diff options
| -rwxr-xr-x | youtube_dl/InfoExtractors.py | 34 | ||||
| -rw-r--r-- | youtube_dl/extractor/tumblr.py | 41 |
2 files changed, 42 insertions, 33 deletions
diff --git a/youtube_dl/InfoExtractors.py b/youtube_dl/InfoExtractors.py index bcf927252..2b8e6e6c6 100755 --- a/youtube_dl/InfoExtractors.py +++ b/youtube_dl/InfoExtractors.py @@ -52,6 +52,7 @@ from .extractor.spiegel import SpiegelIE from .extractor.stanfordoc import StanfordOpenClassroomIE from .extractor.steam import SteamIE from .extractor.ted import TEDIE +from .extractor.tumblr import TumblrIE from .extractor.ustream import UstreamIE from .extractor.vimeo import VimeoIE from .extractor.worldstarhiphop import WorldStarHipHopIE @@ -96,39 +97,6 @@ from .extractor.zdf import ZDFIE -class TumblrIE(InfoExtractor): - _VALID_URL = r'http://(?P<blog_name>.*?)\.tumblr\.com/((post)|(video))/(?P<id>\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(?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(u'Unable to extract video') - video_url = video.group('video_url') - ext = video.group('ext') - - video_thumbnail = self._search_regex(r'posters(.*?)\[\\x22(?P<thumb>.*?)\\x22', - webpage, u'thumbnail', fatal=False) # We pick the first poster - if video_thumbnail: video_thumbnail = video_thumbnail.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 - video_title = self._html_search_regex(r'<title>(?P<title>.*?)</title>', - webpage, u'title', flags=re.DOTALL) - - return [{'id': video_id, - 'url': video_url, - 'title': video_title, - 'thumbnail': video_thumbnail, - 'ext': ext - }] class BandcampIE(InfoExtractor): _VALID_URL = r'http://.*?\.bandcamp\.com/track/(?P<title>.*)' diff --git a/youtube_dl/extractor/tumblr.py b/youtube_dl/extractor/tumblr.py new file mode 100644 index 000000000..b0851b4f9 --- /dev/null +++ b/youtube_dl/extractor/tumblr.py @@ -0,0 +1,41 @@ +import re + +from .common import InfoExtractor +from ..utils import ( + ExtractorError, +) + + +class TumblrIE(InfoExtractor): + _VALID_URL = r'http://(?P<blog_name>.*?)\.tumblr\.com/((post)|(video))/(?P<id>\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(?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(u'Unable to extract video') + video_url = video.group('video_url') + ext = video.group('ext') + + video_thumbnail = self._search_regex(r'posters(.*?)\[\\x22(?P<thumb>.*?)\\x22', + webpage, u'thumbnail', fatal=False) # We pick the first poster + if video_thumbnail: video_thumbnail = video_thumbnail.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 + video_title = self._html_search_regex(r'<title>(?P<title>.*?)</title>', + webpage, u'title', flags=re.DOTALL) + + return [{'id': video_id, + 'url': video_url, + 'title': video_title, + 'thumbnail': video_thumbnail, + 'ext': ext + }] |