From 3a30508b943c044e5f684b703ff58ac352686f63 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sun, 9 Aug 2015 19:11:23 +0600 Subject: [PATCH] [telegraaf] Add extractor (Closes #6492) --- youtube_dl/extractor/__init__.py | 1 + youtube_dl/extractor/telegraaf.py | 35 +++++++++++++++++++++++++++++++ 2 files changed, 36 insertions(+) create mode 100644 youtube_dl/extractor/telegraaf.py diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index e38e77a27..dad3ec87f 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -596,6 +596,7 @@ from .techtalks import TechTalksIE from .ted import TEDIE from .telebruxelles import TeleBruxellesIE from .telecinco import TelecincoIE +from .telegraaf import TelegraafIE from .telemb import TeleMBIE from .teletask import TeleTaskIE from .tenplay import TenPlayIE diff --git a/youtube_dl/extractor/telegraaf.py b/youtube_dl/extractor/telegraaf.py new file mode 100644 index 000000000..6f8333cfc --- /dev/null +++ b/youtube_dl/extractor/telegraaf.py @@ -0,0 +1,35 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..utils import remove_end + + +class TelegraafIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?telegraaf\.nl/tv/(?:[^/]+/)+(?P\d+)/[^/]+\.html' + _TEST = { + 'url': 'http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html', + 'md5': '83245a9779bcc4a24454bfd53c65b6dc', + 'info_dict': { + 'id': '24353229', + 'ext': 'mp4', + 'title': 'Tikibad ontruimd wegens brand', + 'description': 'md5:05ca046ff47b931f9b04855015e163a4', + 'thumbnail': 're:^https?://.*\.jpg$', + 'duration': 33, + }, + } + + def _real_extract(self, url): + playlist_id = self._match_id(url) + + webpage = self._download_webpage(url, playlist_id) + + playlist_url = self._search_regex( + r"iframe\.loadPlayer\('([^']+)'", webpage, 'player') + + entries = self._extract_xspf_playlist(playlist_url, playlist_id) + title = remove_end(self._og_search_title(webpage), ' - VIDEO') + description = self._og_search_description(webpage) + + return self.playlist_result(entries, playlist_id, title, description)