diff options
Diffstat (limited to 'youtube_dl/extractor/scrippsnetworks.py')
| -rw-r--r-- | youtube_dl/extractor/scrippsnetworks.py | 147 |
1 files changed, 103 insertions, 44 deletions
diff --git a/youtube_dl/extractor/scrippsnetworks.py b/youtube_dl/extractor/scrippsnetworks.py index 597d6f5..4023aee 100644 --- a/youtube_dl/extractor/scrippsnetworks.py +++ b/youtube_dl/extractor/scrippsnetworks.py @@ -1,60 +1,119 @@ # coding: utf-8 from __future__ import unicode_literals -from .adobepass import AdobePassIE +import json +import hashlib +import re + +from .aws import AWSIE +from .anvato import AnvatoIE from ..utils import ( - int_or_none, smuggle_url, - update_url_query, + urlencode_postdata, + xpath_text, ) -class ScrippsNetworksWatchIE(AdobePassIE): +class ScrippsNetworksWatchIE(AWSIE): IE_NAME = 'scrippsnetworks:watch' - _VALID_URL = r'https?://watch\.(?:hgtv|foodnetwork|travelchannel|diynetwork|cookingchanneltv)\.com/player\.[A-Z0-9]+\.html#(?P<id>\d+)' - _TEST = { - 'url': 'http://watch.hgtv.com/player.HNT.html#0256538', + _VALID_URL = r'''(?x) + https?:// + watch\. + (?P<site>hgtv|foodnetwork|travelchannel|diynetwork|cookingchanneltv|geniuskitchen)\.com/ + (?: + player\.[A-Z0-9]+\.html\#| + show/(?:[^/]+/){2}| + player/ + ) + (?P<id>\d+) + ''' + _TESTS = [{ + 'url': 'http://watch.hgtv.com/show/HGTVE/Best-Ever-Treehouses/2241515/Best-Ever-Treehouses/', 'md5': '26545fd676d939954c6808274bdb905a', 'info_dict': { - 'id': '0256538', + 'id': '4173834', 'ext': 'mp4', - 'title': 'Seeking a Wow House', - 'description': 'Buyers retiring in Palm Springs, California, want a modern house with major wow factor. They\'re also looking for a pool and a large, open floorplan with tall windows looking out at the views.', - 'uploader': 'SCNI', - 'upload_date': '20170207', - 'timestamp': 1486450493, + 'title': 'Best Ever Treehouses', + 'description': "We're searching for the most over the top treehouses.", + 'uploader': 'ANV', + 'upload_date': '20170922', + 'timestamp': 1506056400, + }, + 'params': { + 'skip_download': True, }, - 'skip': 'requires TV provider authentication', + 'add_ie': [AnvatoIE.ie_key()], + }, { + 'url': 'http://watch.diynetwork.com/show/DSAL/Salvage-Dawgs/2656646/Covington-Church/', + 'only_matching': True, + }, { + 'url': 'http://watch.diynetwork.com/player.HNT.html#2656646', + 'only_matching': True, + }, { + 'url': 'http://watch.geniuskitchen.com/player/3787617/Ample-Hills-Ice-Cream-Bike/', + 'only_matching': True, + }] + + _SNI_TABLE = { + 'hgtv': 'hgtv', + 'diynetwork': 'diy', + 'foodnetwork': 'food', + 'cookingchanneltv': 'cook', + 'travelchannel': 'trav', + 'geniuskitchen': 'genius', } + _AWS_API_KEY = 'E7wSQmq0qK6xPrF13WmzKiHo4BQ7tip4pQcSXVl1' + _AWS_PROXY_HOST = 'web.api.video.snidigital.com' + + _AWS_USER_AGENT = 'aws-sdk-js/2.80.0 callback' + def _real_extract(self, url): - video_id = self._match_id(url) - webpage = self._download_webpage(url, video_id) - channel = self._parse_json(self._search_regex( - r'"channels"\s*:\s*(\[.+\])', - webpage, 'channels'), video_id)[0] - video_data = next(v for v in channel['videos'] if v.get('nlvid') == video_id) - title = video_data['title'] - release_url = video_data['releaseUrl'] - if video_data.get('restricted'): - requestor_id = self._search_regex( - r'requestorId\s*=\s*"([^"]+)";', webpage, 'requestor id') - resource = self._get_mvpd_resource( - requestor_id, title, video_id, - video_data.get('ratings', [{}])[0].get('rating')) - auth = self._extract_mvpd_auth( - url, video_id, requestor_id, resource) - release_url = update_url_query(release_url, {'auth': auth}) - - return { - '_type': 'url_transparent', - 'id': video_id, - 'title': title, - 'url': smuggle_url(release_url, {'force_smil_url': True}), - 'description': video_data.get('description'), - 'thumbnail': video_data.get('thumbnailUrl'), - 'series': video_data.get('showTitle'), - 'season_number': int_or_none(video_data.get('season')), - 'episode_number': int_or_none(video_data.get('episodeNumber')), - 'ie_key': 'ThePlatform', - } + mobj = re.match(self._VALID_URL, url) + site_id, video_id = mobj.group('site', 'id') + + aws_identity_id_json = json.dumps({ + 'IdentityId': '%s:7655847c-0ae7-4d9b-80d6-56c062927eb3' % self._AWS_REGION + }).encode('utf-8') + token = self._download_json( + 'https://cognito-identity.%s.amazonaws.com/' % self._AWS_REGION, video_id, + data=aws_identity_id_json, + headers={ + 'Accept': '*/*', + 'Content-Type': 'application/x-amz-json-1.1', + 'Referer': url, + 'X-Amz-Content-Sha256': hashlib.sha256(aws_identity_id_json).hexdigest(), + 'X-Amz-Target': 'AWSCognitoIdentityService.GetOpenIdToken', + 'X-Amz-User-Agent': self._AWS_USER_AGENT, + })['Token'] + + sts = self._download_xml( + 'https://sts.amazonaws.com/', video_id, data=urlencode_postdata({ + 'Action': 'AssumeRoleWithWebIdentity', + 'RoleArn': 'arn:aws:iam::710330595350:role/Cognito_WebAPIUnauth_Role', + 'RoleSessionName': 'web-identity', + 'Version': '2011-06-15', + 'WebIdentityToken': token, + }), headers={ + 'Referer': url, + 'X-Amz-User-Agent': self._AWS_USER_AGENT, + 'Content-Type': 'application/x-www-form-urlencoded; charset=utf-8', + }) + + def get(key): + return xpath_text( + sts, './/{https://sts.amazonaws.com/doc/2011-06-15/}%s' % key, + fatal=True) + + mcp_id = self._aws_execute_api({ + 'uri': '/1/web/brands/%s/episodes/scrid/%s' % (self._SNI_TABLE[site_id], video_id), + 'access_key': get('AccessKeyId'), + 'secret_key': get('SecretAccessKey'), + 'session_token': get('SessionToken'), + }, video_id)['results'][0]['mcpId'] + + return self.url_result( + smuggle_url( + 'anvato:anvato_scripps_app_web_prod_0837996dbe373629133857ae9eb72e740424d80a:%s' % mcp_id, + {'geo_countries': ['US']}), + AnvatoIE.ie_key(), video_id=mcp_id) |