X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Faenetworks.py;h=c01c6730358f28356dc1bf62ef72bc0af81299c4;hb=95728fda7059265374e92d92004bd75e0beb630d;hp=6adb6d824c00ec733afaf1bbe1b243f7d623b647;hpb=1fd6e30988f44d372c7112c2d5e44c0d5cdbc4ed;p=youtube-dl diff --git a/youtube_dl/extractor/aenetworks.py b/youtube_dl/extractor/aenetworks.py index 6adb6d824..c01c67303 100644 --- a/youtube_dl/extractor/aenetworks.py +++ b/youtube_dl/extractor/aenetworks.py @@ -23,10 +23,22 @@ class AENetworksBaseIE(ThePlatformIE): class AENetworksIE(AENetworksBaseIE): IE_NAME = 'aenetworks' IE_DESC = 'A+E Networks: A&E, Lifetime, History.com, FYI Network' - _VALID_URL = r'https?://(?:www\.)?(?P(?:history|aetv|mylifetime)\.com|fyi\.tv)/(?:shows/(?P[^/]+(?:/[^/]+){0,2})|movies/(?P[^/]+)/full-movie)' + _VALID_URL = r'''(?x) + https?:// + (?:www\.)? + (?P + (?:history|aetv|mylifetime|lifetimemovieclub)\.com| + fyi\.tv + )/ + (?: + shows/(?P[^/]+(?:/[^/]+){0,2})| + movies/(?P[^/]+)(?:/full-movie)?| + specials/(?P[^/]+)/full-special + ) + ''' _TESTS = [{ 'url': 'http://www.history.com/shows/mountain-men/season-1/episode-1', - 'md5': '8ff93eb073449f151d6b90c0ae1ef0c7', + 'md5': 'a97a65f7e823ae10e9244bc5433d5fe6', 'info_dict': { 'id': '22253814', 'ext': 'mp4', @@ -62,17 +74,24 @@ class AENetworksIE(AENetworksBaseIE): }, { 'url': 'http://www.mylifetime.com/movies/center-stage-on-pointe/full-movie', 'only_matching': True + }, { + 'url': 'https://www.lifetimemovieclub.com/movies/a-killer-among-us', + 'only_matching': True + }, { + 'url': 'http://www.history.com/specials/sniper-into-the-kill-zone/full-special', + 'only_matching': True }] _DOMAIN_TO_REQUESTOR_ID = { 'history.com': 'HISTORY', 'aetv.com': 'AETV', 'mylifetime.com': 'LIFETIME', + 'lifetimemovieclub.com': 'LIFETIMEMOVIECLUB', 'fyi.tv': 'FYI', } def _real_extract(self, url): - domain, show_path, movie_display_id = re.match(self._VALID_URL, url).groups() - display_id = show_path or movie_display_id + domain, show_path, movie_display_id, special_display_id = re.match(self._VALID_URL, url).groups() + display_id = show_path or movie_display_id or special_display_id webpage = self._download_webpage(url, display_id) if show_path: url_parts = show_path.split('/') @@ -87,7 +106,7 @@ class AENetworksIE(AENetworksBaseIE): self._html_search_meta('aetn:SeriesTitle', webpage)) elif url_parts_len == 2: entries = [] - for episode_item in re.findall(r'(?s)]+class="[^"]*episode-item[^"]*"[^>]*>', webpage): + for episode_item in re.findall(r'(?s)<[^>]+class="[^"]*(?:episode|program)-item[^"]*"[^>]*>', webpage): episode_attributes = extract_attributes(episode_item) episode_url = compat_urlparse.urljoin( url, episode_attributes['data-canonical']) @@ -99,11 +118,14 @@ class AENetworksIE(AENetworksBaseIE): query = { 'mbr': 'true', - 'assetTypes': 'medium_video_s3' + 'assetTypes': 'high_video_s3' } video_id = self._html_search_meta('aetn:VideoID', webpage) media_url = self._search_regex( - r"media_url\s*=\s*'([^']+)'", webpage, 'video url') + [r"media_url\s*=\s*'(?P[^']+)'", + r'data-media-url=(?P(?:https?:)?//[^\s>]+)', + r'data-media-url=(["\'])(?P(?:(?!\1).)+?)\1'], + webpage, 'video url', group='url') theplatform_metadata = self._download_theplatform_metadata(self._search_regex( r'https?://link.theplatform.com/s/([^?]+)', media_url, 'theplatform_path'), video_id) info = self._parse_theplatform_metadata(theplatform_metadata) @@ -155,7 +177,7 @@ class HistoryTopicIE(AENetworksBaseIE): 'id': 'world-war-i-history', 'title': 'World War I History', }, - 'playlist_mincount': 24, + 'playlist_mincount': 23, }, { 'url': 'http://www.history.com/topics/world-war-i-history/videos', 'only_matching': True, @@ -193,7 +215,8 @@ class HistoryTopicIE(AENetworksBaseIE): return self.theplatform_url_result( release_url, video_id, { 'mbr': 'true', - 'switch': 'hls' + 'switch': 'hls', + 'assetTypes': 'high_video_ak', }) else: webpage = self._download_webpage(url, topic_id) @@ -203,6 +226,7 @@ class HistoryTopicIE(AENetworksBaseIE): entries.append(self.theplatform_url_result( video_attributes['data-release-url'], video_attributes['data-id'], { 'mbr': 'true', - 'switch': 'hls' + 'switch': 'hls', + 'assetTypes': 'high_video_ak', })) return self.playlist_result(entries, topic_id, get_element_by_attribute('class', 'show-title', webpage))