diff --git a/youtube_dl/extractor/roosterteeth.py b/youtube_dl/extractor/roosterteeth.py
index 857434540..d3eeeba62 100644
--- a/youtube_dl/extractor/roosterteeth.py
+++ b/youtube_dl/extractor/roosterteeth.py
@@ -4,11 +4,14 @@
import re
from .common import InfoExtractor
+from ..compat import (
+ compat_HTTPError,
+ compat_str,
+)
from ..utils import (
ExtractorError,
int_or_none,
- strip_or_none,
- unescapeHTML,
+ str_or_none,
urlencode_postdata,
)
@@ -21,15 +24,14 @@ class RoosterTeethIE(InfoExtractor):
'url': 'http://roosterteeth.com/episode/million-dollars-but-season-2-million-dollars-but-the-game-announcement',
'md5': 'e2bd7764732d785ef797700a2489f212',
'info_dict': {
- 'id': '26576',
+ 'id': '9156',
'display_id': 'million-dollars-but-season-2-million-dollars-but-the-game-announcement',
'ext': 'mp4',
- 'title': 'Million Dollars, But...: Million Dollars, But... The Game Announcement',
- 'description': 'md5:0cc3b21986d54ed815f5faeccd9a9ca5',
+ 'title': 'Million Dollars, But... The Game Announcement',
+ 'description': 'md5:168a54b40e228e79f4ddb141e89fe4f5',
'thumbnail': r're:^https?://.*\.png$',
'series': 'Million Dollars, But...',
'episode': 'Million Dollars, But... The Game Announcement',
- 'comment_count': int,
},
}, {
'url': 'http://achievementhunter.roosterteeth.com/episode/off-topic-the-achievement-hunter-podcast-2016-i-didn-t-think-it-would-pass-31',
@@ -89,60 +91,55 @@ def _real_initialize(self):
def _real_extract(self, url):
display_id = self._match_id(url)
+ api_episode_url = 'https://svod-be.roosterteeth.com/api/v1/episodes/%s' % display_id
- webpage = self._download_webpage(url, display_id)
-
- episode = strip_or_none(unescapeHTML(self._search_regex(
- (r'videoTitle\s*=\s*(["\'])(?P
(?:(?!\1).)+)\1',
- r'(?P[^<]+)'), webpage, 'title',
- default=None, group='title')))
-
- title = strip_or_none(self._og_search_title(
- webpage, default=None)) or episode
-
- m3u8_url = self._search_regex(
- r'file\s*:\s*(["\'])(?Phttp.+?\.m3u8.*?)\1',
- webpage, 'm3u8 url', default=None, group='url')
-
- if not m3u8_url:
- if re.search(r']+class=["\']non-sponsor', webpage):
- self.raise_login_required(
- '%s is only available for FIRST members' % display_id)
-
- if re.search(r'
]+class=["\']golive-gate', webpage):
- self.raise_login_required('%s is not available yet' % display_id)
-
- raise ExtractorError('Unable to extract m3u8 URL')
+ try:
+ m3u8_url = self._download_json(
+ api_episode_url + '/videos', display_id,
+ 'Downloading video JSON metadata')['data'][0]['attributes']['url']
+ except ExtractorError as e:
+ if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403:
+ if self._parse_json(e.cause.read().decode(), display_id).get('access') is False:
+ self.raise_login_required(
+ '%s is only available for FIRST members' % display_id)
+ raise
formats = self._extract_m3u8_formats(
- m3u8_url, display_id, ext='mp4',
- entry_protocol='m3u8_native', m3u8_id='hls')
+ m3u8_url, display_id, 'mp4', 'm3u8_native', m3u8_id='hls')
self._sort_formats(formats)
- description = strip_or_none(self._og_search_description(webpage))
- thumbnail = self._proto_relative_url(self._og_search_thumbnail(webpage))
+ episode = self._download_json(
+ api_episode_url, display_id,
+ 'Downloading episode JSON metadata')['data'][0]
+ attributes = episode['attributes']
+ title = attributes.get('title') or attributes['display_title']
+ video_id = compat_str(episode['id'])
- series = self._search_regex(
- (r'
More ([^<]+)
', r'
]+>See All ([^<]+) Videos<'),
- webpage, 'series', fatal=False)
-
- comment_count = int_or_none(self._search_regex(
- r'>Comments \((\d+)\)<', webpage,
- 'comment count', fatal=False))
-
- video_id = self._search_regex(
- (r'containerId\s*=\s*["\']episode-(\d+)\1',
- r'