From 71a1db89198100a0e9bc5099aeed622264690203 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sun, 9 Jul 2017 20:06:24 +0700 Subject: [PATCH] [dailymail] Add support for embeds --- youtube_dl/extractor/dailymail.py | 17 ++++++++++++++--- youtube_dl/extractor/generic.py | 21 +++++++++++++++++++++ 2 files changed, 35 insertions(+), 3 deletions(-) diff --git a/youtube_dl/extractor/dailymail.py b/youtube_dl/extractor/dailymail.py index 538565c66..af3978035 100644 --- a/youtube_dl/extractor/dailymail.py +++ b/youtube_dl/extractor/dailymail.py @@ -1,6 +1,8 @@ # coding: utf-8 from __future__ import unicode_literals +import re + from .common import InfoExtractor from ..compat import compat_str from ..utils import ( @@ -12,8 +14,8 @@ from ..utils import ( class DailyMailIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?dailymail\.co\.uk/video/[^/]+/video-(?P[0-9]+)' - _TEST = { + _VALID_URL = r'https?://(?:www\.)?dailymail\.co\.uk/(?:video/[^/]+/video-|embed/video/)(?P[0-9]+)' + _TESTS = [{ 'url': 'http://www.dailymail.co.uk/video/tvshowbiz/video-1295863/The-Mountain-appears-sparkling-water-ad-Heavy-Bubbles.html', 'md5': 'f6129624562251f628296c3a9ffde124', 'info_dict': { @@ -22,7 +24,16 @@ class DailyMailIE(InfoExtractor): 'title': 'The Mountain appears in sparkling water ad for \'Heavy Bubbles\'', 'description': 'md5:a93d74b6da172dd5dc4d973e0b766a84', } - } + }, { + 'url': 'http://www.dailymail.co.uk/embed/video/1295863.html', + 'only_matching': True, + }] + + @staticmethod + def _extract_urls(webpage): + return re.findall( + r']+\bsrc=["\'](?P(?:https?:)?//(?:www\.)?dailymail\.co\.uk/embed/video/\d+\.html)', + webpage) def _real_extract(self, url): video_id = self._match_id(url) diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py index f2c577f98..5e8890d41 100644 --- a/youtube_dl/extractor/generic.py +++ b/youtube_dl/extractor/generic.py @@ -57,6 +57,7 @@ from .dailymotion import ( DailymotionIE, DailymotionCloudIE, ) +from .dailymail import DailyMailIE from .onionstudios import OnionStudiosIE from .viewlift import ViewLiftEmbedIE from .mtv import MTVServicesEmbeddedIE @@ -760,6 +761,20 @@ class GenericIE(InfoExtractor): }, 'add_ie': ['Dailymotion'], }, + # DailyMail embed + { + 'url': 'http://www.bumm.sk/krimi/2017/07/05/biztonsagi-kamera-buktatta-le-az-agg-ferfit-utlegelo-apolot', + 'info_dict': { + 'id': '1495629', + 'ext': 'mp4', + 'title': 'Care worker punches elderly dementia patient in head 11 times', + 'description': 'md5:3a743dee84e57e48ec68bf67113199a5', + }, + 'add_ie': ['DailyMail'], + 'params': { + 'skip_download': True, + }, + }, # YouTube embed { 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html', @@ -2190,6 +2205,12 @@ class GenericIE(InfoExtractor): return self.playlist_from_matches( playlists, video_id, video_title, lambda p: '//dailymotion.com/playlist/%s' % p) + # Look for DailyMail embeds + dailymail_urls = DailyMailIE._extract_urls(webpage) + if dailymail_urls: + return self.playlist_from_matches( + dailymail_urls, video_id, video_title, ie=DailyMailIE.ie_key()) + # Look for embedded Wistia player wistia_url = WistiaIE._extract_url(webpage) if wistia_url: