Joshua McKinney 34266aa604 [nhl] Cache authentication between runs
This hopefully solves the sign-on restriction error messages when a user
attempts to login too many times.

Refactored API calls to a NHLApi class and reduced repetition
Made timestamp an optional field
Made non-optional parsing use [] instead of get() (e.g. everything that
produces the title / url / id)
2017-01-26 05:19:47 -06:00

555 lines
22 KiB
Python

from __future__ import unicode_literals
import base64
import re
import json
import os
import time
from .common import InfoExtractor
from ..compat import (
compat_cookies,
compat_urlparse,
compat_urllib_parse_urlencode,
compat_urllib_parse_urlparse,
compat_str,
)
from ..utils import (
unified_strdate,
determine_ext,
ExtractorError,
int_or_none,
parse_iso8601,
parse_duration,
sanitized_Request,
)
class NHLBaseInfoExtractor(InfoExtractor):
@staticmethod
def _fix_json(json_string):
return json_string.replace('\\\'', '\'')
def _real_extract_video(self, video_id):
vid_parts = video_id.split(',')
if len(vid_parts) == 3:
video_id = '%s0%s%s-X-h' % (vid_parts[0][:4], vid_parts[1], vid_parts[2].rjust(4, '0'))
json_url = 'http://video.nhl.com/videocenter/servlets/playlist?ids=%s&format=json' % video_id
data = self._download_json(
json_url, video_id, transform_source=self._fix_json)
return self._extract_video(data[0])
def _extract_video(self, info):
video_id = info['id']
self.report_extraction(video_id)
initial_video_url = info['publishPoint']
if info['formats'] == '1':
parsed_url = compat_urllib_parse_urlparse(initial_video_url)
filename, ext = os.path.splitext(parsed_url.path)
path = '%s_sd%s' % (filename, ext)
data = compat_urllib_parse_urlencode({
'type': 'fvod',
'path': compat_urlparse.urlunparse(parsed_url[:2] + (path,) + parsed_url[3:])
})
path_url = 'http://video.nhl.com/videocenter/servlets/encryptvideopath?' + data
path_doc = self._download_xml(
path_url, video_id, 'Downloading final video url')
video_url = path_doc.find('path').text
else:
video_url = initial_video_url
join = compat_urlparse.urljoin
ret = {
'id': video_id,
'title': info['name'],
'url': video_url,
'description': info['description'],
'duration': int(info['duration']),
'thumbnail': join(join(video_url, '/u/'), info['bigImage']),
'upload_date': unified_strdate(info['releaseDate'].split('.')[0]),
}
if video_url.startswith('rtmp:'):
mobj = re.match(r'(?P<tc_url>rtmp://[^/]+/(?P<app>[a-z0-9/]+))/(?P<play_path>mp4:.*)', video_url)
ret.update({
'tc_url': mobj.group('tc_url'),
'play_path': mobj.group('play_path'),
'app': mobj.group('app'),
'no_resume': True,
})
return ret
class NHLVideocenterIE(NHLBaseInfoExtractor):
IE_NAME = 'nhl.com:videocenter'
_VALID_URL = r'https?://video(?P<team>\.[^.]*)?\.nhl\.com/videocenter/(?:console|embed)?(?:\?(?:.*?[?&])?)(?:id|hlg|playlist)=(?P<id>[-0-9a-zA-Z,]+)'
_TESTS = [{
'url': 'http://video.canucks.nhl.com/videocenter/console?catid=6?id=453614',
'md5': 'db704a4ea09e8d3988c85e36cc892d09',
'info_dict': {
'id': '453614',
'ext': 'mp4',
'title': 'Quick clip: Weise 4-3 goal vs Flames',
'description': 'Dale Weise scores his first of the season to put the Canucks up 4-3.',
'duration': 18,
'upload_date': '20131006',
},
}, {
'url': 'http://video.nhl.com/videocenter/console?id=2014020024-628-h',
'md5': 'd22e82bc592f52d37d24b03531ee9696',
'info_dict': {
'id': '2014020024-628-h',
'ext': 'mp4',
'title': 'Alex Galchenyuk Goal on Ray Emery (14:40/3rd)',
'description': 'Home broadcast - Montreal Canadiens at Philadelphia Flyers - October 11, 2014',
'duration': 0,
'upload_date': '20141011',
},
}, {
'url': 'http://video.mapleleafs.nhl.com/videocenter/console?id=58665&catid=802',
'md5': 'c78fc64ea01777e426cfc202b746c825',
'info_dict': {
'id': '58665',
'ext': 'flv',
'title': 'Classic Game In Six - April 22, 1979',
'description': 'It was the last playoff game for the Leafs in the decade, and the last time the Leafs and Habs played in the playoffs. Great game, not a great ending.',
'duration': 400,
'upload_date': '20100129'
},
}, {
'url': 'http://video.flames.nhl.com/videocenter/console?id=630616',
'only_matching': True,
}, {
'url': 'http://video.nhl.com/videocenter/?id=736722',
'only_matching': True,
}, {
'url': 'http://video.nhl.com/videocenter/console?hlg=20142015,2,299&lang=en',
'md5': '076fcb88c255154aacbf0a7accc3f340',
'info_dict': {
'id': '2014020299-X-h',
'ext': 'mp4',
'title': 'Penguins at Islanders / Game Highlights',
'description': 'Home broadcast - Pittsburgh Penguins at New York Islanders - November 22, 2014',
'duration': 268,
'upload_date': '20141122',
}
}, {
'url': 'http://video.oilers.nhl.com/videocenter/console?id=691469&catid=4',
'info_dict': {
'id': '691469',
'ext': 'mp4',
'title': 'RAW | Craig MacTavish Full Press Conference',
'description': 'Oilers GM Craig MacTavish addresses the media at Rexall Place on Friday.',
'upload_date': '20141205',
},
'params': {
'skip_download': True, # Requires rtmpdump
}
}, {
'url': 'http://video.nhl.com/videocenter/embed?playlist=836127',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
return self._real_extract_video(video_id)
class NHLNewsIE(NHLBaseInfoExtractor):
IE_NAME = 'nhl.com:news'
IE_DESC = 'NHL news'
_VALID_URL = r'https?://(?:.+?\.)?nhl\.com/(?:ice|club)/news\.html?(?:\?(?:.*?[?&])?)id=(?P<id>[-0-9a-zA-Z]+)'
_TESTS = [{
'url': 'http://www.nhl.com/ice/news.htm?id=750727',
'md5': '4b3d1262e177687a3009937bd9ec0be8',
'info_dict': {
'id': '736722',
'ext': 'mp4',
'title': 'Cal Clutterbuck has been fined $2,000',
'description': 'md5:45fe547d30edab88b23e0dd0ab1ed9e6',
'duration': 37,
'upload_date': '20150128',
},
}, {
# iframe embed
'url': 'http://sabres.nhl.com/club/news.htm?id=780189',
'md5': '9f663d1c006c90ac9fb82777d4294e12',
'info_dict': {
'id': '836127',
'ext': 'mp4',
'title': 'Morning Skate: OTT vs. BUF (9/23/15)',
'description': "Brian Duff chats with Tyler Ennis prior to Buffalo's first preseason home game.",
'duration': 93,
'upload_date': '20150923',
},
}]
def _real_extract(self, url):
news_id = self._match_id(url)
webpage = self._download_webpage(url, news_id)
video_id = self._search_regex(
[r'pVid(\d+)', r"nlid\s*:\s*'(\d+)'",
r'<iframe[^>]+src=["\']https?://video.*?\.nhl\.com/videocenter/embed\?.*\bplaylist=(\d+)'],
webpage, 'video id')
return self._real_extract_video(video_id)
class NHLVideocenterCategoryIE(NHLBaseInfoExtractor):
IE_NAME = 'nhl.com:videocenter:category'
IE_DESC = 'NHL videocenter category'
_VALID_URL = r'https?://video\.(?P<team>[^.]*)\.nhl\.com/videocenter/(console\?[^(id=)]*catid=(?P<catid>[0-9]+)(?![&?]id=).*?)?$'
_TEST = {
'url': 'http://video.canucks.nhl.com/videocenter/console?catid=999',
'info_dict': {
'id': '999',
'title': 'Highlights',
},
'playlist_count': 12,
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
team = mobj.group('team')
webpage = self._download_webpage(url, team)
cat_id = self._search_regex(
[r'var defaultCatId = "(.+?)";',
r'{statusIndex:0,index:0,.*?id:(.*?),'],
webpage, 'category id')
playlist_title = self._html_search_regex(
r'tab0"[^>]*?>(.*?)</td>',
webpage, 'playlist title', flags=re.DOTALL).lower().capitalize()
data = compat_urllib_parse_urlencode({
'cid': cat_id,
# This is the default value
'count': 12,
'ptrs': 3,
'format': 'json',
})
path = '/videocenter/servlets/browse?' + data
request_url = compat_urlparse.urljoin(url, path)
response = self._download_webpage(request_url, playlist_title)
response = self._fix_json(response)
if not response.strip():
self._downloader.report_warning('Got an empty response, trying '
'adding the "newvideos" parameter')
response = self._download_webpage(request_url + '&newvideos=true',
playlist_title)
response = self._fix_json(response)
videos = json.loads(response)
return {
'_type': 'playlist',
'title': playlist_title,
'id': cat_id,
'entries': [self._extract_video(v) for v in videos],
}
class NHLIE(InfoExtractor):
IE_NAME = 'nhl.com'
_VALID_URL = r'https?://(?:www\.)?(?P<site>nhl|wch2016)\.com/(?:[^/]+/)*c-(?P<id>\d+)'
_SITES_MAP = {
'nhl': 'nhl',
'wch2016': 'wch',
}
_TESTS = [{
# type=video
'url': 'https://www.nhl.com/video/anisimov-cleans-up-mess/t-277752844/c-43663503',
'md5': '0f7b9a8f986fb4b4eeeece9a56416eaf',
'info_dict': {
'id': '43663503',
'ext': 'mp4',
'title': 'Anisimov cleans up mess',
'description': 'md5:a02354acdfe900e940ce40706939ca63',
'timestamp': 1461288600,
'upload_date': '20160422',
},
}, {
# type=article
'url': 'https://www.nhl.com/news/dennis-wideman-suspended/c-278258934',
'md5': '1f39f4ea74c1394dea110699a25b366c',
'info_dict': {
'id': '40784403',
'ext': 'mp4',
'title': 'Wideman suspended by NHL',
'description': 'Flames defenseman Dennis Wideman was banned 20 games for violation of Rule 40 (Physical Abuse of Officials)',
'upload_date': '20160204',
'timestamp': 1454544904,
},
}, {
# Some m3u8 URLs are invalid (https://github.com/rg3/youtube-dl/issues/10713)
'url': 'https://www.nhl.com/predators/video/poile-laviolette-on-subban-trade/t-277437416/c-44315003',
'md5': '50b2bb47f405121484dda3ccbea25459',
'info_dict': {
'id': '44315003',
'ext': 'mp4',
'title': 'Poile, Laviolette on Subban trade',
'description': 'General manager David Poile and head coach Peter Laviolette share their thoughts on acquiring P.K. Subban from Montreal (06/29/16)',
'timestamp': 1467242866,
'upload_date': '20160629',
},
}, {
'url': 'https://www.wch2016.com/video/caneur-best-of-game-2-micd-up/t-281230378/c-44983703',
'only_matching': True,
}, {
'url': 'https://www.wch2016.com/news/3-stars-team-europe-vs-team-canada/c-282195068',
'only_matching': True,
}]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
tmp_id, site = mobj.group('id'), mobj.group('site')
video_data = self._download_json(
'https://nhl.bamcontent.com/%s/id/v1/%s/details/web-v1.json'
% (self._SITES_MAP[site], tmp_id), tmp_id)
if video_data.get('type') == 'article':
video_data = video_data['media']
video_id = compat_str(video_data['id'])
title = video_data['title']
formats = []
for playback in video_data.get('playbacks', []):
playback_url = playback.get('url')
if not playback_url:
continue
ext = determine_ext(playback_url)
if ext == 'm3u8':
m3u8_formats = self._extract_m3u8_formats(
playback_url, video_id, 'mp4', 'm3u8_native',
m3u8_id=playback.get('name', 'hls'), fatal=False)
self._check_formats(m3u8_formats, video_id)
formats.extend(m3u8_formats)
else:
height = int_or_none(playback.get('height'))
formats.append({
'format_id': playback.get('name', 'http' + ('-%dp' % height if height else '')),
'url': playback_url,
'width': int_or_none(playback.get('width')),
'height': height,
})
self._sort_formats(formats, ('preference', 'width', 'height', 'tbr', 'format_id'))
thumbnails = []
for thumbnail_id, thumbnail_data in video_data.get('image', {}).get('cuts', {}).items():
thumbnail_url = thumbnail_data.get('src')
if not thumbnail_url:
continue
thumbnails.append({
'id': thumbnail_id,
'url': thumbnail_url,
'width': int_or_none(thumbnail_data.get('width')),
'height': int_or_none(thumbnail_data.get('height')),
})
return {
'id': video_id,
'title': title,
'description': video_data.get('description'),
'timestamp': parse_iso8601(video_data.get('date')),
'duration': parse_duration(video_data.get('duration')),
'thumbnails': thumbnails,
'formats': formats,
}
class NHLApi:
def __init__(self, extractor, auth=None):
self.extractor = extractor
self.auth = auth
if auth:
extractor.to_screen("Using cached credentials. Use the --rm-cache-dir option to remove.")
cookie = compat_cookies.SimpleCookie(auth.encode('utf8', 'replace'))
auth_cookie = cookie['Authorization']
# TODO handle cookie expiry
extractor._set_cookie('nhl.com', 'Authorization', auth_cookie.value)
def login(self, username, password, auth_provider='nhl'):
if auth_provider not in ['nhl', 'rogers']:
raise ExtractorError('Unknown authentication provider: %s. Valid values are nhl, rogers' % auth_provider)
access_token = self._get_oauth_access_token()
if auth_provider == 'nhl':
url = 'https://gateway.web.nhl.com/ws/subscription/flow/nhlPurchase.login'
credentials = {
'nhlCredentials': {
'email': username,
'password': password,
}
}
referrer = 'https://www.nhl.com/login/nhl'
elif auth_provider == 'rogers':
url = 'https://activation-rogers.svc.nhl.com/ws/subscription/flow/rogers.login-check'
credentials = {
'rogerCredentials': {
'email': username,
'password': password,
}
}
referrer = 'https://www.nhl.com/login/rogers'
login_request = sanitized_Request(
url,
data=json.dumps(credentials, sort_keys=True).encode('utf-8'),
headers={
'Referer': referrer,
'Accept': 'application/json, text/javascript, */*; q=0.01',
'Authorization': access_token,
'Content-Type': 'application/json'
})
self.extractor._download_webpage(
login_request, None, 'Logging in', 'Unable to log in')
# TODO this doesn't extract the cookie expiry from the cookie correctly
self.auth = self.extractor._get_cookies('http://nhl.com').get('Authorization').output()
def _get_oauth_access_token(self):
authorization = base64.b64encode(
'web_nhl-v1.0.0:2d1d846ea3b194a18ef40ac9fbce97e3'.encode('utf-8')
).decode('ascii')
oauth_request = sanitized_Request(
'https://user.svc.nhl.com/oauth/token?grant_type=client_credentials',
data='',
headers={
'Referer': 'https://www.nhl.com/login',
'Accept': 'application/json, text/javascript, */*; q=0.01',
'Authorization': 'Basic %s' % authorization,
'Content-Type': 'application/json',
})
oauth_response = self.extractor._download_json(
oauth_request,
None, # video_id
'Requesting OAuth access token',
'Unable to get OAuth access token')
return oauth_response['access_token']
def get_game_data(self, video_id, game_id):
game_data_url = 'https://statsapi.web.nhl.com/api/v1/schedule?gamePk=%s&expand=schedule.game.content.media.milestones&expand=schedule.game.content.media.epg&expand=schedule.venue' % game_id
return self.extractor._download_json(
game_data_url,
video_id,
'Downloading game data',
'Unable to download game data')
def get_stream_data(self, video_id):
stream_data_url = 'https://mf.svc.nhl.com/ws/media/mf/v2.4/stream?contentId=%s&playbackScenario=HTTP_CLOUD_WIRED_WEB&sessionKey=%s&auth=response&format=json&platform=WEB_MEDIAPLAYER&_=%s000'
session_key = 'abcdefghijklmnop'
timestamp = int(time.time())
url = stream_data_url % (video_id, session_key, timestamp)
return self.extractor._download_json(url, video_id, 'Downloading stream data', 'Unable to download stream data')
class NHLTVIE(InfoExtractor):
IE_NAME = 'nhl.com:nhltv'
_VALID_URL = r'https?://(?:www\.)?nhl.com/tv/(?P<gameId>\d+)(/[^/]+)*(/(?P<id>\d+))?'
_NETRC_MACHINE = 'nhltv'
_NHLTV_CACHE = 'nhltv'
_TESTS = [{
# This is a free video that anyone with an NHL TV login can access
'url': 'https://www.nhl.com/tv/2016020321/221-1003765/46561403',
'md5': '34d9518c495ebdad947b9723b5a7c9a9',
'info_dict': {
'id': '46561403',
'ext': 'ts',
'title': '2016-11-26: Anaheim Ducks @ San Jose Sharks (AWAY feed)',
'timestamp': 1480217427,
},
'skip': 'requires a login to NHL TV, and takes a long time to run as the video is 3h+',
'params': {
'usenetrc': True,
'format': '[width=400]',
'hls_use_mpegts': True,
}
}, {
'url': 'https://www.nhl.com/tv/2016020362/221-1003808',
'only_matching': True,
}, {
'url': 'https://www.nhl.com/tv/2016020373',
'only_matching': True,
}]
def _real_initialize(self):
auth = self._downloader.cache.load(self._NHLTV_CACHE, 'auth')
self.api = NHLApi(self, auth)
if auth is None:
self._login()
def _login(self):
(username, password) = self._get_login_info()
if username is None:
self.raise_login_required()
auth_provider = self._get_auth_provider() or 'nhl'
self.report_login()
self.api.login(username, password, auth_provider)
self._downloader.cache.store(self._NHLTV_CACHE, 'auth', self.api.auth)
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id, game_id = mobj.group('id'), mobj.group('gameId')
# At this point we may have a game_id without a video_id. The next call
# ensures that we get a video_id for the desired game.
video_id, title, timestamp = self.extract_game_info(video_id, game_id)
m3u8_url, media_auth = self.extract_playlist_url_and_auth(video_id)
m3u8_url = self.get_60fps_playlist(m3u8_url)
# media auth cookie authenticates the specific download url
self._set_cookie('nhl.com', 'mediaAuth_v2', media_auth)
formats = self._extract_m3u8_formats(m3u8_url, video_id, 'ts', m3u8_id='hls')
self._check_formats(formats, video_id)
self._sort_formats(formats, ('preference', 'width', 'height', 'tbr', 'format_id'))
return {
'id': video_id,
'title': title,
'timestamp': timestamp,
'formats': formats,
}
def extract_game_info(self, video_id, game_id):
"""calls the nhl api to get the video_id, title, and optionally the timestamp of the start of the game"""
game_data = self.api.get_game_data(video_id, game_id)
game_date = game_data['dates'][0]
date = game_date['date'] # yyyy-mm-dd
game = game_date['games'][0]
teams = game['teams']
away = teams['away']['team']['name']
home = teams['home']['team']['name']
feed_type = "UNKNOWN"
media = game['content']['media']
for epg_item in media['epg']:
# ignore audio feeds and highlights
if epg_item.get('title') != 'NHLTV':
continue
for item in epg_item.get('items', []):
# get the specified video feed based on the video id or the
# first video if there no video id is specified
if item.get('mediaPlaybackId') == video_id or video_id is None:
video_id = item.get('mediaPlaybackId')
feed_type = item.get('mediaFeedType') # HOME / AWAY
title = "%s: %s @ %s (%s feed)" % (date, away, home, feed_type)
streamStart = media.get('milestones', {}).get('streamStart')
if streamStart:
timestamp = parse_iso8601(streamStart)
return (video_id, title, timestamp)
def extract_playlist_url_and_auth(self, video_id):
"""Calls the nhl api to get the url of the video and an authorization key"""
stream_data = self.api.get_stream_data(video_id)
status_code = stream_data['status_code']
if status_code != 1:
# e.g. Media not found, Too many sign ons, etc.
status_message = stream_data['status_message']
raise ExtractorError(status_message, expected=True)
m3u8_url = stream_data['user_verified_event'][0]['user_verified_content'][0]['user_verified_media_item'][0]['url']
media_auth = stream_data['session_info']['sessionAttributes'][0]['attributeValue']
return (m3u8_url, media_auth)
def get_60fps_playlist(self, url):
"""Returns a modified url that adds a 720p 60fps broadcast"""
return re.sub('_wired_web', '_wired60', url)