-# encoding: utf-8
from __future__ import unicode_literals
-import json
import re
from .common import InfoExtractor
+from ..compat import compat_str
from ..utils import (
- ExtractorError,
+ clean_html,
+ int_or_none,
+ unified_timestamp,
+ update_url_query,
)
class RBMARadioIE(InfoExtractor):
- _VALID_URL = r'https?://(?:www\.)?rbmaradio\.com/shows/(?P<videoID>[^/]+)$'
+ _VALID_URL = r'https?://(?:www\.)?rbmaradio\.com/shows/(?P<show_id>[^/]+)/episodes/(?P<id>[^/?#&]+)'
_TEST = {
- 'url': 'http://www.rbmaradio.com/shows/ford-lopatin-live-at-primavera-sound-2011',
+ 'url': 'https://www.rbmaradio.com/shows/main-stage/episodes/ford-lopatin-live-at-primavera-sound-2011',
'md5': '6bc6f9bcb18994b4c983bc3bf4384d95',
'info_dict': {
'id': 'ford-lopatin-live-at-primavera-sound-2011',
'ext': 'mp3',
- "uploader_id": "ford-lopatin",
- "location": "Spain",
- "description": "Joel Ford and Daniel ’Oneohtrix Point Never’ Lopatin fly their midified pop extravaganza to Spain. Live at Primavera Sound 2011.",
- "uploader": "Ford & Lopatin",
- "title": "Live at Primavera Sound 2011",
+ 'title': 'Main Stage - Ford & Lopatin',
+ 'description': 'md5:4f340fb48426423530af5a9d87bd7b91',
+ 'thumbnail': r're:^https?://.*\.jpg',
+ 'duration': 2452,
+ 'timestamp': 1307103164,
+ 'upload_date': '20110603',
},
}
def _real_extract(self, url):
- m = re.match(self._VALID_URL, url)
- video_id = m.group('videoID')
+ mobj = re.match(self._VALID_URL, url)
+ show_id = mobj.group('show_id')
+ episode_id = mobj.group('id')
- webpage = self._download_webpage(url, video_id)
+ webpage = self._download_webpage(url, episode_id)
- json_data = self._search_regex(r'window\.gon.*?gon\.show=(.+?);$',
- webpage, 'json data', flags=re.MULTILINE)
+ episode = self._parse_json(
+ self._search_regex(
+ r'__INITIAL_STATE__\s*=\s*({.+?})\s*</script>',
+ webpage, 'json data'),
+ episode_id)['episodes'][show_id][episode_id]
- try:
- data = json.loads(json_data)
- except ValueError as e:
- raise ExtractorError('Invalid JSON: ' + str(e))
+ title = episode['title']
- video_url = data['akamai_url'] + '&cbr=256'
+ show_title = episode.get('showTitle')
+ if show_title:
+ title = '%s - %s' % (show_title, title)
+
+ formats = [{
+ 'url': update_url_query(episode['audioURL'], query={'cbr': abr}),
+ 'format_id': compat_str(abr),
+ 'abr': abr,
+ 'vcodec': 'none',
+ } for abr in (96, 128, 256)]
+
+ description = clean_html(episode.get('longTeaser'))
+ thumbnail = self._proto_relative_url(episode.get('imageURL', {}).get('landscape'))
+ duration = int_or_none(episode.get('duration'))
+ timestamp = unified_timestamp(episode.get('publishedAt'))
return {
- 'id': video_id,
- 'url': video_url,
- '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'),
+ 'id': episode_id,
+ 'title': title,
+ 'description': description,
+ 'thumbnail': thumbnail,
+ 'duration': duration,
+ 'timestamp': timestamp,
+ 'formats': formats,
}