From cf7cb9428745dc744129e0ba90c626919fb98f48 Mon Sep 17 00:00:00 2001 From: Unknown Date: Fri, 9 Oct 2020 07:50:22 +0200 Subject: [PATCH] [mtvn] update mtv network related extractors --- youtube_dlc/extractor/bet.py | 2 ++ youtube_dlc/extractor/cmt.py | 6 ++++-- youtube_dlc/extractor/comedycentral.py | 2 +- youtube_dlc/extractor/mtv.py | 23 +++++++++++++---------- youtube_dlc/extractor/nick.py | 2 +- youtube_dlc/extractor/spike.py | 16 +++++++++++++--- youtube_dlc/extractor/vh1.py | 2 ++ 7 files changed, 36 insertions(+), 17 deletions(-) diff --git a/youtube_dlc/extractor/bet.py b/youtube_dlc/extractor/bet.py index d7ceaa85e..2c7144235 100644 --- a/youtube_dlc/extractor/bet.py +++ b/youtube_dlc/extractor/bet.py @@ -3,6 +3,8 @@ from __future__ import unicode_literals from .mtv import MTVServicesInfoExtractor from ..utils import unified_strdate +# TODO Remove - Reason: Outdated Site + class BetIE(MTVServicesInfoExtractor): _VALID_URL = r'https?://(?:www\.)?bet\.com/(?:[^/]+/)+(?P.+?)\.html' diff --git a/youtube_dlc/extractor/cmt.py b/youtube_dlc/extractor/cmt.py index e701fbeab..a4ddb9160 100644 --- a/youtube_dlc/extractor/cmt.py +++ b/youtube_dlc/extractor/cmt.py @@ -2,6 +2,8 @@ from __future__ import unicode_literals from .mtv import MTVIE +# TODO Remove - Reason: Outdated Site + class CMTIE(MTVIE): IE_NAME = 'cmt.com' @@ -39,7 +41,7 @@ class CMTIE(MTVIE): 'only_matching': True, }] - def _extract_mgid(self, webpage): + def _extract_mgid(self, webpage, url): mgid = self._search_regex( r'MTVN\.VIDEO\.contentUri\s*=\s*([\'"])(?P.+?)\1', webpage, 'mgid', group='mgid', default=None) @@ -50,5 +52,5 @@ class CMTIE(MTVIE): def _real_extract(self, url): video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) - mgid = self._extract_mgid(webpage) + mgid = self._extract_mgid(webpage, url) return self.url_result('http://media.mtvnservices.com/embed/%s' % mgid) diff --git a/youtube_dlc/extractor/comedycentral.py b/youtube_dlc/extractor/comedycentral.py index d08b909a6..f54c4adeb 100644 --- a/youtube_dlc/extractor/comedycentral.py +++ b/youtube_dlc/extractor/comedycentral.py @@ -48,7 +48,7 @@ class ComedyCentralFullEpisodesIE(MTVServicesInfoExtractor): def _real_extract(self, url): playlist_id = self._match_id(url) webpage = self._download_webpage(url, playlist_id) - mgid = self._extract_triforce_mgid(webpage, data_zone='t2_lc_promo1') + mgid = self._extract_mgid(webpage, url, data_zone='t2_lc_promo1') videos_info = self._get_videos_info(mgid) return videos_info diff --git a/youtube_dlc/extractor/mtv.py b/youtube_dlc/extractor/mtv.py index 88c5eda38..e545a9ef3 100644 --- a/youtube_dlc/extractor/mtv.py +++ b/youtube_dlc/extractor/mtv.py @@ -255,8 +255,10 @@ class MTVServicesInfoExtractor(InfoExtractor): return try_get(feed, lambda x: x['result']['data']['id'], compat_str) - def _extract_new_triforce_mgid(self, webpage, url='', data_zone=None, video_id=None): + def _extract_new_triforce_mgid(self, webpage, url='', video_id=None): # print(compat_urlparse.urlparse(url).netloc) + if url == '': + return domain = get_domain(url) if domain is None: raise ExtractorError( @@ -268,13 +270,14 @@ class MTVServicesInfoExtractor(InfoExtractor): triforce_manifest_url = _TRIFORCE_V8_TEMPLATE % (domain, enc_url) manifest = self._download_json(triforce_manifest_url, video_id, fatal=False) - if manifest.get('manifest').get('type') == 'redirect': - self.to_screen('Found a redirect. Downloading manifest from new location') - new_loc = manifest.get('manifest').get('newLocation') - new_loc = new_loc.replace("https://", "http://") - enc_new_loc = compat_urlparse.quote(new_loc, safe='') - triforce_manifest_new_loc = _TRIFORCE_V8_TEMPLATE % (domain, enc_new_loc) - manifest = self._download_json(triforce_manifest_new_loc, video_id, fatal=False) + if manifest: + if manifest.get('manifest').get('type') == 'redirect': + self.to_screen('Found a redirect. Downloading manifest from new location') + new_loc = manifest.get('manifest').get('newLocation') + new_loc = new_loc.replace("https://", "http://") + enc_new_loc = compat_urlparse.quote(new_loc, safe='') + triforce_manifest_new_loc = _TRIFORCE_V8_TEMPLATE % (domain, enc_new_loc) + manifest = self._download_json(triforce_manifest_new_loc, video_id, fatal=False) item_id = try_get(manifest, lambda x: x['manifest']['reporting']['itemId'], compat_str) if not item_id: @@ -287,7 +290,7 @@ class MTVServicesInfoExtractor(InfoExtractor): return mgid - def _extract_mgid(self, webpage, url): + def _extract_mgid(self, webpage, url, data_zone=None): try: # the url can be http://media.mtvnservices.com/fb/{mgid}.swf # or http://media.mtvnservices.com/{mgid} @@ -313,7 +316,7 @@ class MTVServicesInfoExtractor(InfoExtractor): mgid = self._extract_new_triforce_mgid(webpage, url) if not mgid: - mgid = self._extract_triforce_mgid(webpage) + mgid = self._extract_triforce_mgid(webpage, data_zone) return mgid diff --git a/youtube_dlc/extractor/nick.py b/youtube_dlc/extractor/nick.py index 2e8b302ac..04b98f7bd 100644 --- a/youtube_dlc/extractor/nick.py +++ b/youtube_dlc/extractor/nick.py @@ -245,5 +245,5 @@ class NickRuIE(MTVServicesInfoExtractor): def _real_extract(self, url): video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) - mgid = self._extract_mgid(webpage) + mgid = self._extract_mgid(webpage, url) return self.url_result('http://media.mtvnservices.com/embed/%s' % mgid) diff --git a/youtube_dlc/extractor/spike.py b/youtube_dlc/extractor/spike.py index aabff7a3c..3cee331f6 100644 --- a/youtube_dlc/extractor/spike.py +++ b/youtube_dlc/extractor/spike.py @@ -20,8 +20,18 @@ class BellatorIE(MTVServicesInfoExtractor): _FEED_URL = 'http://www.bellator.com/feeds/mrss/' _GEO_COUNTRIES = ['US'] - def _extract_mgid(self, webpage): - return self._extract_triforce_mgid(webpage) + def _extract_mgid(self, webpage, url): + mgid = None + + if not mgid: + mgid = self._extract_triforce_mgid(webpage) + + if not mgid: + mgid = self._extract_new_triforce_mgid(webpage, url) + + return mgid + +# TODO Remove - Reason: Outdated Site class ParamountNetworkIE(MTVServicesInfoExtractor): @@ -43,7 +53,7 @@ class ParamountNetworkIE(MTVServicesInfoExtractor): _FEED_URL = 'http://www.paramountnetwork.com/feeds/mrss/' _GEO_COUNTRIES = ['US'] - def _extract_mgid(self, webpage): + def _extract_mgid(self, webpage, url): root_data = self._parse_json(self._search_regex( r'window\.__DATA__\s*=\s*({.+})', webpage, 'data'), None) diff --git a/youtube_dlc/extractor/vh1.py b/youtube_dlc/extractor/vh1.py index dff94a2b8..ea576dc6b 100644 --- a/youtube_dlc/extractor/vh1.py +++ b/youtube_dlc/extractor/vh1.py @@ -3,6 +3,8 @@ from __future__ import unicode_literals from .mtv import MTVServicesInfoExtractor +# TODO Remove - Reason: Outdated Site + class VH1IE(MTVServicesInfoExtractor): IE_NAME = 'vh1.com'