github/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-21 20:46:36 -05:00
Code Issues Projects Releases Packages Wiki Activity

[eagleplatform] Add support for referrer protected videos (closes #13557)

Browse source
This commit is contained in:
Sergey M․ 2017-07-09 15:57:33 +07:00
parent 5af2fd7fa0
commit 665e945246
No known key found for this signature in database
GPG key ID: 2C393E0F18A9236D
2 changed files with 27 additions and 8 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

25
youtube_dl/extractor/eagleplatform.py
View file

@ -11,6 +11,7 @@
from ..utils import ( from ..utils import (
ExtractorError, ExtractorError,
int_or_none, int_or_none,
unsmuggle_url,
) )
@ -50,6 +51,10 @@ class EaglePlatformIE(InfoExtractor):
'view_count': int, 'view_count': int,
}, },
'skip': 'Georestricted', 'skip': 'Georestricted',
}, {
# referrer protected video (https://tvrain.ru/lite/teleshow/kak_vse_nachinalos/namin-418921/)
'url': 'tvrainru.media.eagleplatform.com:582306',
'only_matching': True,
}] }]
@staticmethod @staticmethod
@ -103,9 +108,10 @@ def _handle_error(response):
if status != 200: if status != 200:
raise ExtractorError(' '.join(response['errors']), expected=True) raise ExtractorError(' '.join(response['errors']), expected=True)
def _download_json(self, url_or_request, video_id, note='Downloading JSON metadata', *args, **kwargs): def _download_json(self, url_or_request, video_id, *args, **kwargs):
try: try:
response = super(EaglePlatformIE, self)._download_json(url_or_request, video_id, note) response = super(EaglePlatformIE, self)._download_json(
url_or_request, video_id, *args, **kwargs)
except ExtractorError as ee: except ExtractorError as ee:
if isinstance(ee.cause, compat_HTTPError): if isinstance(ee.cause, compat_HTTPError):
response = self._parse_json(ee.cause.read().decode('utf-8'), video_id) response = self._parse_json(ee.cause.read().decode('utf-8'), video_id)
@ -117,11 +123,24 @@ def _get_video_url(self, url_or_request, video_id, note='Downloading JSON metada
return self._download_json(url_or_request, video_id, note)['data'][0] return self._download_json(url_or_request, video_id, note)['data'][0]
def _real_extract(self, url): def _real_extract(self, url):
url, smuggled_data = unsmuggle_url(url, {})
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url)
host, video_id = mobj.group('custom_host') or mobj.group('host'), mobj.group('id') host, video_id = mobj.group('custom_host') or mobj.group('host'), mobj.group('id')
headers = {}
query = {
'id': video_id,
}
referrer = smuggled_data.get('referrer')
if referrer:
headers['Referer'] = referrer
query['referrer'] = referrer
player_data = self._download_json( player_data = self._download_json(
'http://%s/api/player_data?id=%s' % (host, video_id), video_id) 'http://%s/api/player_data' % host, video_id,
headers=headers, query=query)
media = player_data['data']['playlist']['viewports'][0]['medialist'][0] media = player_data['data']['playlist']['viewports'][0]['medialist'][0]

10
youtube_dl/extractor/generic.py
View file

@ -1185,7 +1185,7 @@ class GenericIE(InfoExtractor):
}, },
'add_ie': ['Kaltura'], 'add_ie': ['Kaltura'],
}, },
# Eagle.Platform embed (generic URL) # EaglePlatform embed (generic URL)
{ {
'url': 'http://lenta.ru/news/2015/03/06/navalny/', 'url': 'http://lenta.ru/news/2015/03/06/navalny/',
# Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
@ -1200,7 +1200,7 @@ class GenericIE(InfoExtractor):
'age_limit': 0, 'age_limit': 0,
}, },
}, },
# ClipYou (Eagle.Platform) embed (custom URL) # ClipYou (EaglePlatform) embed (custom URL)
{ {
'url': 'http://muz-tv.ru/play/7129/', 'url': 'http://muz-tv.ru/play/7129/',
# Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
@ -2443,12 +2443,12 @@ def _real_extract(self, url):
if kaltura_url: if kaltura_url:
return self.url_result(smuggle_url(kaltura_url, {'source_url': url}), KalturaIE.ie_key()) return self.url_result(smuggle_url(kaltura_url, {'source_url': url}), KalturaIE.ie_key())
# Look for Eagle.Platform embeds # Look for EaglePlatform embeds
eagleplatform_url = EaglePlatformIE._extract_url(webpage) eagleplatform_url = EaglePlatformIE._extract_url(webpage)
if eagleplatform_url: if eagleplatform_url:
return self.url_result(eagleplatform_url, EaglePlatformIE.ie_key()) return self.url_result(smuggle_url(eagleplatform_url, {'referrer': url}), EaglePlatformIE.ie_key())
# Look for ClipYou (uses Eagle.Platform) embeds # Look for ClipYou (uses EaglePlatform) embeds
mobj = re.search( mobj = re.search(
r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage) r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
if mobj is not None: if mobj is not None: