From a63d9bd0b00c2c6b8d5f1a90fd783780ceda4023 Mon Sep 17 00:00:00 2001 From: Yuan Chao Date: Sun, 19 Sep 2021 08:18:22 -0400 Subject: [PATCH] [CGTN] Add extractor (#981) Authored by: chao813 --- yt_dlp/extractor/cgtn.py | 64 ++++++++++++++++++++++++++++++++++ yt_dlp/extractor/extractors.py | 1 + yt_dlp/utils.py | 1 + 3 files changed, 66 insertions(+) create mode 100644 yt_dlp/extractor/cgtn.py diff --git a/yt_dlp/extractor/cgtn.py b/yt_dlp/extractor/cgtn.py new file mode 100644 index 0000000000..89f173887e --- /dev/null +++ b/yt_dlp/extractor/cgtn.py @@ -0,0 +1,64 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..utils import ( + try_get, + unified_timestamp, +) + + +class CGTNIE(InfoExtractor): + _VALID_URL = r'https?://news\.cgtn\.com/news/[0-9]{4}-[0-9]{2}-[0-9]{2}/[a-zA-Z0-9-]+-(?P[a-zA-Z0-9-]+)/index\.html' + _TESTS = [ + { + 'url': 'https://news.cgtn.com/news/2021-03-09/Up-and-Out-of-Poverty-Ep-1-A-solemn-promise-YuOUaOzGQU/index.html', + 'info_dict': { + 'id': 'YuOUaOzGQU', + 'ext': 'mp4', + 'title': 'Up and Out of Poverty Ep. 1: A solemn promise', + 'thumbnail': r're:^https?://.*\.jpg$', + 'timestamp': 1615295940, + 'upload_date': '20210309', + }, + 'params': { + 'skip_download': True + } + }, { + 'url': 'https://news.cgtn.com/news/2021-06-06/China-Indonesia-vow-to-further-deepen-maritime-cooperation-10REvJCewCY/index.html', + 'info_dict': { + 'id': '10REvJCewCY', + 'ext': 'mp4', + 'title': 'China, Indonesia vow to further deepen maritime cooperation', + 'thumbnail': r're:^https?://.*\.png$', + 'description': 'China and Indonesia vowed to upgrade their cooperation into the maritime sector and also for political security, economy, and cultural and people-to-people exchanges.', + 'author': 'CGTN', + 'category': 'China', + 'timestamp': 1622950200, + 'upload_date': '20210606', + }, + 'params': { + 'skip_download': False + } + } + ] + + def _real_extract(self, url): + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) + + download_url = self._html_search_regex(r'data-video ="(?P.+m3u8)"', webpage, 'download_url') + datetime_str = self._html_search_regex(r'\s*(.+?)\s*', webpage, 'datetime_str', fatal=False) + + return { + 'id': video_id, + 'title': self._og_search_title(webpage), + 'description': self._og_search_description(webpage, default=None), + 'thumbnail': self._og_search_thumbnail(webpage), + 'formats': self._extract_m3u8_formats(download_url, video_id, 'mp4', 'm3u8_native', m3u8_id='hls'), + 'category': self._html_search_regex(r'\s*(.+?)\s*', + webpage, 'category', fatal=False), + 'author': self._html_search_regex(r'
\s*(.+?)\s*
', + webpage, 'author', default=None, fatal=False), + 'timestamp': try_get(unified_timestamp(datetime_str), lambda x: x - 8 * 3600), + } diff --git a/yt_dlp/extractor/extractors.py b/yt_dlp/extractor/extractors.py index 3dd56c65a2..ddae1d7cc9 100644 --- a/yt_dlp/extractor/extractors.py +++ b/yt_dlp/extractor/extractors.py @@ -239,6 +239,7 @@ CeskaTelevizeIE, CeskaTelevizePoradyIE, ) +from .cgtn import CGTNIE from .channel9 import Channel9IE from .charlierose import CharlieRoseIE from .chaturbate import ChaturbateIE diff --git a/yt_dlp/utils.py b/yt_dlp/utils.py index 4c0ac5a254..de0213b142 100644 --- a/yt_dlp/utils.py +++ b/yt_dlp/utils.py @@ -1762,6 +1762,7 @@ def random_user_agent(): '%b %d %Y at %H:%M:%S', '%B %d %Y at %H:%M', '%B %d %Y at %H:%M:%S', + '%H:%M %d-%b-%Y', ) DATE_FORMATS_DAY_FIRST = list(DATE_FORMATS)