[tumblr] Added support for HD video where available (#7036)

[tumblr] Replaced test URL for HD video as old one lead to 404

[tumblr] Don't make assumptions about video resolution, cleaner handling of no HD version available

[tumblr] Removed extraneous resolution key in HD video tests
This commit is contained in:
Oli Allen 2015-10-01 22:50:12 +01:00 committed by Sergey M․
parent e759a00119
commit 2a27e66234

View File

@ -28,6 +28,32 @@ class TumblrIE(InfoExtractor):
'description': 'md5:dba62ac8639482759c8eb10ce474586a',
'thumbnail': 're:http://.*\.jpg',
}
}, {
'url': 'http://hdvideotest.tumblr.com/post/130323439814/test-description-for-my-hd-video',
'md5': '99a84522f60972bf064a0b80f87bcbb5',
'info_dict': {
'id': '130323439814',
'ext': 'mp4',
'title': 'HD Video Testing \u2014 Test description for my HD video',
'description': 'md5:97cc3ab5fcd27ee4af6356701541319c',
'thumbnail': 're:http://.*\.jpg',
},
'params': {
'format': 'sd',
},
}, {
'url': 'http://hdvideotest.tumblr.com/post/130323439814/test-description-for-my-hd-video',
'md5': '7ae503065ad150122dc3089f8cf1546c',
'info_dict': {
'id': '130323439814',
'ext': 'mp4',
'title': 'HD Video Testing \u2014 Test description for my HD video',
'description': 'md5:97cc3ab5fcd27ee4af6356701541319c',
'thumbnail': 're:http://.*\.jpg',
},
'params': {
'format': 'hd',
},
}, {
'url': 'http://naked-yogi.tumblr.com/post/118312946248/naked-smoking-stretching',
'md5': 'de07e5211d60d4f3a2c3df757ea9f6ab',
@ -57,6 +83,8 @@ def _real_extract(self, url):
video_id = m_url.group('id')
blog = m_url.group('blog_name')
video_urls = []
url = 'http://%s.tumblr.com/post/%s/' % (blog, video_id)
webpage, urlh = self._download_webpage_handle(url, video_id)
@ -68,8 +96,32 @@ def _real_extract(self, url):
iframe = self._download_webpage(iframe_url, video_id,
'Downloading iframe page')
video_url = self._search_regex(r'<source src="([^"]+)"',
iframe, 'video url')
sd_video_url = self._search_regex(r'<source src="([^"]+)"',
iframe, 'sd video url')
resolution_id = sd_video_url.split("/")[-1] + 'p'
if len(resolution_id) != 4:
resolution_id = None
video_urls.append({
'ext': 'mp4',
'format_id': 'sd',
'url': sd_video_url,
'resolution': resolution_id,
})
hd_video_url = self._search_regex(r'hdUrl":"([^"]+)"', iframe,
'hd video url', default=None)
if hd_video_url:
hd_video_url = hd_video_url.replace("\\", "")
resolution_id = hd_video_url.split("/")[-1] + 'p'
if len(resolution_id) != 4:
resolution_id = None
video_urls.append({
'ext': 'mp4',
'format_id': 'hd',
'url': hd_video_url,
'resolution': resolution_id,
})
# The only place where you can get a title, it's not complete,
# but searching in other places doesn't work for all videos
@ -79,7 +131,7 @@ def _real_extract(self, url):
return {
'id': video_id,
'url': video_url,
'formats': video_urls,
'ext': 'mp4',
'title': video_title,
'description': self._og_search_description(webpage, default=None),