From 72ab7687194f353079b4f6e6ac9a59f586c9a9ef Mon Sep 17 00:00:00 2001 From: Ashish Gupta <39122144+Ashish0804@users.noreply.github.com> Date: Mon, 18 Oct 2021 08:09:50 +0530 Subject: [PATCH] [SkyNewsAU] Add extractor (#1308) Closes #1287 Authored by: Ashish0804 --- yt_dlp/extractor/extractors.py | 1 + yt_dlp/extractor/skynewsau.py | 46 ++++++++++++++++++++++++++++++++++ 2 files changed, 47 insertions(+) create mode 100644 yt_dlp/extractor/skynewsau.py diff --git a/yt_dlp/extractor/extractors.py b/yt_dlp/extractor/extractors.py index 03d4a67f54..ffd26ca0bb 100644 --- a/yt_dlp/extractor/extractors.py +++ b/yt_dlp/extractor/extractors.py @@ -1284,6 +1284,7 @@ from .skynewsarabia import ( SkyNewsArabiaIE, SkyNewsArabiaArticleIE, ) +from .skynewsau import SkyNewsAUIE from .sky import ( SkyNewsIE, SkySportsIE, diff --git a/yt_dlp/extractor/skynewsau.py b/yt_dlp/extractor/skynewsau.py new file mode 100644 index 0000000000..b1d77951e7 --- /dev/null +++ b/yt_dlp/extractor/skynewsau.py @@ -0,0 +1,46 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..utils import ( + try_get, + unified_strdate, +) + + +class SkyNewsAUIE(InfoExtractor): + _VALID_URL = r'(?:https?://)(?:www\.)?skynews\.com\.au/[^/]+/[^/]+/[^/]+/video/(?P[a-z0-9]+)' + + _TESTS = [{ + 'url': 'https://www.skynews.com.au/world-news/united-states/incredible-vision-shows-lava-overflowing-from-spains-la-palma-volcano/video/0f4c6243d6903502c01251f228b91a71', + 'info_dict': { + 'id': '6277184925001', + 'ext': 'mp4', + 'title': 'md5:60594f1ea6d5ae93e292900f4d34e9ae', + 'description': 'md5:60594f1ea6d5ae93e292900f4d34e9ae', + 'thumbnail': r're:^https?://.*\.jpg', + 'duration': 76.394, + 'timestamp': 1634271300, + 'uploader_id': '5348771529001', + 'tags': ['fblink', 'msn', 'usa', 'world', 'yt'], + 'upload_date': '20211015', + }, + 'params': {'skip_download': True, 'format': 'bv'} + }] + + _API_KEY = '6krsj3w249nk779d8fukqx9f' + + def _real_extract(self, url): + id = self._match_id(url) + webpage = self._download_webpage(url, id) + embedcode = self._search_regex(r'embedcode\s?=\s?\"([^\"]+)\"', webpage, 'embedcode') + data_json = self._download_json( + f'https://content.api.news/v3/videos/brightcove/{embedcode}?api_key={self._API_KEY}', id)['content'] + return { + 'id': id, + '_type': 'url_transparent', + 'url': 'https://players.brightcove.net/%s/default_default/index.html?videoId=%s' % tuple(embedcode.split('-')), + 'ie_key': 'BrightcoveNew', + 'title': data_json.get('caption'), + 'upload_date': unified_strdate(try_get(data_json, lambda x: x['date']['created'])), + }