From bc35ed3fb6fcae88d59fd440b505b9e1a7cf112e Mon Sep 17 00:00:00 2001 From: Yen Chi Hsuan Date: Mon, 23 Jan 2017 23:33:30 +0800 Subject: [PATCH] =?utf8?q?[nextmedia]=20Add=20support=20for=20NextTV=20(?= =?utf8?q?=E5=A3=B9=E9=9B=BB=E8=A6=96)?= MIME-Version: 1.0 Content-Type: text/plain; charset=utf8 Content-Transfer-Encoding: 8bit --- ChangeLog | 6 ++++ youtube_dl/extractor/extractors.py | 1 + youtube_dl/extractor/nextmedia.py | 54 +++++++++++++++++++++++++++++- 3 files changed, 60 insertions(+), 1 deletion(-) diff --git a/ChangeLog b/ChangeLog index beea17e54..ba2f5cffc 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,3 +1,9 @@ +version + +Extractors ++ [nextmedia] Add support for NextTV (壹電視) + + version 2017.01.22 Extractors diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index cfddf5b92..e23b5d0f6 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -598,6 +598,7 @@ from .nextmedia import ( NextMediaIE, NextMediaActionNewsIE, AppleDailyIE, + NextTVIE, ) from .nfb import NFBIE from .nfl import NFLIE diff --git a/youtube_dl/extractor/nextmedia.py b/youtube_dl/extractor/nextmedia.py index 626ed8b49..680f03aad 100644 --- a/youtube_dl/extractor/nextmedia.py +++ b/youtube_dl/extractor/nextmedia.py @@ -3,7 +3,14 @@ from __future__ import unicode_literals from .common import InfoExtractor from ..compat import compat_urlparse -from ..utils import parse_iso8601 +from ..utils import ( + clean_html, + get_element_by_class, + int_or_none, + parse_iso8601, + remove_start, + unified_timestamp, +) class NextMediaIE(InfoExtractor): @@ -184,3 +191,48 @@ class AppleDailyIE(NextMediaIE): def _fetch_description(self, page): return self._html_search_meta('description', page, 'news description') + + +class NextTVIE(InfoExtractor): + IE_DESC = '壹電視' + _VALID_URL = r'https?://(?:www\.)?nexttv\.com\.tw/(?:[^/]+/)+(?P\d+)' + + _TEST = { + 'url': 'http://www.nexttv.com.tw/news/realtime/politics/11779671', + 'info_dict': { + 'id': '11779671', + 'ext': 'mp4', + 'title': '「超收稅」近4千億! 藍議員籲發消費券', + 'thumbnail': r're:^https?://.*\.jpg$', + 'timestamp': 1484825400, + 'upload_date': '20170119', + 'view_count': int, + }, + } + + def _real_extract(self, url): + video_id = self._match_id(url) + + webpage = self._download_webpage(url, video_id) + + title = self._html_search_regex( + r']*>([^<]+)', webpage, 'title') + + data = self._hidden_inputs(webpage) + + video_url = data['ntt-vod-src-detailview'] + + date_str = get_element_by_class('date', webpage) + timestamp = unified_timestamp(date_str + '+0800') if date_str else None + + view_count = int_or_none(remove_start( + clean_html(get_element_by_class('click', webpage)), '點閱:')) + + return { + 'id': video_id, + 'title': title, + 'url': video_url, + 'thumbnail': data.get('ntt-vod-img-src'), + 'timestamp': timestamp, + 'view_count': view_count, + } -- 2.39.5