1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
|
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..compat import (
compat_urllib_parse_urlparse,
)
from ..utils import (
ExtractorError,
int_or_none,
remove_end,
)
class NFLIE(InfoExtractor):
IE_NAME = 'nfl.com'
_VALID_URL = r'''(?x)
https?://
(?P<host>
(?:www\.)?
(?:
(?:
nfl|
buffalobills|
miamidolphins|
patriots|
newyorkjets|
baltimoreravens|
bengals|
clevelandbrowns|
steelers|
houstontexans|
colts|
jaguars|
titansonline|
denverbroncos|
kcchiefs|
raiders|
chargers|
dallascowboys|
giants|
philadelphiaeagles|
redskins|
chicagobears|
detroitlions|
packers|
vikings|
atlantafalcons|
panthers|
neworleanssaints|
buccaneers|
azcardinals|
stlouisrams|
49ers|
seahawks
)\.com|
.+?\.clubs\.nfl\.com
)
)/
(?:.+?/)*
(?P<id>(?:[a-z0-9]{16}|\w{8}\-(?:\w{4}\-){3}\w{12}))
'''
_TESTS = [{
'url': 'http://www.nfl.com/videos/nfl-game-highlights/0ap3000000398478/Week-3-Redskins-vs-Eagles-highlights',
'md5': '394ef771ddcd1354f665b471d78ec4c6',
'info_dict': {
'id': '0ap3000000398478',
'ext': 'mp4',
'title': 'Week 3: Redskins vs. Eagles highlights',
'description': 'md5:56323bfb0ac4ee5ab24bd05fdf3bf478',
'upload_date': '20140921',
'timestamp': 1411337580,
'thumbnail': 're:^https?://.*\.jpg$',
}
}, {
'url': 'http://prod.www.steelers.clubs.nfl.com/video-and-audio/videos/LIVE_Post_Game_vs_Browns/9d72f26a-9e2b-4718-84d3-09fb4046c266',
'md5': 'cf85bdb4bc49f6e9d3816d130c78279c',
'info_dict': {
'id': '9d72f26a-9e2b-4718-84d3-09fb4046c266',
'ext': 'mp4',
'title': 'LIVE: Post Game vs. Browns',
'description': 'md5:6a97f7e5ebeb4c0e69a418a89e0636e8',
'upload_date': '20131229',
'timestamp': 1388354455,
'thumbnail': 're:^https?://.*\.jpg$',
}
}, {
'url': 'http://www.nfl.com/news/story/0ap3000000467586/article/patriots-seahawks-involved-in-lategame-skirmish',
'info_dict': {
'id': '0ap3000000467607',
'ext': 'mp4',
'title': 'Frustrations flare on the field',
'description': 'Emotions ran high at the end of the Super Bowl on both sides of the ball after a dramatic finish.',
'timestamp': 1422850320,
'upload_date': '20150202',
},
}, {
'url': 'http://www.nfl.com/videos/nfl-network-top-ten/09000d5d810a6bd4/Top-10-Gutsiest-Performances-Jack-Youngblood',
'only_matching': True,
}, {
'url': 'http://www.buffalobills.com/video/videos/Rex_Ryan_Show_World_Wide_Rex/b1dcfab2-3190-4bb1-bfc0-d6e603d6601a',
'only_matching': True,
}]
@staticmethod
def prepend_host(host, url):
if not url.startswith('http'):
if not url.startswith('/'):
url = '/%s' % url
url = 'http://{0:}{1:}'.format(host, url)
return url
@staticmethod
def format_from_stream(stream, protocol, host, path_prefix='',
preference=0, note=None):
url = '{protocol:}://{host:}/{prefix:}{path:}'.format(
protocol=protocol,
host=host,
prefix=path_prefix,
path=stream.get('path'),
)
return {
'url': url,
'vbr': int_or_none(stream.get('rate', 0), 1000),
'preference': preference,
'format_note': note,
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id, host = mobj.group('id'), mobj.group('host')
webpage = self._download_webpage(url, video_id)
config_url = NFLIE.prepend_host(host, self._search_regex(
r'(?:config|configURL)\s*:\s*"([^"]+)"', webpage, 'config URL',
default='static/content/static/config/video/config.json'))
# For articles, the id in the url is not the video id
video_id = self._search_regex(
r'contentId\s*:\s*"([^"]+)"', webpage, 'video id', default=video_id)
config = self._download_json(config_url, video_id,
note='Downloading player config')
url_template = NFLIE.prepend_host(
host, '{contentURLTemplate:}'.format(**config))
video_data = self._download_json(
url_template.format(id=video_id), video_id)
formats = []
cdn_data = video_data.get('cdnData', {})
streams = cdn_data.get('bitrateInfo', [])
if cdn_data.get('format') == 'EXTERNAL_HTTP_STREAM':
parts = compat_urllib_parse_urlparse(cdn_data.get('uri'))
protocol, host = parts.scheme, parts.netloc
for stream in streams:
formats.append(
NFLIE.format_from_stream(stream, protocol, host))
else:
cdns = config.get('cdns')
if not cdns:
raise ExtractorError('Failed to get CDN data', expected=True)
for name, cdn in cdns.items():
# LimeLight streams don't seem to work
if cdn.get('name') == 'LIMELIGHT':
continue
protocol = cdn.get('protocol')
host = remove_end(cdn.get('host', ''), '/')
if not (protocol and host):
continue
prefix = cdn.get('pathprefix', '')
if prefix and not prefix.endswith('/'):
prefix = '%s/' % prefix
preference = 0
if protocol == 'rtmp':
preference = -2
elif 'prog' in name.lower():
preference = 1
for stream in streams:
formats.append(
NFLIE.format_from_stream(stream, protocol, host,
prefix, preference, name))
self._sort_formats(formats)
thumbnail = None
for q in ('xl', 'l', 'm', 's', 'xs'):
thumbnail = video_data.get('imagePaths', {}).get(q)
if thumbnail:
break
return {
'id': video_id,
'title': video_data.get('headline'),
'formats': formats,
'description': video_data.get('caption'),
'duration': video_data.get('duration'),
'thumbnail': thumbnail,
'timestamp': int_or_none(video_data.get('posted'), 1000),
}
|
