diff --git a/youtube_dl/extractor/cbc.py b/youtube_dl/extractor/cbc.py index 3be0c646b..54b4b9be9 100644 --- a/youtube_dl/extractor/cbc.py +++ b/youtube_dl/extractor/cbc.py @@ -5,7 +5,10 @@ import json import re from .common import InfoExtractor -from ..compat import compat_str +from ..compat import ( + compat_str, + compat_HTTPError, +) from ..utils import ( js_to_json, smuggle_url, @@ -206,30 +209,48 @@ class CBCWatchBaseIE(InfoExtractor): def _call_api(self, path, video_id): url = path if path.startswith('http') else self._API_BASE_URL + path - result = self._download_xml(url, video_id, headers={ - 'X-Clearleap-DeviceId': self._device_id, - 'X-Clearleap-DeviceToken': self._device_token, - }) + for _ in range(2): + try: + result = self._download_xml(url, video_id, headers={ + 'X-Clearleap-DeviceId': self._device_id, + 'X-Clearleap-DeviceToken': self._device_token, + }) + except ExtractorError as e: + if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401: + # Device token has expired, re-acquiring device token + self._register_device() + continue + raise error_message = xpath_text(result, 'userMessage') or xpath_text(result, 'systemMessage') if error_message: raise ExtractorError('%s said: %s' % (self.IE_NAME, error_message)) return result def _real_initialize(self): - if not self._device_id or not self._device_token: - device = self._downloader.cache.load('cbcwatch', 'device') or {} - self._device_id, self._device_token = device.get('id'), device.get('token') - if not self._device_id or not self._device_token: - result = self._download_xml( - self._API_BASE_URL + 'device/register', - None, data=b'web') - self._device_id = xpath_text(result, 'deviceId', fatal=True) - self._device_token = xpath_text(result, 'deviceToken', fatal=True) - self._downloader.cache.store( - 'cbcwatch', 'device', { - 'id': self._device_id, - 'token': self._device_token, - }) + if self._valid_device_token(): + return + device = self._downloader.cache.load('cbcwatch', 'device') or {} + self._device_id, self._device_token = device.get('id'), device.get('token') + if self._valid_device_token(): + return + self._register_device() + + def _valid_device_token(self): + return self._device_id and self._device_token + + def _register_device(self): + self._device_id = self._device_token = None + result = self._download_xml( + self._API_BASE_URL + 'device/register', + None, 'Acquiring device token', + data=b'web') + self._device_id = xpath_text(result, 'deviceId', fatal=True) + self._device_token = xpath_text(result, 'deviceToken', fatal=True) + self._downloader.cache.store( + 'cbcwatch', 'device', { + 'id': self._device_id, + 'token': self._device_token, + }) def _parse_rss_feed(self, rss): channel = xpath_element(rss, 'channel', fatal=True) diff --git a/youtube_dl/extractor/fxnetworks.py b/youtube_dl/extractor/fxnetworks.py index 37549fb01..00e67426b 100644 --- a/youtube_dl/extractor/fxnetworks.py +++ b/youtube_dl/extractor/fxnetworks.py @@ -41,7 +41,7 @@ class FXNetworksIE(AdobePassIE): if 'The content you are trying to access is not available in your region.' in webpage: self.raise_geo_restricted() video_data = extract_attributes(self._search_regex( - r'()', webpage, 'video data')) + r'()', webpage, 'video data')) player_type = self._search_regex(r'playerType\s*=\s*[\'"]([^\'"]+)', webpage, 'player type', default=None) release_url = video_data['rel'] title = video_data['data-title'] diff --git a/youtube_dl/extractor/pornhub.py b/youtube_dl/extractor/pornhub.py index 9ce513aeb..23e24d216 100644 --- a/youtube_dl/extractor/pornhub.py +++ b/youtube_dl/extractor/pornhub.py @@ -33,7 +33,7 @@ class PornHubIE(InfoExtractor): _VALID_URL = r'''(?x) https?:// (?: - (?:[a-z]+\.)?pornhub\.com/(?:(?:view_video\.php|video/show)\?viewkey=|embed/)| + (?:[^/]+\.)?pornhub\.com/(?:(?:view_video\.php|video/show)\?viewkey=|embed/)| (?:www\.)?thumbzilla\.com/video/ ) (?P[\da-z]+) @@ -264,7 +264,7 @@ class PornHubPlaylistBaseIE(InfoExtractor): class PornHubPlaylistIE(PornHubPlaylistBaseIE): - _VALID_URL = r'https?://(?:www\.)?pornhub\.com/playlist/(?P\d+)' + _VALID_URL = r'https?://(?:[^/]+\.)?pornhub\.com/playlist/(?P\d+)' _TESTS = [{ 'url': 'http://www.pornhub.com/playlist/4667351', 'info_dict': { @@ -272,11 +272,14 @@ class PornHubPlaylistIE(PornHubPlaylistBaseIE): 'title': 'Nataly Hot', }, 'playlist_mincount': 2, + }, { + 'url': 'https://de.pornhub.com/playlist/4667351', + 'only_matching': True, }] class PornHubUserVideosIE(PornHubPlaylistBaseIE): - _VALID_URL = r'https?://(?:www\.)?pornhub\.com/(?:user|channel)s/(?P[^/]+)/videos' + _VALID_URL = r'https?://(?:[^/]+\.)?pornhub\.com/(?:user|channel)s/(?P[^/]+)/videos' _TESTS = [{ 'url': 'http://www.pornhub.com/users/zoe_ph/videos/public', 'info_dict': { @@ -305,6 +308,9 @@ class PornHubUserVideosIE(PornHubPlaylistBaseIE): # Most Viewed Videos 'url': 'https://www.pornhub.com/channels/povd/videos?o=vi', 'only_matching': True, + }, { + 'url': 'http://www.pornhub.com/users/zoe_ph/videos/public', + 'only_matching': True, }] def _real_extract(self, url):