From 27c0f899c8f4a71e2ec8ac7ee4ab0217da7934bd Mon Sep 17 00:00:00 2001 From: bashonly <88596187+bashonly@users.noreply.github.com> Date: Tue, 22 Nov 2022 00:40:02 +0000 Subject: [PATCH] [extractor/screencastify] Add extractor (#5604) Closes #5603 Authored by: bashonly --- yt_dlp/extractor/_extractors.py | 1 + yt_dlp/extractor/screencastify.py | 52 +++++++++++++++++++++++++++++++ 2 files changed, 53 insertions(+) create mode 100644 yt_dlp/extractor/screencastify.py diff --git a/yt_dlp/extractor/_extractors.py b/yt_dlp/extractor/_extractors.py index a3c5472f0..375ac0d06 100644 --- a/yt_dlp/extractor/_extractors.py +++ b/yt_dlp/extractor/_extractors.py @@ -1603,6 +1603,7 @@ from .sbs import SBSIE from .screen9 import Screen9IE from .screencast import ScreencastIE +from .screencastify import ScreencastifyIE from .screencastomatic import ScreencastOMaticIE from .scrippsnetworks import ( ScrippsNetworksWatchIE, diff --git a/yt_dlp/extractor/screencastify.py b/yt_dlp/extractor/screencastify.py new file mode 100644 index 000000000..136b8479b --- /dev/null +++ b/yt_dlp/extractor/screencastify.py @@ -0,0 +1,52 @@ +import urllib.parse + +from .common import InfoExtractor +from ..utils import traverse_obj, update_url_query + + +class ScreencastifyIE(InfoExtractor): + _VALID_URL = r'https?://watch\.screencastify\.com/v/(?P[^/?#]+)' + _TESTS = [{ + 'url': 'https://watch.screencastify.com/v/sYVkZip3quLKhHw4Ybk8', + 'info_dict': { + 'id': 'sYVkZip3quLKhHw4Ybk8', + 'ext': 'mp4', + 'title': 'Inserting and Aligning the Case Top and Bottom', + 'description': '', + 'uploader': 'Paul Gunn', + 'extra_param_to_segment_url': str, + }, + 'params': { + 'skip_download': 'm3u8', + }, + }] + + def _real_extract(self, url): + video_id = self._match_id(url) + info = self._download_json( + f'https://umbrella.svc.screencastify.com/api/umbrellaService/watch/{video_id}', video_id) + + query_string = traverse_obj(info, ('manifest', 'auth', 'query')) + query = urllib.parse.parse_qs(query_string) + formats = [] + dash_manifest_url = traverse_obj(info, ('manifest', 'url')) + if dash_manifest_url: + formats.extend( + self._extract_mpd_formats( + dash_manifest_url, video_id, mpd_id='dash', query=query, fatal=False)) + hls_manifest_url = traverse_obj(info, ('manifest', 'hlsUrl')) + if hls_manifest_url: + formats.extend( + self._extract_m3u8_formats( + hls_manifest_url, video_id, ext='mp4', m3u8_id='hls', query=query, fatal=False)) + for f in formats: + f['url'] = update_url_query(f['url'], query) + + return { + 'id': video_id, + 'title': info.get('title'), + 'description': info.get('description'), + 'uploader': info.get('userName'), + 'formats': formats, + 'extra_param_to_segment_url': query_string, + }