From d93083789bf9c318b18d52ac132e9495345b9ebc Mon Sep 17 00:00:00 2001 From: =?utf8?q?Sergey=20M=E2=80=A4?= Date: Sun, 17 Feb 2019 14:09:30 +0700 Subject: [PATCH] [tvp:series] Fix extraction --- youtube_dl/extractor/tvp.py | 67 ++++++++++++++++--------------------- 1 file changed, 29 insertions(+), 38 deletions(-) diff --git a/youtube_dl/extractor/tvp.py b/youtube_dl/extractor/tvp.py index 536b580fc..05669a366 100644 --- a/youtube_dl/extractor/tvp.py +++ b/youtube_dl/extractor/tvp.py @@ -1,14 +1,16 @@ # coding: utf-8 from __future__ import unicode_literals +import itertools import re from .common import InfoExtractor from ..utils import ( - determine_ext, clean_html, - get_element_by_attribute, + determine_ext, ExtractorError, + get_element_by_attribute, + orderedSet, ) @@ -198,46 +200,35 @@ class TVPEmbedIE(InfoExtractor): class TVPSeriesIE(InfoExtractor): IE_NAME = 'tvp:series' - _VALID_URL = r'https?://vod\.tvp\.pl/(?:[^/]+/){2}(?P[^/]+)/?$' + _VALID_URL = r'https?://vod\.tvp\.pl/website/(?P[^,]+),(?P\d+)/video' _TESTS = [{ - 'url': 'http://vod.tvp.pl/filmy-fabularne/filmy-za-darmo/ogniem-i-mieczem', + 'url': 'https://vod.tvp.pl/website/lzy-cennet,38678312/video', 'info_dict': { - 'title': 'Ogniem i mieczem', - 'id': '4278026', + 'id': '38678312', }, - 'playlist_count': 4, - }, { - 'url': 'http://vod.tvp.pl/audycje/podroze/boso-przez-swiat', - 'info_dict': { - 'title': 'Boso przez świat', - 'id': '9329207', - }, - 'playlist_count': 86, + 'playlist_count': 115, }] - def _real_extract(self, url): - display_id = self._match_id(url) - webpage = self._download_webpage(url, display_id, tries=5) - - title = self._html_search_regex( - r'(?s) id=[\'"]path[\'"]>(?:.*? / ){2}(.*?)', webpage, 'series') - playlist_id = self._search_regex(r'nodeId:\s*(\d+)', webpage, 'playlist id') - playlist = self._download_webpage( - 'http://vod.tvp.pl/vod/seriesAjax?type=series&nodeId=%s&recommend' - 'edId=0&sort=&page=0&pageSize=10000' % playlist_id, display_id, tries=5, - note='Downloading playlist') - - 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] + def _entries(self, url, display_id): + for page_num in itertools.count(1): + page = self._download_webpage( + url, display_id, 'Downloading page %d' % page_num, + query={'page': page_num}) - return { - '_type': 'playlist', - 'id': playlist_id, - 'display_id': display_id, - 'title': title, - 'entries': entries, - } + video_ids = orderedSet(re.findall( + r']+\bhref=["\']/video/%s,[^,]+,(\d+)' % display_id, + page)) + + if not video_ids: + break + + for video_id in video_ids: + yield self.url_result( + 'tvp:%s' % video_id, ie=TVPEmbedIE.ie_key(), + video_id=video_id) + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + display_id, playlist_id = mobj.group('display_id', 'id') + return self.playlist_result(self._entries(url, display_id), playlist_id) -- 2.22.2