aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/rbmaradio.py
diff options
context:
space:
mode:
authorSergey M․ <dstftw@gmail.com>2016-08-09 02:46:29 +0700
committerSergey M․ <dstftw@gmail.com>2016-08-09 02:46:29 +0700
commit3a380766d1d6abd83213319b41cdf9a18977a69c (patch)
treeebfca4e4357143e5cb12f10629e32d7a8e2fbe84 /youtube_dl/extractor/rbmaradio.py
parentaffaea0688780c03afe36bc81c7151e696649b5a (diff)
[rbmaradio] Improve, simplify and extract all formats (Closes #10242)
Diffstat (limited to 'youtube_dl/extractor/rbmaradio.py')
-rw-r--r--youtube_dl/extractor/rbmaradio.py69
1 files changed, 47 insertions, 22 deletions
diff --git a/youtube_dl/extractor/rbmaradio.py b/youtube_dl/extractor/rbmaradio.py
index 92f0d8f76..471928ef8 100644
--- a/youtube_dl/extractor/rbmaradio.py
+++ b/youtube_dl/extractor/rbmaradio.py
@@ -1,46 +1,71 @@
-# encoding: utf-8
from __future__ import unicode_literals
+import re
+
from .common import InfoExtractor
+from ..compat import compat_str
from ..utils import (
- clean_html
+ clean_html,
+ int_or_none,
+ unified_timestamp,
+ update_url_query,
)
class RBMARadioIE(InfoExtractor):
- _VALID_URL = r'https?://(?:www\.)?rbmaradio\.com/shows/[^/]+/episodes/(?P<id>[^/]+)$'
+ _VALID_URL = r'https?://(?:www\.)?rbmaradio\.com/shows/(?P<show_id>[^/]+)/episodes/(?P<id>[^/?#&]+)'
_TEST = {
'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',
- 'description': 'Joel Ford and Daniel ’Oneohtrix Point Never’ Lopatin fly their midified pop extravaganza to Spain. Live at Primavera Sound 2011.',
- 'title': 'Ford & Lopatin - Main Stage',
+ 'title': 'Main Stage - Ford & Lopatin',
+ 'description': 'md5:4f340fb48426423530af5a9d87bd7b91',
+ 'thumbnail': 're:^https?://.*\.jpg',
+ 'duration': 2452,
+ 'timestamp': 1307103164,
+ 'upload_date': '20110603',
},
}
def _real_extract(self, url):
- video_id = self._match_id(url)
+ mobj = re.match(self._VALID_URL, url)
+ show_id = mobj.group('show_id')
+ episode_id = mobj.group('id')
+
+ webpage = self._download_webpage(url, episode_id)
+
+ episode = self._parse_json(
+ self._search_regex(
+ r'__INITIAL_STATE__\s*=\s*({.+?})\s*</script>',
+ webpage, 'json data'),
+ episode_id)['episodes'][show_id][episode_id]
+
+ title = episode['title']
- webpage = self._download_webpage(url, video_id)
- json_data = self._search_regex(r'<script>window\.__INITIAL_STATE__\s*=\s*(.+?)</script>',
- webpage, 'json data')
- data = self._parse_json(json_data, video_id)
+ show_title = episode.get('showTitle')
+ if show_title:
+ title = '%s - %s' % (show_title, title)
- item = None
- for episode in data['episodes']:
- items = data['episodes'][episode]
- if video_id in items:
- item = items[video_id]
+ 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)]
- video_url = item['audioURL'] + '?cbr=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': item.get('title') + ' - ' + item.get('showTitle'),
- 'description': clean_html(item.get('longTeaser')),
- 'thumbnail': self._proto_relative_url(item.get('imageURL', {}).get('landscape')),
- 'duration': item.get('duration'),
+ 'id': episode_id,
+ 'title': title,
+ 'description': description,
+ 'thumbnail': thumbnail,
+ 'duration': duration,
+ 'timestamp': timestamp,
+ 'formats': formats,
}