R-yan/l1ving_youtube-dl
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

find video parameters in iframe

Browse Source
This commit is contained in:
MikeCol 2014-09-08 00:54:14 +02:00
parent e154762c74
commit 1323ab2a8f
1 changed files with 43 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

52
youtube_dl/extractor/tumblr.py
View File

@ -11,7 +11,8 @@ from ..utils import (
class TumblrIE(InfoExtractor):
_VALID_URL = r'http://(?P<blog_name>.*?)\.tumblr\.com/((post)|(video))/(?P<id>\d*)($|/)'
_TESTS = [{
_TESTS = [
{
'url': 'http://tatianamaslanydaily.tumblr.com/post/54196191430/orphan-black-dvd-extra-behind-the-scenes',
'md5': '479bb068e5b16462f5176a6828829767',
'info_dict': {
@ -31,29 +32,61 @@ class TumblrIE(InfoExtractor):
'description': 'md5:dba62ac8639482759c8eb10ce474586a',
'thumbnail': 're:http://.*\.jpg',
}
}]
}, {
'url': 'http://anotherkindofhorse.tumblr.com/post/96805380497',
'md5': '84a5c3c1cb2325a9a9e900d1726e956a',
'info_dict': {
'id': '96805380497',
'ext': 'mp4',
'title': 'Tumblr',
'description': 'md5:06e250cb873c721abee97e543f9997d3',
'thumbnail': 're:http://.*\.jpg',
}
}
]
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)
video_thumbnails = []
# try "old" way first
purl = 'http://%s.tumblr.com/post/%s/' % (blog, video_id)
webpage = self._download_webpage(purl, video_id)
re_video = r'src=\\x22(?P<video_url>http://%s\.tumblr\.com/video_file/%s/(.*?))\\x22 type=\\x22video/(?P<ext>.*?)\\x22' % (blog, video_id)
video = re.search(re_video, webpage)
if video is None:
raise ExtractorError('Unable to extract video')
video_url = video.group('video_url')
ext = video.group('ext')
video_thumbnail = self._search_regex(
r'posters.*?\[\\x22(.*?)\\x22',
webpage, 'thumbnail', fatal=False) # We pick the first poster
webpage, 'thumbnail', default="", fatal=False) # We pick the first poster
if video_thumbnail:
video_thumbnail = video_thumbnail.replace('\\\\/', '/')
if video is None:
# This did not work - search for iframe
iframe_m = re.search(r'<div class="videoWrapper">.+?<iframe src="(.+?)"',webpage,re.S)
if iframe_m is not None:
iframe_url = iframe_m.group(1)
webpage = self._download_webpage(iframe_url, video_id)
video = re.search(r'source src="(?P<video_url>.+?/video_file/.+?)" type="video/(?P<ext>.+?)"', webpage)
thumbs_match = re.search(r'posters.*?\[(.+?)]', webpage)
if thumbs_match is not None:
thumbs = [ w[1:-1].replace(r'\/',r'/') for w in thumbs_match.group(1).split(',') ]
if len(thumbs) > 0:
video_thumbnail = thumbs[0]
video_thumbnails = [ {"url": ele} for ele in thumbs ]
if video is None:
raise ExtractorError('Unable to extract video')
video_url = video.group('video_url')
ext = video.group('ext')
# The only place where you can get a title, it's not complete,
# but searching in other places doesn't work for all videos
video_title = self._html_search_regex(r'<title>(?P<title>.*?)(?: \| Tumblr)?</title>',
@ -64,5 +97,6 @@ class TumblrIE(InfoExtractor):
'title': video_title,
'description': self._html_search_meta('description', webpage),
'thumbnail': video_thumbnail,
'thumbnails': video_thumbnails,
'ext': ext
}]