X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/782e271dfe61ed8d5dbf100286ad876068ea585c..34bfb8236336b5e77b689e55cc2e70a247efb96d:/youtube_dl/extractor/dailymotion.py
diff --git a/youtube_dl/extractor/dailymotion.py b/youtube_dl/extractor/dailymotion.py
index 3f012ae..7d83539 100644
--- a/youtube_dl/extractor/dailymotion.py
+++ b/youtube_dl/extractor/dailymotion.py
@@ -10,6 +10,7 @@ from ..utils import (
compat_str,
get_element_by_attribute,
get_element_by_id,
+ orderedSet,
ExtractorError,
)
@@ -27,15 +28,31 @@ class DailymotionIE(DailymotionBaseInfoExtractor, SubtitlesInfoExtractor):
_VALID_URL = r'(?i)(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/(?:embed/)?video/([^/]+)'
IE_NAME = u'dailymotion'
- _TEST = {
- u'url': u'http://www.dailymotion.com/video/x33vw9_tutoriel-de-youtubeur-dl-des-video_tech',
- u'file': u'x33vw9.mp4',
- u'md5': u'392c4b85a60a90dc4792da41ce3144eb',
- u'info_dict': {
- u"uploader": u"Amphora Alex and Van .",
- u"title": u"Tutoriel de Youtubeur\"DL DES VIDEO DE YOUTUBE\""
- }
- }
+ _TESTS = [
+ {
+ u'url': u'http://www.dailymotion.com/video/x33vw9_tutoriel-de-youtubeur-dl-des-video_tech',
+ u'file': u'x33vw9.mp4',
+ u'md5': u'392c4b85a60a90dc4792da41ce3144eb',
+ u'info_dict': {
+ u"uploader": u"Amphora Alex and Van .",
+ u"title": u"Tutoriel de Youtubeur\"DL DES VIDEO DE YOUTUBE\""
+ }
+ },
+ # Vevo video
+ {
+ u'url': u'http://www.dailymotion.com/video/x149uew_katy-perry-roar-official_musi',
+ u'file': u'USUV71301934.mp4',
+ u'info_dict': {
+ u'title': u'Roar (Official)',
+ u'uploader': u'Katy Perry',
+ u'upload_date': u'20130905',
+ },
+ u'params': {
+ u'skip_download': True,
+ },
+ u'skip': u'VEVO is only available in some countries',
+ },
+ ]
def _real_extract(self, url):
# Extract id and simplified title from URL
@@ -53,6 +70,15 @@ class DailymotionIE(DailymotionBaseInfoExtractor, SubtitlesInfoExtractor):
# Extract URL, uploader and title from webpage
self.report_extraction(video_id)
+ # It may just embed a vevo video:
+ m_vevo = re.search(
+ r'[\w]*)',
+ webpage)
+ if m_vevo is not None:
+ vevo_id = m_vevo.group('id')
+ self.to_screen(u'Vevo video detected: %s' % vevo_id)
+ return self.url_result(u'vevo:%s' % vevo_id, ie='Vevo')
+
video_uploader = self._search_regex([r'(?im)[^<]+?]+?>([^<]+?)',
# Looking for official user
r'<(?:span|a) .*?rel="author".*?>([^<]+?)'],
@@ -133,12 +159,12 @@ class DailymotionPlaylistIE(DailymotionBaseInfoExtractor):
id, u'Downloading page %s' % pagenum)
playlist_el = get_element_by_attribute(u'class', u'video_list', webpage)
- video_ids.extend(re.findall(r'data-id="(.+?)" data-ext-id', playlist_el))
+ video_ids.extend(re.findall(r'data-id="(.+?)"', playlist_el))
if re.search(self._MORE_PAGES_INDICATOR, webpage, re.DOTALL) is None:
break
return [self.url_result('http://www.dailymotion.com/video/%s' % video_id, 'Dailymotion')
- for video_id in video_ids]
+ for video_id in orderedSet(video_ids)]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)