From 57c68ec4c303f471b2519db21b9b56c080d88338 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Tue, 14 Aug 2018 22:51:44 +0700 Subject: [PATCH] [generic] Add support for expressen embeds --- youtube_dl/extractor/expressen.py | 23 ++++++++++++++++++++++- youtube_dl/extractor/generic.py | 6 ++++++ 2 files changed, 28 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/expressen.py b/youtube_dl/extractor/expressen.py index f61178012..934571472 100644 --- a/youtube_dl/extractor/expressen.py +++ b/youtube_dl/extractor/expressen.py @@ -1,6 +1,8 @@ # coding: utf-8 from __future__ import unicode_literals +import re + from .common import InfoExtractor from ..utils import ( determine_ext, @@ -11,7 +13,13 @@ from ..utils import ( class ExpressenIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?expressen\.se/tv/(?:[^/]+/)*(?P[^/?#&]+)' + _VALID_URL = r'''(?x) + https?:// + (?:www\.)?expressen\.se/ + (?:(?:tvspelare/video|videoplayer/embed)/)? + tv/(?:[^/]+/)* + (?P[^/?#&]+) + ''' _TESTS = [{ 'url': 'https://www.expressen.se/tv/ledare/ledarsnack/ledarsnack-om-arbetslosheten-bland-kvinnor-i-speciellt-utsatta-omraden/', 'md5': '2fbbe3ca14392a6b1b36941858d33a45', @@ -28,8 +36,21 @@ class ExpressenIE(InfoExtractor): }, { 'url': 'https://www.expressen.se/tv/kultur/kulturdebatt-med-expressens-karin-olsson/', 'only_matching': True, + }, { + 'url': 'https://www.expressen.se/tvspelare/video/tv/ditv/ekonomistudion/experterna-har-ar-fragorna-som-avgor-valet/?embed=true&external=true&autoplay=true&startVolume=0&partnerId=di', + 'only_matching': True, + }, { + 'url': 'https://www.expressen.se/videoplayer/embed/tv/ditv/ekonomistudion/experterna-har-ar-fragorna-som-avgor-valet/?embed=true&external=true&autoplay=true&startVolume=0&partnerId=di', + 'only_matching': True, }] + @staticmethod + def _extract_urls(webpage): + return [ + mobj.group('url') for mobj in re.finditer( + r']+\bsrc=(["\'])(?P(?:https?:)?//(?:www\.)?expressen\.se/(?:tvspelare/video|videoplayer/embed)/tv/.+?)\1', + webpage)] + def _real_extract(self, url): display_id = self._match_id(url) diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py index 43218c3a4..83a31f3d3 100644 --- a/youtube_dl/extractor/generic.py +++ b/youtube_dl/extractor/generic.py @@ -114,6 +114,7 @@ from .indavideo import IndavideoEmbedIE from .apa import APAIE from .foxnews import FoxNewsIE from .viqeo import ViqeoIE +from .expressen import ExpressenIE class GenericIE(InfoExtractor): @@ -3109,6 +3110,11 @@ class GenericIE(InfoExtractor): return self.playlist_from_matches( viqeo_urls, video_id, video_title, ie=ViqeoIE.ie_key()) + expressen_urls = ExpressenIE._extract_urls(webpage) + if expressen_urls: + return self.playlist_from_matches( + expressen_urls, video_id, video_title, ie=ExpressenIE.ie_key()) + # Look for HTML5 media entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls') if entries: