commit: 4b85f0f9db9329ef1774a66c3e2fd4da558a5201
parent 19d6991312405f5af108af28b3721966720fc72d
Author: Remita Amine <remitamine@gmail.com>
Date: Tue, 22 Jan 2019 14:38:29 +0100
[vrv] add support for authentication(closes #14307)
Diffstat:
1 file changed, 57 insertions(+), 40 deletions(-)
diff --git a/youtube_dl/extractor/vrv.py b/youtube_dl/extractor/vrv.py
@@ -11,10 +11,12 @@ import time
from .common import InfoExtractor
from ..compat import (
+ compat_HTTPError,
compat_urllib_parse_urlencode,
compat_urllib_parse,
)
from ..utils import (
+ ExtractorError,
float_or_none,
int_or_none,
)
@@ -24,29 +26,41 @@ class VRVBaseIE(InfoExtractor):
_API_DOMAIN = None
_API_PARAMS = {}
_CMS_SIGNING = {}
+ _TOKEN = None
+ _TOKEN_SECRET = ''
def _call_api(self, path, video_id, note, data=None):
+ # https://tools.ietf.org/html/rfc5849#section-3
base_url = self._API_DOMAIN + '/core/' + path
- encoded_query = compat_urllib_parse_urlencode({
+ query = {
'oauth_consumer_key': self._API_PARAMS['oAuthKey'],
'oauth_nonce': ''.join([random.choice(string.ascii_letters) for _ in range(32)]),
'oauth_signature_method': 'HMAC-SHA1',
'oauth_timestamp': int(time.time()),
- 'oauth_version': '1.0',
- })
+ }
+ if self._TOKEN:
+ query['oauth_token'] = self._TOKEN
+ encoded_query = compat_urllib_parse_urlencode(query)
headers = self.geo_verification_headers()
if data:
data = json.dumps(data).encode()
headers['Content-Type'] = 'application/json'
- method = 'POST' if data else 'GET'
- base_string = '&'.join([method, compat_urllib_parse.quote(base_url, ''), compat_urllib_parse.quote(encoded_query, '')])
+ base_string = '&'.join([
+ 'POST' if data else 'GET',
+ compat_urllib_parse.quote(base_url, ''),
+ compat_urllib_parse.quote(encoded_query, '')])
oauth_signature = base64.b64encode(hmac.new(
- (self._API_PARAMS['oAuthSecret'] + '&').encode('ascii'),
+ (self._API_PARAMS['oAuthSecret'] + '&' + self._TOKEN_SECRET).encode('ascii'),
base_string.encode(), hashlib.sha1).digest()).decode()
encoded_query += '&oauth_signature=' + compat_urllib_parse.quote(oauth_signature, '')
- return self._download_json(
- '?'.join([base_url, encoded_query]), video_id,
- note='Downloading %s JSON metadata' % note, headers=headers, data=data)
+ try:
+ return self._download_json(
+ '?'.join([base_url, encoded_query]), video_id,
+ note='Downloading %s JSON metadata' % note, headers=headers, data=data)
+ except ExtractorError as e:
+ if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401:
+ raise ExtractorError(json.loads(e.cause.read().decode())['message'], expected=True)
+ raise
def _call_cms(self, path, video_id, note):
if not self._CMS_SIGNING:
@@ -55,19 +69,22 @@ class VRVBaseIE(InfoExtractor):
self._API_DOMAIN + path, video_id, query=self._CMS_SIGNING,
note='Downloading %s JSON metadata' % note, headers=self.geo_verification_headers())
- def _set_api_params(self, webpage, video_id):
- if not self._API_PARAMS:
- self._API_PARAMS = self._parse_json(self._search_regex(
- r'window\.__APP_CONFIG__\s*=\s*({.+?})</script>',
- webpage, 'api config'), video_id)['cxApiParams']
- self._API_DOMAIN = self._API_PARAMS.get('apiDomain', 'https://api.vrv.co')
-
def _get_cms_resource(self, resource_key, video_id):
return self._call_api(
'cms_resource', video_id, 'resource path', data={
'resource_key': resource_key,
})['__links__']['cms_resource']['href']
+ def _real_initialize(self):
+ webpage = self._download_webpage(
+ 'https://vrv.co/', None, headers=self.geo_verification_headers())
+ self._API_PARAMS = self._parse_json(self._search_regex(
+ [
+ r'window\.__APP_CONFIG__\s*=\s*({.+?})(?:</script>|;)',
+ r'window\.__APP_CONFIG__\s*=\s*({.+})'
+ ], webpage, 'app config'), None)['cxApiParams']
+ self._API_DOMAIN = self._API_PARAMS.get('apiDomain', 'https://api.vrv.co')
+
class VRVIE(VRVBaseIE):
IE_NAME = 'vrv'
@@ -86,6 +103,22 @@ class VRVIE(VRVBaseIE):
'skip_download': True,
},
}]
+ _NETRC_MACHINE = 'vrv'
+
+ def _real_initialize(self):
+ super(VRVIE, self)._real_initialize()
+
+ email, password = self._get_login_info()
+ if email is None:
+ return
+
+ token_credentials = self._call_api(
+ 'authenticate/by:credentials', None, 'Token Credentials', data={
+ 'email': email,
+ 'password': password,
+ })
+ self._TOKEN = token_credentials['oauth_token']
+ self._TOKEN_SECRET = token_credentials['oauth_token_secret']
def _extract_vrv_formats(self, url, video_id, stream_format, audio_lang, hardsub_lang):
if not url or stream_format not in ('hls', 'dash'):
@@ -116,28 +149,16 @@ class VRVIE(VRVBaseIE):
def _real_extract(self, url):
video_id = self._match_id(url)
- webpage = self._download_webpage(
- url, video_id,
- headers=self.geo_verification_headers())
- media_resource = self._parse_json(self._search_regex(
- [
- r'window\.__INITIAL_STATE__\s*=\s*({.+?})(?:</script>|;)',
- r'window\.__INITIAL_STATE__\s*=\s*({.+})'
- ], webpage, 'inital state'), video_id).get('watch', {}).get('mediaResource') or {}
-
- video_data = media_resource.get('json')
- if not video_data:
- self._set_api_params(webpage, video_id)
- episode_path = self._get_cms_resource(
- 'cms:/episodes/' + video_id, video_id)
- video_data = self._call_cms(episode_path, video_id, 'video')
+
+ episode_path = self._get_cms_resource(
+ 'cms:/episodes/' + video_id, video_id)
+ video_data = self._call_cms(episode_path, video_id, 'video')
title = video_data['title']
- streams_json = media_resource.get('streams', {}).get('json', {})
- if not streams_json:
- self._set_api_params(webpage, video_id)
- streams_path = video_data['__links__']['streams']['href']
- streams_json = self._call_cms(streams_path, video_id, 'streams')
+ streams_path = video_data['__links__'].get('streams', {}).get('href')
+ if not streams_path:
+ self.raise_login_required()
+ streams_json = self._call_cms(streams_path, video_id, 'streams')
audio_locale = streams_json.get('audio_locale')
formats = []
@@ -202,11 +223,7 @@ class VRVSeriesIE(VRVBaseIE):
def _real_extract(self, url):
series_id = self._match_id(url)
- webpage = self._download_webpage(
- url, series_id,
- headers=self.geo_verification_headers())
- self._set_api_params(webpage, series_id)
seasons_path = self._get_cms_resource(
'cms:/seasons?series_id=' + series_id, series_id)
seasons_data = self._call_cms(seasons_path, series_id, 'seasons')
