From 8b7340a45eb0e3aeaa996896ff8690b6c3a32af6 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Thu, 22 Mar 2018 22:55:28 +0700 Subject: [PATCH] [lenta] Add extractor (closes #15953) --- youtube_dl/extractor/extractors.py | 5 +-- youtube_dl/extractor/generic.py | 18 ---------- youtube_dl/extractor/lenta.py | 53 ++++++++++++++++++++++++++++++ 3 files changed, 56 insertions(+), 20 deletions(-) create mode 100644 youtube_dl/extractor/lenta.py diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 3bde40eb3..de48a37ad 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -532,13 +532,14 @@ from .lcp import ( ) from .learnr import LearnrIE from .lecture2go import Lecture2GoIE -from .lego import LEGOIE -from .lemonde import LemondeIE from .leeco import ( LeIE, LePlaylistIE, LetvCloudIE, ) +from .lego import LEGOIE +from .lemonde import LemondeIE +from .lenta import LentaIE from .libraryofcongress import LibraryOfCongressIE from .libsyn import LibsynIE from .lifenews import ( diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py index 1cc491b19..cf64398e3 100644 --- a/youtube_dl/extractor/generic.py +++ b/youtube_dl/extractor/generic.py @@ -1270,24 +1270,6 @@ class GenericIE(InfoExtractor): }, 'add_ie': ['Kaltura'], }, - # EaglePlatform embed (generic URL) - { - 'url': 'http://lenta.ru/news/2015/03/06/navalny/', - # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used - 'info_dict': { - 'id': '227304', - 'ext': 'mp4', - 'title': 'Навальный вышел на свободу', - 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5', - 'thumbnail': r're:^https?://.*\.jpg$', - 'duration': 87, - 'view_count': int, - 'age_limit': 0, - }, - 'params': { - 'skip_download': True, - }, - }, # referrer protected EaglePlatform embed { 'url': 'https://tvrain.ru/lite/teleshow/kak_vse_nachinalos/namin-418921/', diff --git a/youtube_dl/extractor/lenta.py b/youtube_dl/extractor/lenta.py new file mode 100644 index 000000000..2ebd4e577 --- /dev/null +++ b/youtube_dl/extractor/lenta.py @@ -0,0 +1,53 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor + + +class LentaIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?lenta\.ru/[^/]+/\d+/\d+/\d+/(?P[^/?#&]+)' + _TESTS = [{ + 'url': 'https://lenta.ru/news/2018/03/22/savshenko_go/', + 'info_dict': { + 'id': '964400', + 'ext': 'mp4', + 'title': 'Надежду Савченко задержали', + 'thumbnail': r're:^https?://.*\.jpg$', + 'duration': 61, + 'view_count': int, + }, + 'params': { + 'skip_download': True, + }, + }, { + # EaglePlatform iframe embed + 'url': 'http://lenta.ru/news/2015/03/06/navalny/', + 'info_dict': { + 'id': '227304', + 'ext': 'mp4', + 'title': 'Навальный вышел на свободу', + 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5', + 'thumbnail': r're:^https?://.*\.jpg$', + 'duration': 87, + 'view_count': int, + 'age_limit': 0, + }, + 'params': { + 'skip_download': True, + }, + }] + + def _real_extract(self, url): + display_id = self._match_id(url) + + webpage = self._download_webpage(url, display_id) + + video_id = self._search_regex( + r'vid\s*:\s*["\']?(\d+)', webpage, 'eagleplatform id', + default=None) + if video_id: + return self.url_result( + 'eagleplatform:lentaru.media.eagleplatform.com:%s' % video_id, + ie='EaglePlatform', video_id=video_id) + + return self.url_result(url, ie='Generic')