From e10e576fed8264d52b186adfeb4eb53183a75959 Mon Sep 17 00:00:00 2001 From: Philipp Hagemeister Date: Sun, 23 Jun 2013 22:09:32 +0200 Subject: [RBMARadio] move into own file --- youtube_dl/extractor/rbmaradio.py | 44 +++++++++++++++++++++++++++++++++++++++ 1 file changed, 44 insertions(+) create mode 100644 youtube_dl/extractor/rbmaradio.py (limited to 'youtube_dl/extractor') diff --git a/youtube_dl/extractor/rbmaradio.py b/youtube_dl/extractor/rbmaradio.py new file mode 100644 index 000000000..0c75eee2a --- /dev/null +++ b/youtube_dl/extractor/rbmaradio.py @@ -0,0 +1,44 @@ +import json +import re + +from .common import InfoExtractor +from ..utils import ( + compat_urllib_parse_urlparse, + + ExtractorError, +) + + +class RBMARadioIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?rbmaradio\.com/shows/(?P[^/]+)$' + + def _real_extract(self, url): + m = re.match(self._VALID_URL, url) + video_id = m.group('videoID') + + webpage = self._download_webpage(url, video_id) + + json_data = self._search_regex(r'window\.gon.*?gon\.show=(.+?);$', + webpage, u'json data', flags=re.MULTILINE) + + try: + data = json.loads(json_data) + except ValueError as e: + raise ExtractorError(u'Invalid JSON: ' + str(e)) + + video_url = data['akamai_url'] + '&cbr=256' + url_parts = compat_urllib_parse_urlparse(video_url) + video_ext = url_parts.path.rpartition('.')[2] + info = { + 'id': video_id, + 'url': video_url, + 'ext': video_ext, + 'title': data['title'], + 'description': data.get('teaser_text'), + 'location': data.get('country_of_origin'), + 'uploader': data.get('host', {}).get('name'), + 'uploader_id': data.get('host', {}).get('slug'), + 'thumbnail': data.get('image', {}).get('large_url_2x'), + 'duration': data.get('duration'), + } + return [info] -- cgit v1.2.3