From bf4fa24414d2f4f4418b17ed379eb60df5726c4f Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Thu, 30 Jun 2016 18:14:59 +0100 Subject: [PATCH] [ctvnews] Add new extractor(closes #2156) --- youtube_dl/extractor/ctvnews.py | 64 ++++++++++++++++++++++++++++++ youtube_dl/extractor/extractors.py | 1 + 2 files changed, 65 insertions(+) create mode 100644 youtube_dl/extractor/ctvnews.py diff --git a/youtube_dl/extractor/ctvnews.py b/youtube_dl/extractor/ctvnews.py new file mode 100644 index 000000000..e14b30085 --- /dev/null +++ b/youtube_dl/extractor/ctvnews.py @@ -0,0 +1,64 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor + + +class CTVNewsIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?ctvnews\.ca/(?:video\?(?:clip|playlist|bin)Id=|.*?)(?P[0-9.]+)' + _TESTS = [{ + 'url': 'http://www.ctvnews.ca/video?clipId=901995', + 'md5': '10deb320dc0ccb8d01d34d12fc2ea672', + 'info_dict': { + 'id': '901995', + 'ext': 'mp4', + 'title': 'Extended: \'That person cannot be me\' Johnson says', + 'description': 'md5:958dd3b4f5bbbf0ed4d045c790d89285', + 'timestamp': 1467286284, + 'upload_date': '20160630', + } + }, { + 'url': 'http://www.ctvnews.ca/video?playlistId=1.2966224', + 'info_dict': + { + 'id': '1.2966224', + }, + 'playlist_mincount': 19, + }, { + 'url': 'http://www.ctvnews.ca/video?binId=1.810401', + 'info_dict': + { + 'id': '1.810401', + }, + 'playlist_mincount': 91, + }, { + 'url': 'http://www.ctvnews.ca/1.810401', + 'only_matching': True, + }, { + 'url': 'http://www.ctvnews.ca/canadiens-send-p-k-subban-to-nashville-in-blockbuster-trade-1.2967231', + 'only_matching': True, + }] + + def _real_extract(self, url): + page_id = self._match_id(url) + + def ninecninemedia_url_result(clip_id): + return { + '_type': 'url_transparent', + 'id': clip_id, + 'url': '9c9media:ctvnews_web:%s' % clip_id, + 'ie_key': 'NineCNineMedia', + } + + if page_id.isdigit(): + return ninecninemedia_url_result(page_id) + else: + webpage = self._download_webpage('http://www.ctvnews.ca/%s' % page_id, page_id, query={ + 'ot': 'example.AjaxPageLayout.ot', + 'maxItemsPerPage': 20, + }) + entries = [ninecninemedia_url_result(clip_id) for clip_id in set( + re.findall(r'clip\.id\s*=\s*(\d+);', webpage))] + return self.playlist_result(entries, page_id) diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 1b2854cb9..4765fbc77 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -171,6 +171,7 @@ from .crunchyroll import ( ) from .cspan import CSpanIE from .ctsnews import CtsNewsIE +from .ctvnews import CTVNewsIE from .cultureunplugged import CultureUnpluggedIE from .cwtv import CWTVIE from .dailymail import DailyMailIE