From 25a4c5a9ed59eca0241922363e83e61172527658 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Jaime=20Marqui=CC=81nez=20Ferra=CC=81ndiz?= Date: Sun, 2 Aug 2015 15:19:57 +0200 Subject: [PATCH] [dailymotion:playlist] Use an iterator for the entries So that using '--playlist-end' only downloads the required pages (reported in #2175). --- youtube_dl/extractor/dailymotion.py | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/youtube_dl/extractor/dailymotion.py b/youtube_dl/extractor/dailymotion.py index 85d945509..2d90b2224 100644 --- a/youtube_dl/extractor/dailymotion.py +++ b/youtube_dl/extractor/dailymotion.py @@ -15,7 +15,6 @@ ExtractorError, determine_ext, int_or_none, - orderedSet, parse_iso8601, str_to_int, unescapeHTML, @@ -278,7 +277,7 @@ class DailymotionPlaylistIE(DailymotionBaseInfoExtractor): }] def _extract_entries(self, id): - video_ids = [] + video_ids = set() processed_urls = set() for pagenum in itertools.count(1): page_url = self._PAGE_TEMPLATE % (id, pagenum) @@ -291,12 +290,13 @@ def _extract_entries(self, id): processed_urls.add(urlh.geturl()) - video_ids.extend(re.findall(r'data-xid="(.+?)"', webpage)) + for video_id in re.findall(r'data-xid="(.+?)"', webpage): + if video_id not in video_ids: + yield self.url_result('http://www.dailymotion.com/video/%s' % video_id, 'Dailymotion') + video_ids.add(video_id) if re.search(self._MORE_PAGES_INDICATOR, webpage) is None: break - return [self.url_result('http://www.dailymotion.com/video/%s' % video_id, 'Dailymotion') - for video_id in orderedSet(video_ids)] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url)