From c54283824c72434c31e0dcce1d09fc3259dbcdc0 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Jaime=20Marqui=CC=81nez=20Ferra=CC=81ndiz?=
<jaime.marquinez.ferrandiz@gmail.com>
Date: Tue, 1 Oct 2013 15:05:41 +0200
Subject: [PATCH] [dailymotion] Detect vevo videos (fixes #1532)
All videos from the Vevo user, just embed videos from vevo.com
---
youtube_dl/extractor/dailymotion.py | 43 +++++++++++++++++++++++------
1 file changed, 34 insertions(+), 9 deletions(-)
diff --git a/youtube_dl/extractor/dailymotion.py b/youtube_dl/extractor/dailymotion.py
index 3f012aedc1..259806f385 100644
--- a/youtube_dl/extractor/dailymotion.py
+++ b/youtube_dl/extractor/dailymotion.py
@@ -27,15 +27,31 @@ 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 +69,15 @@ 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'<link rel="video_src" href="[^"]*?vevo.com[^"]*?videoId=(?P<id>[\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)<span class="owner[^\"]+?">[^<]+?<a [^>]+?>([^<]+?)</a>',
# Looking for official user
r'<(?:span|a) .*?rel="author".*?>([^<]+?)</'],