From c15e024141727e5eed8056d3b2732f4f7553b2b4 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Jaime=20Marqui=CC=81nez=20Ferra=CC=81ndiz?= Date: Mon, 22 Apr 2013 21:07:49 +0200 Subject: [PATCH] TumblrIE I haven't found many videos to test, so it may not work for all. --- test/tests.json | 9 +++++++++ youtube_dl/InfoExtractors.py | 35 +++++++++++++++++++++++++++++++++++ 2 files changed, 44 insertions(+) diff --git a/test/tests.json b/test/tests.json index 7808a07de..2b56738a0 100644 --- a/test/tests.json +++ b/test/tests.json @@ -337,6 +337,15 @@ "title": "11.04.2013 09:23 Uhr - Tagesschau in 100 Sekunden" }, "skip": "Requires rtmpdump" + }, + { + "name": "Tumblr", + "url": "http://birthdayproject2012.tumblr.com/post/17258355236/a-sample-video-from-leeann-if-you-need-an-idea", + "file": "17258355236.mp4", + "md5": "7c6a514d691b034ccf8567999e9e88a3", + "info_dict": { + "title": "A sample video from LeeAnn. (If you need an idea..." + } } ] diff --git a/youtube_dl/InfoExtractors.py b/youtube_dl/InfoExtractors.py index ff1f07e9b..6a6545c9b 100755 --- a/youtube_dl/InfoExtractors.py +++ b/youtube_dl/InfoExtractors.py @@ -4327,6 +4327,40 @@ class ARDIE(InfoExtractor): info["url"] = stream["video_url"] return [info] +class TumblrIE(InfoExtractor): + _VALID_URL = r'http://(?P.*?).tumblr.com/((post)|(video))/(?P\d*)/(.*?)' + + def _real_extract(self, url): + m_url = re.match(self._VALID_URL, url) + video_id = m_url.group('id') + blog = m_url.group('blog_name') + + url = 'http://%s.tumblr.com/post/%s/' % (blog, video_id) + webpage = self._download_webpage(url, video_id) + + re_video = r'src=\\x22(?Phttp://%s.tumblr.com/video_file/%s/(.*?))\\x22 type=\\x22video/(?P.*?)\\x22' % (blog, video_id) + video = re.search(re_video, webpage) + if video is None: + self.to_screen("No video founded") + return [] + video_url = video.group('video_url') + ext = video.group('ext') + + re_thumb = r'posters(.*?)\[\\x22(?P.*?)\\x22' # We pick the first poster + thumb = re.search(re_thumb, webpage).group('thumb').replace('\\', '') + + # The only place where you can get a title, it's not complete, + # but searching in other places doesn't work for all videos + re_title = r'(.*?) - (?P<title>.*?)' + title = unescapeHTML(re.search(re_title, webpage).group('title')) + + return [{'id': video_id, + 'url': video_url, + 'title': title, + 'thumbnail': thumb, + 'ext': ext + }] + def gen_extractors(): """ Return a list of an instance of every supported extractor. @@ -4381,6 +4415,7 @@ def gen_extractors(): SpiegelIE(), LiveLeakIE(), ARDIE(), + TumblrIE(), GenericIE() ]