R-yan/l1ving_youtube-dl
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

Improve the roosterteeth extractor by using the API

Browse Source 
This commit is here for improving the roosterteeth extractor by using the API and fix #16694
This commit is contained in:
Urgau 2018-06-11 17:29:54 +02:00 committed by GitHub
parent 93cffb1444
commit 74b57769db
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 35 additions and 46 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

81
youtube_dl/extractor/roosterteeth.py
View File

@ -1,18 +1,17 @@
# coding: utf-8 # coding: utf-8
from __future__ import unicode_literals from __future__ import unicode_literals
import re
from .common import InfoExtractor from .common import InfoExtractor
from ..compat import (
compat_HTTPError,
)
from ..utils import ( from ..utils import (
ExtractorError, ExtractorError,
int_or_none, int_or_none,
strip_or_none, str_or_none,
unescapeHTML,
urlencode_postdata, urlencode_postdata,
) )
class RoosterTeethIE(InfoExtractor): class RoosterTeethIE(InfoExtractor):
_VALID_URL = r'https?://(?:.+?\.)?roosterteeth\.com/episode/(?P<id>[^/?#&]+)' _VALID_URL = r'https?://(?:.+?\.)?roosterteeth\.com/episode/(?P<id>[^/?#&]+)'
_LOGIN_URL = 'https://roosterteeth.com/login' _LOGIN_URL = 'https://roosterteeth.com/login'
@ -29,7 +28,6 @@ class RoosterTeethIE(InfoExtractor):
'thumbnail': r're:^https?://.*\.png$', 'thumbnail': r're:^https?://.*\.png$',
'series': 'Million Dollars, But...', 'series': 'Million Dollars, But...',
'episode': 'Million Dollars, But... The Game Announcement', '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', 'url': 'http://achievementhunter.roosterteeth.com/episode/off-topic-the-achievement-hunter-podcast-2016-i-didn-t-think-it-would-pass-31',
@ -50,7 +48,7 @@ class RoosterTeethIE(InfoExtractor):
}] }]
def _login(self): def _login(self):
username, password = self._get_login_info() (username, password) = self._get_login_info()
if username is None: if username is None:
return return
@ -90,51 +88,42 @@ class RoosterTeethIE(InfoExtractor):
def _real_extract(self, url): def _real_extract(self, url):
display_id = self._match_id(url) display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id) try:
json_m3u8 = self._download_json(
episode = strip_or_none(unescapeHTML(self._search_regex( 'https://svod-be.roosterteeth.com/api/v1/episodes/%s/videos' % display_id,
(r'videoTitle\s*=\s*(["\'])(?P<title>(?:(?!\1).)+)\1', display_id, 'Downloading JSON m3u8')
r'<title>(?P<title>[^<]+)</title>'), webpage, 'title', json_metadata = self._download_json(
default=None, group='title'))) 'https://svod-be.roosterteeth.com/api/v1/episodes/%s/' % display_id,
display_id)
title = strip_or_none(self._og_search_title( except ExtractorError as e:
webpage, default=None)) or episode if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403:
self.raise_login_required('This video is only available for FIRST memebers')
m3u8_url = self._search_regex( raise
r'file\s*:\s*(["\'])(?P<url>http.+?\.m3u8.*?)\1',
webpage, 'm3u8 url', default=None, group='url')
if not m3u8_url:
if re.search(r'<div[^>]+class=["\']non-sponsor', webpage):
self.raise_login_required(
'%s is only available for FIRST members' % display_id)
if re.search(r'<div[^>]+class=["\']golive-gate', webpage):
self.raise_login_required('%s is not available yet' % display_id)
try:
m3u8_url = json_m3u8['data'][0]['attributes']['url']
except:
raise ExtractorError('Unable to extract m3u8 URL') raise ExtractorError('Unable to extract m3u8 URL')
formats = self._extract_m3u8_formats( formats = self._extract_m3u8_formats(
m3u8_url, display_id, ext='mp4', m3u8_url, display_id, ext='mp4',
entry_protocol='m3u8_native', m3u8_id='hls') entry_protocol='m3u8_native', m3u8_id='hls')
self._sort_formats(formats) self._sort_formats(formats)
description = strip_or_none(self._og_search_description(webpage)) json_body = json_metadata['data'][0]
thumbnail = self._proto_relative_url(self._og_search_thumbnail(webpage)) json_attributes = json_body['attributes']
series = self._search_regex( display_title = json_attributes['display_title']
(r'<h2>More ([^<]+)</h2>', r'<a[^>]+>See All ([^<]+) Videos<'),
webpage, 'series', fatal=False) title = str_or_none(self._search_regex(r': ([\w]+)$', display_title, 'title'))
episode = int_or_none(self._search_regex(r':E([\d]+)', display_title, 'episode', fatal=False))
comment_count = int_or_none(self._search_regex( season = int_or_none(self._search_regex(r'^V([\d]+):E', display_title, 'season', fatal=False))
r'>Comments \((\d+)\)<', webpage,
'comment count', fatal=False)) video_id = str(json_body.get('id'))
thumbnail = json_body['included']['images'][0]['attributes']['large']
video_id = self._search_regex( description = json_attributes.get('description')
(r'containerId\s*=\s*["\']episode-(\d+)\1', series = json_attributes.get('show_title')
r'<div[^<]+id=["\']episode-(\d+)'), webpage,
'video id', default=display_id)
return { return {
'id': video_id, 'id': video_id,
'display_id': display_id, 'display_id': display_id,
@ -142,7 +131,7 @@ class RoosterTeethIE(InfoExtractor):
'description': description, 'description': description,
'thumbnail': thumbnail, 'thumbnail': thumbnail,
'series': series, 'series': series,
'season': season,
'episode': episode, 'episode': episode,
'comment_count': comment_count,
'formats': formats, 'formats': formats,
} }