]> jfr.im git - yt-dlp.git/blob - youtube_dl/extractor/nba.py
[nba] extract width,height and bitrate from format key
[yt-dlp.git] / youtube_dl / extractor / nba.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 int_or_none,
9 )
10
11
12 class NBAIE(InfoExtractor):
13 _VALID_URL = r'https?://(?:watch\.|www\.)?nba\.com/(?:nba/)?video/(?P<id>[^?]*?)/?(?:/index\.html)?(?:\?.*)?$'
14 _TESTS = [{
15 'url': 'http://www.nba.com/video/games/nets/2012/12/04/0021200253-okc-bkn-recap.nba/index.html',
16 'md5': '9d902940d2a127af3f7f9d2f3dc79c96',
17 'info_dict': {
18 'id': '0021200253-okc-bkn-recap',
19 'ext': 'mp4',
20 'title': 'Thunder vs. Nets',
21 'description': 'Kevin Durant scores 32 points and dishes out six assists as the Thunder beat the Nets in Brooklyn.',
22 'duration': 181,
23 'timestamp': 1354638466,
24 'upload_date': '20121204',
25 },
26 }, {
27 'url': 'http://www.nba.com/video/games/hornets/2014/12/05/0021400276-nyk-cha-play5.nba/',
28 'only_matching': True,
29 },{
30 'url': 'http://watch.nba.com/nba/video/channels/playoffs/2015/05/20/0041400301-cle-atl-recap.nba',
31 'md5': 'b2b39b81cf28615ae0c3360a3f9668c4',
32 'info_dict': {
33 'id': '0041400301-cle-atl-recap',
34 'ext': 'mp4',
35 'title': 'Hawks vs. Cavaliers Game 1',
36 'description': 'md5:8094c3498d35a9bd6b1a8c396a071b4d',
37 'duration': 228,
38 'timestamp': 1432134543,
39 'upload_date': '20150520',
40 }
41 }]
42
43 def _real_extract(self, url):
44 video_id = self._match_id(url)
45 video_info = self._download_xml('http://www.nba.com/video/%s.xml' % video_id, video_id)
46 video_id = video_info.find('slug').text
47 title = video_info.find('headline').text
48 description = video_info.find('description').text
49 duration = parse_duration(video_info.find('length').text)
50 timestamp = int_or_none(video_info.find('dateCreated').attrib.get('uts'))
51
52 thumbnails = []
53 for image in video_info.find('images'):
54 thumbnails.append({
55 'id': image.attrib.get('cut'),
56 'url': image.text,
57 'width': int_or_none(image.attrib.get('width')),
58 'height': int_or_none(image.attrib.get('height')),
59 })
60
61 formats = []
62 for video_file in video_info.find('files').iter('file'):
63 video_url = video_file.text
64 if video_url.startswith('/'):
65 continue
66 if video_url.endswith('.m3u8'):
67 formats.extend(self._extract_m3u8_formats(video_url, video_id))
68 elif video_url.endswith('.f4m'):
69 formats.extend(self._extract_f4m_formats(video_url + '?hdcore=3.4.1.1', video_id))
70 else:
71 key = video_file.attrib.get('bitrate')
72 width, height, bitrate = re.search(r'(\d+)x(\d+)(?:_(\d+))?', key).groups()
73 formats.append({
74 'format_id': key,
75 'url': video_url,
76 'width': int_or_none(width),
77 'height': int_or_none(height),
78 'tbr': int_or_none(bitrate),
79 })
80 self._sort_formats(formats)
81
82 return {
83 'id': video_id,
84 'title': title,
85 'description': description,
86 'duration': duration,
87 'timestamp': timestamp,
88 'thumbnails': thumbnails,
89 'formats': formats,
90 }