aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorNehal Patel <nehalvpatels+github@gmail.com>2016-06-22 02:58:42 -0500
committerSergey M․ <dstftw@gmail.com>2016-07-10 01:30:12 +0700
commit3121b25639a06cc9cad48fad0ce222482a58b216 (patch)
treec9d5992c9e7439e3787e9971ccbc5ba3adf01ba0
parent0286b85c79c278375cc5e71d3199bdc8284a5a11 (diff)
[roosterteeth] Add extractor
-rw-r--r--youtube_dl/extractor/extractors.py1
-rw-r--r--youtube_dl/extractor/roosterteeth.py112
2 files changed, 113 insertions, 0 deletions
diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py
index 9f70ce752..864c9af68 100644
--- a/youtube_dl/extractor/extractors.py
+++ b/youtube_dl/extractor/extractors.py
@@ -680,6 +680,7 @@ from .rice import RICEIE
from .ringtv import RingTVIE
from .ro220 import Ro220IE
from .rockstargames import RockstarGamesIE
+from .roosterteeth import RoosterTeethIE
from .rottentomatoes import RottenTomatoesIE
from .roxwel import RoxwelIE
from .rtbf import RTBFIE
diff --git a/youtube_dl/extractor/roosterteeth.py b/youtube_dl/extractor/roosterteeth.py
new file mode 100644
index 000000000..4053747d3
--- /dev/null
+++ b/youtube_dl/extractor/roosterteeth.py
@@ -0,0 +1,112 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import (
+ ExtractorError,
+ urlencode_postdata,
+)
+
+
+class RoosterTeethIE(InfoExtractor):
+ _VALID_URL = r'https?://(?:.+?\.)?roosterteeth\.com/episode/(?P<id>[^/?#&]+)'
+ _LOGIN_URL = 'https://roosterteeth.com/login'
+ _NETRC_MACHINE = 'roosterteeth'
+ _TESTS = [{
+ 'url': 'http://roosterteeth.com/episode/million-dollars-but-season-2-million-dollars-but-the-game-announcement',
+ 'info_dict': {
+ 'id': '26576',
+ 'ext': 'mp4',
+ 'title': 'Million Dollars, But... The Game Announcement',
+ 'thumbnail': 're:^https?://.*\.png$',
+ 'description': 'Introducing Million Dollars, But... The Game! Available for pre-order now at www.MDBGame.com ',
+ 'creator': 'Rooster Teeth',
+ 'series': 'Million Dollars, But...',
+ 'episode': 'Million Dollars, But... The Game Announcement',
+ 'episode_id': '26576',
+ },
+ 'params': {
+ 'skip_download': True, # m3u8 downloads
+ },
+ }, {
+ 'url': 'http://achievementhunter.roosterteeth.com/episode/off-topic-the-achievement-hunter-podcast-2016-i-didn-t-think-it-would-pass-31',
+ 'only_matching': True,
+ }, {
+ 'url': 'http://funhaus.roosterteeth.com/episode/funhaus-shorts-2016-austin-sucks-funhaus-shorts',
+ 'only_matching': True,
+ }, {
+ 'url': 'http://screwattack.roosterteeth.com/episode/death-battle-season-3-mewtwo-vs-shadow',
+ 'only_matching': True,
+ }, {
+ 'url': 'http://theknow.roosterteeth.com/episode/the-know-game-news-season-1-boring-steam-sales-are-better',
+ 'only_matching': True,
+ }]
+
+ def _login(self):
+ (username, password) = self._get_login_info()
+ if username is None or password is None:
+ return False
+
+ # token is required to authenticate request
+ login_page = self._download_webpage(self._LOGIN_URL, None, 'Getting login token', 'Unable to get login token')
+
+ login_form = self._hidden_inputs(login_page)
+ login_form.update({
+ 'username': username,
+ 'password': password,
+ })
+ login_payload = urlencode_postdata(login_form)
+
+ # required for proper responses
+ login_headers = {
+ 'Referer': self._LOGIN_URL,
+ }
+
+ login_request = self._download_webpage(
+ self._LOGIN_URL, None,
+ note='Logging in as %s' % username,
+ data=login_payload,
+ headers=login_headers)
+
+ if 'Authentication failed' in login_request:
+ raise ExtractorError(
+ 'Login failed (invalid username/password)', expected=True)
+
+ def _real_initialize(self):
+ self._login()
+
+ def _real_extract(self, url):
+ match_id = self._match_id(url)
+ webpage = self._download_webpage(url, match_id)
+
+ episode_id = self._html_search_regex(r"commentControls\('#comment-([0-9]+)'\)", webpage, 'episode id', match_id, False)
+
+ self.report_extraction(episode_id)
+
+ title = self._html_search_regex(r'<title>([^<]+)</title>', webpage, 'episode title', self._og_search_title(webpage), False)
+ thumbnail = self._og_search_thumbnail(webpage)
+ description = self._og_search_description(webpage)
+ creator = self._html_search_regex(r'<h3>Latest (.+) Gear</h3>', webpage, 'site', 'Rooster Teeth', False)
+ series = self._html_search_regex(r'<h2>More ([^<]+)</h2>', webpage, 'series', fatal=False)
+ episode = self._html_search_regex(r'<title>([^<]+)</title>', webpage, 'episode title', fatal=False)
+
+ if '<div class="non-sponsor">' in webpage:
+ self.raise_login_required('%s is only available for FIRST members' % title)
+
+ if '<div class="golive-gate">' in webpage:
+ self.raise_login_required('%s is not available yet' % title)
+
+ formats = self._extract_m3u8_formats(self._html_search_regex(r"file: '(.+?)m3u8'", webpage, 'm3u8 url') + 'm3u8', episode_id, ext='mp4')
+ self._sort_formats(formats)
+
+ return {
+ 'id': episode_id,
+ 'title': title,
+ 'formats': formats,
+ 'thumbnail': thumbnail,
+ 'description': description,
+ 'creator': creator,
+ 'series': series,
+ 'episode': episode,
+ 'episode_id': episode_id,
+ }