copy()
55 mp4_f.update({
56 'url': progressive_base_url + 'mp4',
57 'format_id': m3u8_format['format_id'].replace('hls', 'mp4'),
58 'protocol': 'http',
59 })
60 web_f = {
61 'url': progressive_base_url + 'webm',
62 'format_id': m3u8_format['format_id'].replace('hls', 'webm'),
63 'width': m3u8_format['width'],
64 'height': m3u8_format['height'],
65 'tbr': m3u8_format.get('tbr'),
66 'ext': 'webm',
67 }
68 formats.extend([web_f, mp4_f])
69 else:
70 for bitrate in self._BITRATES:
71 for ext in ('web', 'mp4'):
72 formats.append({
73 'format_id': '%s-%s' % (ext, bitrate),
74 'url': '%spublic/%s_%d.%s' % (progressive_base, path, bitrate, ext),
75 'tbr': bitrate,
76 'ext': ext,
77 })
78 self._sort_formats(formats)
79
80 return {
81 'id': video_id,
82 'title': title,
83 'thumbnail': video_data.get('CoverImageUrl'),
84 'duration': int_or_none(video_data.get('Length')),
85 'formats': formats,
86 }