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 .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..b2fb56e70 --- /dev/null +++ b/youtube_dl/extractor/hotnewhiphop.py @@ -0,0 +1,42 @@ +import re +import base64 + +from .common import InfoExtractor + + +class HotNewHipHopIE(InfoExtractor): + _VALID_URL = r'(http://www\.hotnewhiphop.com/.*\.(?P.*)\.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) + + video_url_base64 = self._search_regex(r'data-path="(.*?)"', + webpage_src, u'video URL', fatal=False) + + if video_url_base64 == None: + video_url = self._search_regex(r'"contentUrl" content="(.*?)"', webpage_src, + u'video URL') + return self.url_result(video_url, ie='Youtube') + + video_url = base64.b64decode(video_url_base64) + + video_title = self._html_search_regex(r"(.*)", + 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