l1ving_youtube-dl/youtube_dl/extractor/nhl.py

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)