2 from __future__
import unicode_literals
6 from .common
import InfoExtractor
9 compat_urllib_parse_urlparse
,
15 class NFLIE(InfoExtractor
):
17 _VALID_URL
= r
'''(?x)https?://
18 (?P<host>(?:www\.)?(?:nfl\.com|.*?\.clubs\.nfl\.com))/
20 (?P<id>(?:\d[a-z]{2}\d{13}|\w{8}\-(?:\w{4}\-){3}\w{12}))'''
23 'url': 'http://www.nfl.com/videos/nfl-game-highlights/0ap3000000398478/Week-3-Redskins-vs-Eagles-highlights',
24 'md5': '394ef771ddcd1354f665b471d78ec4c6',
26 'id': '0ap3000000398478',
28 'title': 'Week 3: Redskins vs. Eagles highlights',
29 'description': 'md5:56323bfb0ac4ee5ab24bd05fdf3bf478',
30 'upload_date': '20140921',
31 'timestamp': 1411337580,
32 'thumbnail': 're:^https?://.*\.jpg$',
36 'url': 'http://prod.www.steelers.clubs.nfl.com/video-and-audio/videos/LIVE_Post_Game_vs_Browns/9d72f26a-9e2b-4718-84d3-09fb4046c266',
37 'md5': 'cf85bdb4bc49f6e9d3816d130c78279c',
39 'id': '9d72f26a-9e2b-4718-84d3-09fb4046c266',
41 'title': 'LIVE: Post Game vs. Browns',
42 'description': 'md5:6a97f7e5ebeb4c0e69a418a89e0636e8',
43 'upload_date': '20131229',
44 'timestamp': 1388354455,
45 'thumbnail': 're:^https?://.*\.jpg$',
51 def prepend_host(host
, url
):
52 if not url
.startswith('http'):
53 if not url
.startswith('/'):
55 url
= 'http://{0:}{1:}'.format(host
, url
)
59 def format_from_stream(stream
, protocol
, host
, path_prefix
='',
60 preference
=0, note
=None):
61 url
= '{protocol:}://{host:}/{prefix:}{path:}'.format(
65 path
=stream
.get('path'),
69 'vbr': int_or_none(stream
.get('rate', 0), 1000),
70 'preference': preference
,
74 def _real_extract(self
, url
):
75 mobj
= re
.match(self
._VALID
_URL
, url
)
76 video_id
, host
= mobj
.group('id'), mobj
.group('host')
78 webpage
= self
._download
_webpage
(url
, video_id
)
80 config_url
= NFLIE
.prepend_host(host
, self
._search
_regex
(
81 r
'(?:config|configURL)\s*:\s*"([^"]+)"', webpage
, 'config URL'))
82 config
= self
._download
_json
(config_url
, video_id
,
83 note
='Downloading player config')
84 url_template
= NFLIE
.prepend_host(
85 host
, '{contentURLTemplate:}'.format(**config
))
86 video_data
= self
._download
_json
(
87 url_template
.format(id=video_id
), video_id
)
90 cdn_data
= video_data
.get('cdnData', {})
91 streams
= cdn_data
.get('bitrateInfo', [])
92 if cdn_data
.get('format') == 'EXTERNAL_HTTP_STREAM':
93 parts
= compat_urllib_parse_urlparse(cdn_data
.get('uri'))
94 protocol
, host
= parts
.scheme
, parts
.netloc
95 for stream
in streams
:
97 NFLIE
.format_from_stream(stream
, protocol
, host
))
99 cdns
= config
.get('cdns')
101 raise ExtractorError('Failed to get CDN data', expected
=True)
103 for name
, cdn
in cdns
.items():
104 # LimeLight streams don't seem to work
105 if cdn
.get('name') == 'LIMELIGHT':
108 protocol
= cdn
.get('protocol')
109 host
= remove_end(cdn
.get('host', ''), '/')
110 if not (protocol
and host
):
113 prefix
= cdn
.get('pathprefix', '')
114 if prefix
and not prefix
.endswith('/'):
115 prefix
= '%s/' % prefix
118 if protocol
== 'rtmp':
120 elif 'prog' in name
.lower():
123 for stream
in streams
:
125 NFLIE
.format_from_stream(stream
, protocol
, host
,
126 prefix
, preference
, name
))
128 self
._sort
_formats
(formats
)
131 for q
in ('xl', 'l', 'm', 's', 'xs'):
132 thumbnail
= video_data
.get('imagePaths', {}).get(q
)
138 'title': video_data
.get('headline'),
140 'description': video_data
.get('caption'),
141 'duration': video_data
.get('duration'),
142 'thumbnail': thumbnail
,
143 'timestamp': int_or_none(video_data
.get('posted'), 1000),