From: Tithen-Firion Date: Thu, 4 Dec 2014 04:14:09 +0000 (+0100) Subject: [tvp] Add extractor X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=commitdiff_plain;h=6ce2c6783b2c1516fe9b1b5cb88d28231db45f8c;p=youtube-dl [tvp] Add extractor --- diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 8b513ffd1..b09ee303d 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -415,7 +415,7 @@ from .tunein import TuneInIE from .turbo import TurboIE from .tutv import TutvIE from .tvigle import TvigleIE -from .tvp import TvpIE +from .tvp import TvpIE, TvpSeriesIE from .tvplay import TVPlayIE from .twentyfourvideo import TwentyFourVideoIE from .twitch import TwitchIE diff --git a/youtube_dl/extractor/tvp.py b/youtube_dl/extractor/tvp.py index 6b95e2ed1..2248a9fdf 100644 --- a/youtube_dl/extractor/tvp.py +++ b/youtube_dl/extractor/tvp.py @@ -110,3 +110,59 @@ class TvpIE(InfoExtractor): 'formats': formats, }) return info_dict + + +class TvpSeriesIE(InfoExtractor): + IE_NAME = 'tvp.pl:Series' + _VALID_URL = r'https?://vod\.tvp\.pl/(?:[^/]+/){2}(?P[^/]+)/?$' + + _TESTS = [ + { + 'url': 'http://vod.tvp.pl/filmy-fabularne/filmy-za-darmo/ogniem-i-mieczem', + 'info_dict': { + 'title': 'Ogniem i mieczem', + 'id': '4278026', + }, + 'playlist_count': 4, + }, { + 'url': 'http://vod.tvp.pl/audycje/podroze/boso-przez-swiat', + 'info_dict': { + 'title': 'Boso przez świat', + 'id': '9329207', + }, + 'playlist_count': 86, + } + ] + + def _force_download_webpage(self, url, v_id, tries=0): + if tries >= 5: + raise ExtractorError( + '%s: Cannot download webpage, try again later' % v_id) + # Sometimes happen, but in my tests second try always succeeded + try: + return self._download_webpage(url, v_id) + except IncompleteRead as e: + return self._force_download_webpage(url, v_id, tries+1) + + def _real_extract(self, url): + display_id = self._match_id(url) + webpage = self._force_download_webpage(url, display_id) + title = self._html_search_regex( + r'(?s) id=[\'"]path[\'"]>(.*?)', webpage, 'series') + title = title.split(' / ', 2)[-1] + playlist_id = self._search_regex(r'nodeId:\s*(\d+)', webpage, 'playlist id') + playlist = self._force_download_webpage( + 'http://vod.tvp.pl/vod/seriesAjax?type=series&nodeId=%s&recommend' + 'edId=0&sort=&page=0&pageSize=1000000' % playlist_id, display_id) + videos_paths = re.findall( + '(?s)class="shortTitle">.*?href="(/[^"]+)', playlist) + entries = [ + self.url_result('http://vod.tvp.pl%s' % v_path, ie=TvpIE.ie_key()) + for v_path in videos_paths] + return { + '_type': 'playlist', + 'id': playlist_id, + 'display_id': display_id, + 'title': title, + 'entries': entries, + }