Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/scrippsnetworks.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import json
   5 import hashlib
   6 import re
   7
   8 from .aws import AWSIE
   9 from .anvato import AnvatoIE
  10 from .common import InfoExtractor
  11 from ..utils import (
  12     smuggle_url,
  13     urlencode_postdata,
  14     xpath_text,
  15 )
  16
  17
  18 class ScrippsNetworksWatchIE(AWSIE):
  19     IE_NAME = 'scrippsnetworks:watch'
  20     _VALID_URL = r'''(?x)
  21                     https?://
  22                         watch\.
  23                         (?P<site>geniuskitchen)\.com/
  24                         (?:
  25                             player\.[A-Z0-9]+\.html\#|
  26                             show/(?:[^/]+/){2}|
  27                             player/
  28                         )
  29                         (?P<id>\d+)
  30                     '''
  31     _TESTS = [{
  32         'url': 'http://watch.geniuskitchen.com/player/3787617/Ample-Hills-Ice-Cream-Bike/',
  33         'info_dict': {
  34             'id': '4194875',
  35             'ext': 'mp4',
  36             'title': 'Ample Hills Ice Cream Bike',
  37             'description': 'Courtney Rada churns up a signature GK Now ice cream with The Scoopmaster.',
  38             'uploader': 'ANV',
  39             'upload_date': '20171011',
  40             'timestamp': 1507698000,
  41         },
  42         'params': {
  43             'skip_download': True,
  44         },
  45         'add_ie': [AnvatoIE.ie_key()],
  46     }]
  47
  48     _SNI_TABLE = {
  49         'geniuskitchen': 'genius',
  50     }
  51
  52     _AWS_API_KEY = 'E7wSQmq0qK6xPrF13WmzKiHo4BQ7tip4pQcSXVl1'
  53     _AWS_PROXY_HOST = 'web.api.video.snidigital.com'
  54
  55     _AWS_USER_AGENT = 'aws-sdk-js/2.80.0 callback'
  56
  57     def _real_extract(self, url):
  58         mobj = re.match(self._VALID_URL, url)
  59         site_id, video_id = mobj.group('site', 'id')
  60
  61         aws_identity_id_json = json.dumps({
  62             'IdentityId': '%s:7655847c-0ae7-4d9b-80d6-56c062927eb3' % self._AWS_REGION
  63         }).encode('utf-8')
  64         token = self._download_json(
  65             'https://cognito-identity.%s.amazonaws.com/' % self._AWS_REGION, video_id,
  66             data=aws_identity_id_json,
  67             headers={
  68                 'Accept': '*/*',
  69                 'Content-Type': 'application/x-amz-json-1.1',
  70                 'Referer': url,
  71                 'X-Amz-Content-Sha256': hashlib.sha256(aws_identity_id_json).hexdigest(),
  72                 'X-Amz-Target': 'AWSCognitoIdentityService.GetOpenIdToken',
  73                 'X-Amz-User-Agent': self._AWS_USER_AGENT,
  74             })['Token']
  75
  76         sts = self._download_xml(
  77             'https://sts.amazonaws.com/', video_id, data=urlencode_postdata({
  78                 'Action': 'AssumeRoleWithWebIdentity',
  79                 'RoleArn': 'arn:aws:iam::710330595350:role/Cognito_WebAPIUnauth_Role',
  80                 'RoleSessionName': 'web-identity',
  81                 'Version': '2011-06-15',
  82                 'WebIdentityToken': token,
  83             }), headers={
  84                 'Referer': url,
  85                 'X-Amz-User-Agent': self._AWS_USER_AGENT,
  86                 'Content-Type': 'application/x-www-form-urlencoded; charset=utf-8',
  87             })
  88
  89         def get(key):
  90             return xpath_text(
  91                 sts, './/{https://sts.amazonaws.com/doc/2011-06-15/}%s' % key,
  92                 fatal=True)
  93
  94         mcp_id = self._aws_execute_api({
  95             'uri': '/1/web/brands/%s/episodes/scrid/%s' % (self._SNI_TABLE[site_id], video_id),
  96             'access_key': get('AccessKeyId'),
  97             'secret_key': get('SecretAccessKey'),
  98             'session_token': get('SessionToken'),
  99         }, video_id)['results'][0]['mcpId']
 100
 101         return self.url_result(
 102             smuggle_url(
 103                 'anvato:anvato_scripps_app_web_prod_0837996dbe373629133857ae9eb72e740424d80a:%s' % mcp_id,
 104                 {'geo_countries': ['US']}),
 105             AnvatoIE.ie_key(), video_id=mcp_id)
 106
 107
 108 class ScrippsNetworksIE(InfoExtractor):
 109     _VALID_URL = r'https?://(?:www\.)?(?P<site>cookingchanneltv|discovery|(?:diy|food)network|hgtv|travelchannel)\.com/videos/[0-9a-z-]+-(?P<id>\d+)'
 110     _TESTS = [{
 111         'url': 'https://www.cookingchanneltv.com/videos/the-best-of-the-best-0260338',
 112         'info_dict': {
 113             'id': '0260338',
 114             'ext': 'mp4',
 115             'title': 'The Best of the Best',
 116             'description': 'Catch a new episode of MasterChef Canada Tuedsay at 9/8c.',
 117             'timestamp': 1475678834,
 118             'upload_date': '20161005',
 119             'uploader': 'SCNI-SCND',
 120         },
 121         'add_ie': ['ThePlatform'],
 122     }, {
 123         'url': 'https://www.diynetwork.com/videos/diy-barnwood-tablet-stand-0265790',
 124         'only_matching': True,
 125     }, {
 126         'url': 'https://www.foodnetwork.com/videos/chocolate-strawberry-cake-roll-7524591',
 127         'only_matching': True,
 128     }, {
 129         'url': 'https://www.hgtv.com/videos/cookie-decorating-101-0301929',
 130         'only_matching': True,
 131     }, {
 132         'url': 'https://www.travelchannel.com/videos/two-climates-one-bag-5302184',
 133         'only_matching': True,
 134     }, {
 135         'url': 'https://www.discovery.com/videos/guardians-of-the-glades-cooking-with-tom-cobb-5578368',
 136         'only_matching': True,
 137     }]
 138     _ACCOUNT_MAP = {
 139         'cookingchanneltv': 2433005105,
 140         'discovery': 2706091867,
 141         'diynetwork': 2433004575,
 142         'foodnetwork': 2433005105,
 143         'hgtv': 2433004575,
 144         'travelchannel': 2433005739,
 145     }
 146     _TP_TEMPL = 'https://link.theplatform.com/s/ip77QC/media/guid/%d/%s?mbr=true'
 147
 148     def _real_extract(self, url):
 149         site, guid = re.match(self._VALID_URL, url).groups()
 150         return self.url_result(smuggle_url(
 151             self._TP_TEMPL % (self._ACCOUNT_MAP[site], guid),
 152             {'force_smil_url': True}), 'ThePlatform', guid)