From 92ddaa415e20134eaa20421e16bb692dc5e1f18d Mon Sep 17 00:00:00 2001 From: Poschi <825911+poschi3@users.noreply.github.com> Date: Tue, 7 Sep 2021 19:11:56 +0200 Subject: [PATCH] [gotostage] Add extractor (#883) Authored by: poschi3 --- yt_dlp/extractor/extractors.py | 1 + yt_dlp/extractor/gotostage.py | 73 ++++++++++++++++++++++++++++++++++ 2 files changed, 74 insertions(+) create mode 100644 yt_dlp/extractor/gotostage.py diff --git a/yt_dlp/extractor/extractors.py b/yt_dlp/extractor/extractors.py index c745fd079..736868a09 100644 --- a/yt_dlp/extractor/extractors.py +++ b/yt_dlp/extractor/extractors.py @@ -511,6 +511,7 @@ from .googlepodcasts import ( ) from .googlesearch import GoogleSearchIE from .goshgay import GoshgayIE +from .gotostage import GoToStageIE from .gputechconf import GPUTechConfIE from .groupon import GrouponIE from .hbo import HBOIE diff --git a/yt_dlp/extractor/gotostage.py b/yt_dlp/extractor/gotostage.py new file mode 100644 index 000000000..6aa96106a --- /dev/null +++ b/yt_dlp/extractor/gotostage.py @@ -0,0 +1,73 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..compat import compat_str +from ..utils import ( + try_get, + url_or_none +) + +import json + + +class GoToStageIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?gotostage\.com/channel/[a-z0-9]+/recording/(?P[a-z0-9]+)/watch' + _TESTS = [{ + 'url': 'https://www.gotostage.com/channel/8901680603948959494/recording/60bb55548d434f21b9ce4f0e225c4895/watch', + 'md5': 'ca72ce990cdcd7a2bd152f7217e319a2', + 'info_dict': { + 'id': '60bb55548d434f21b9ce4f0e225c4895', + 'ext': 'mp4', + 'title': 'What is GoToStage?', + 'thumbnail': r're:^https?://.*\.jpg$', + 'duration': 93.924711 + } + }, { + 'url': 'https://www.gotostage.com/channel/bacc3d3535b34bafacc3f4ef8d4df78a/recording/831e74cd3e0042be96defba627b6f676/watch?source=HOMEPAGE', + 'only_matching': True, + }] + + def _real_extract(self, url): + video_id = self._match_id(url) + metadata = self._download_json( + 'https://api.gotostage.com/contents?ids=%s' % video_id, + video_id, + note='Downloading video metadata', + errnote='Unable to download video metadata')[0] + + registration_data = { + 'product': metadata['product'], + 'resourceType': metadata['contentType'], + 'productReferenceKey': metadata['productRefKey'], + 'firstName': 'foo', + 'lastName': 'bar', + 'email': 'foobar@example.com' + } + + registration_response = self._download_json( + 'https://api-registrations.logmeininc.com/registrations', + video_id, + data=json.dumps(registration_data).encode(), + expected_status=409, + headers={'Content-Type': 'application/json'}, + note='Register user', + errnote='Unable to register user') + + content_response = self._download_json( + 'https://api.gotostage.com/contents/%s/asset' % video_id, + video_id, + headers={'x-registrantkey': registration_response['registrationKey']}, + note='Get download url', + errnote='Unable to get download url') + + return { + 'id': video_id, + 'title': try_get(metadata, lambda x: x['title'], compat_str), + 'url': try_get(content_response, lambda x: x['cdnLocation'], compat_str), + 'ext': 'mp4', + 'thumbnail': url_or_none(try_get(metadata, lambda x: x['thumbnail']['location'])), + 'duration': try_get(metadata, lambda x: x['duration'], float), + 'categories': [try_get(metadata, lambda x: x['category'], compat_str)], + 'is_live': False + }