diff options
author | Johny Mo Swag <johnymo@me.com> | 2013-06-26 18:38:48 -0700 |
---|---|---|
committer | Johny Mo Swag <johnymo@me.com> | 2013-06-26 18:38:48 -0700 |
commit | 5b66de88592f124b586f90ef3bbd0e2d3d91968c (patch) | |
tree | f9d59974a12022eb9f3f108a6ecb6f745adb8b05 /youtube_dl | |
parent | e38af9e00c6183edd149d7c7debf580be4503444 (diff) |
Added HotNewHipHop IE
Diffstat (limited to 'youtube_dl')
-rw-r--r-- | youtube_dl/extractor/__init__.py | 2 | ||||
-rw-r--r-- | youtube_dl/extractor/hotnewhiphop.py | 39 |
2 files changed, 41 insertions, 0 deletions
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 2750fc8f9..cc818fcc1 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -18,6 +18,7 @@ from .gametrailers import GametrailersIE from .generic import GenericIE from .googleplus import GooglePlusIE from .googlesearch import GoogleSearchIE +from .hotnewhiphop import HotNewHipHopIE from .howcast import HowcastIE from .hypem import HypemIE from .ina import InaIE @@ -136,6 +137,7 @@ def gen_extractors(): TudouIE(), CSpanIE(), WimpIE(), + HotNewHipHopIE(), GenericIE() ] diff --git a/youtube_dl/extractor/hotnewhiphop.py b/youtube_dl/extractor/hotnewhiphop.py new file mode 100644 index 000000000..fb403b14e --- /dev/null +++ b/youtube_dl/extractor/hotnewhiphop.py @@ -0,0 +1,39 @@ +import re +import base64 + +from .common import InfoExtractor + + +class HotNewHipHopIE(InfoExtractor): + _VALID_URL = r'(http://www\.hotnewhiphop.com/.*\.(?P<id>.*)\.html)' + IE_NAME = u'HotNewHipHop' + + def _real_extract(self, url): + m = re.match(self._VALID_URL, url) + video_id = m.group('id') + + webpage_src = self._download_webpage(url, video_id) + + print video_id + + video_url_base64 = self._search_regex(r'data-path="(.*?)"', + webpage_src, u'video URL') + + video_url = base64.b64decode(video_url_base64) + + video_title = self._html_search_regex(r"<title>(.*)</title>", + webpage_src, u'title') + + #"og:image" content= + # Getting thumbnail and if not thumbnail sets correct title for WSHH candy video. + thumbnail = self._html_search_regex(r'"og:image" content="(.*)"', + webpage_src, u'thumbnail', fatal=False) + + results = [{ + 'id': video_id, + 'url' : video_url, + 'title' : video_title, + 'thumbnail' : thumbnail, + 'ext' : 'mp3', + }] + return results
\ No newline at end of file |