yt-dlp/youtube_dl/extractor/rbmaradio.py

58 lines
1.9 KiB
Python
Raw Normal View History

# encoding: utf-8
from __future__ import unicode_literals
2013-06-23 20:09:32 +00:00
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<videoID>[^/]+)$'
2013-06-27 18:46:46 +00:00
_TEST = {
'url': 'http://www.rbmaradio.com/shows/ford-lopatin-live-at-primavera-sound-2011',
'file': 'ford-lopatin-live-at-primavera-sound-2011.mp3',
'md5': '6bc6f9bcb18994b4c983bc3bf4384d95',
'info_dict': {
"uploader_id": "ford-lopatin",
"location": "Spain",
"description": "Joel Ford and Daniel Oneohtrix Point Never Lopatin fly their midified pop extravaganza to Spain. Live at Primavera Sound 2011.",
"uploader": "Ford & Lopatin",
"title": "Live at Primavera Sound 2011",
},
2013-06-27 18:46:46 +00:00
}
2013-06-23 20:09:32 +00:00
def _real_extract(self, url):
m = re.match(self._VALID_URL, url)
video_id = m.group('videoID')
webpage = self._download_webpage(url, video_id)
json_data = self._search_regex(r'window\.gon.*?gon\.show=(.+?);$',
webpage, 'json data', flags=re.MULTILINE)
2013-06-23 20:09:32 +00:00
try:
data = json.loads(json_data)
except ValueError as e:
raise ExtractorError('Invalid JSON: ' + str(e))
2013-06-23 20:09:32 +00:00
video_url = data['akamai_url'] + '&cbr=256'
url_parts = compat_urllib_parse_urlparse(video_url)
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'),
2013-06-23 20:09:32 +00:00
}