diff options
| author | Philipp Hagemeister <[email protected]> | 2014-04-04 02:04:16 +0200 |
|---|---|---|
| committer | Philipp Hagemeister <[email protected]> | 2014-04-04 02:04:16 +0200 |
| commit | 1e0a235f39e9076cad94977e5eafc5fbd3ee0be6 (patch) | |
| tree | 5ccac0b3e52cd54e0c2d298a14201b8c3ffb3ce4 | |
| parent | 9ad400f75ede95256d337a16046db8ae3690532b (diff) | |
| download | youtube-dl-1e0a235f39e9076cad94977e5eafc5fbd3ee0be6.tar.gz youtube-dl-1e0a235f39e9076cad94977e5eafc5fbd3ee0be6.zip | |
[dailymotion] Fix playlist+user
| -rw-r--r-- | youtube_dl/extractor/dailymotion.py | 10 |
1 files changed, 4 insertions, 6 deletions
diff --git a/youtube_dl/extractor/dailymotion.py b/youtube_dl/extractor/dailymotion.py index 10b97d8ca..7ed7f2723 100644 --- a/youtube_dl/extractor/dailymotion.py +++ b/youtube_dl/extractor/dailymotion.py @@ -180,7 +180,7 @@ class DailymotionIE(DailymotionBaseInfoExtractor, SubtitlesInfoExtractor): class DailymotionPlaylistIE(DailymotionBaseInfoExtractor): IE_NAME = u'dailymotion:playlist' _VALID_URL = r'(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/playlist/(?P<id>.+?)/' - _MORE_PAGES_INDICATOR = r'<div class="next">.*?<a.*?href="/playlist/.+?".*?>.*?</a>.*?</div>' + _MORE_PAGES_INDICATOR = r'(?s)<div class="pages[^"]*">.*?<a\s+class="[^"]*?icon-arrow_right[^"]*?"' _PAGE_TEMPLATE = 'https://www.dailymotion.com/playlist/%s/%s' def _extract_entries(self, id): @@ -190,10 +190,9 @@ class DailymotionPlaylistIE(DailymotionBaseInfoExtractor): webpage = self._download_webpage(request, id, u'Downloading page %s' % pagenum) - playlist_el = get_element_by_attribute(u'class', u'row video_list', webpage) - video_ids.extend(re.findall(r'data-id="(.+?)"', playlist_el)) + video_ids.extend(re.findall(r'data-id="(.+?)"', webpage)) - if re.search(self._MORE_PAGES_INDICATOR, webpage, re.DOTALL) is None: + 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)] @@ -212,8 +211,7 @@ class DailymotionPlaylistIE(DailymotionBaseInfoExtractor): class DailymotionUserIE(DailymotionPlaylistIE): IE_NAME = u'dailymotion:user' - _VALID_URL = r'(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/user/(?P<user>[^/]+)' - _MORE_PAGES_INDICATOR = r'<div class="next">.*?<a.*?href="/user/.+?".*?>.*?</a>.*?</div>' + _VALID_URL = r'https?://(?:www\.)?dailymotion\.[a-z]{2,3}/user/(?P<user>[^/]+)' _PAGE_TEMPLATE = 'http://www.dailymotion.com/user/%s/%s' def _real_extract(self, url): |