diff options
author | Philipp Hagemeister <phihag@phihag.de> | 2014-08-22 01:38:59 +0200 |
---|---|---|
committer | Philipp Hagemeister <phihag@phihag.de> | 2014-08-22 01:38:59 +0200 |
commit | a200f4cee21093975d881190c6ff4227f5490594 (patch) | |
tree | fc4331eafefd59794093ed3140827005421487c0 | |
parent | ea6e8d545430ebd8cf622c5c04571f180452360e (diff) | |
parent | 83d35817f5e0960ffa750043a2add1247a3206ac (diff) |
Merge remote-tracking branch 'yasoob/master'
-rw-r--r-- | youtube_dl/extractor/__init__.py | 1 | ||||
-rw-r--r-- | youtube_dl/extractor/dump.py | 48 |
2 files changed, 49 insertions, 0 deletions
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index be7616edc..7ad5d9318 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -69,6 +69,7 @@ from .dfb import DFBIE from .dotsub import DotsubIE from .dreisat import DreiSatIE from .drtv import DRTVIE +from .dump import DumpIE from .defense import DefenseGouvFrIE from .discovery import DiscoveryIE from .divxstage import DivxStageIE diff --git a/youtube_dl/extractor/dump.py b/youtube_dl/extractor/dump.py new file mode 100644 index 000000000..4b756b20a --- /dev/null +++ b/youtube_dl/extractor/dump.py @@ -0,0 +1,48 @@ +# encoding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + ExtractorError, +) + +class DumpIE(InfoExtractor): + _VALID_URL = r'^https?://(?:www\.)?dump\.com/(?P<id>[a-zA-Z0-9]+)/' + + _TEST = { + u'url': u'http://www.dump.com/oneus/', + u'file': u'oneus.flv', + u'md5': u'ad71704d1e67dfd9e81e3e8b42d69d99', + u'info_dict': { + u"title": u"He's one of us.", + }, + } + + def _real_extract(self, url): + m = re.match(self._VALID_URL, url) + video_id = m.group('id') + + # Note: There is an easier-to-parse configuration at + # http://www.aparat.com/video/video/config/videohash/%video_id + # but the URL in there does not work + + webpage = self._download_webpage(url, video_id) + + try: + video_url = re.findall(r'file","(.+?.flv)"', webpage)[-1] + except IndexError: + raise ExtractorError(u'No video URL found') + + thumb = re.findall('<meta property="og:image" content="(.+?)"',webpage)[0] + + title = self._search_regex(r'<b>([^"]+)</b>', webpage, u'title') + + return { + 'id': video_id, + 'title': title, + 'url': video_url, + 'ext': 'flv', + 'thumbnail': thumb, + } |