From 7f7801e77687da91d3376c4642d7f98b43a6909c Mon Sep 17 00:00:00 2001 From: carsten demming Date: Tue, 20 Feb 2018 12:00:25 +0100 Subject: [PATCH] - added vol.at extractor template --- youtube_dl/extractor/extractors.py | 3 ++- youtube_dl/extractor/volat.py | 40 ++++++++++++++++++++++++++++++ 2 files changed, 42 insertions(+), 1 deletion(-) create mode 100644 youtube_dl/extractor/volat.py diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index b2a4893fe..6f42d66da 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -1269,6 +1269,7 @@ from .vodlocker import VodlockerIE from .vodpl import VODPlIE from .vodplatform import VODPlatformIE from .voicerepublic import VoiceRepublicIE +from .volat import VolAtIE from .voot import VootIE from .voxmedia import ( VoxMediaVolumeIE, @@ -1311,7 +1312,7 @@ from .webofstories import ( WebOfStoriesPlaylistIE, ) from .weibo import ( - WeiboIE, + WeiboIE, WeiboMobileIE ) from .weiqitv import WeiqiTVIE diff --git a/youtube_dl/extractor/volat.py b/youtube_dl/extractor/volat.py new file mode 100644 index 000000000..8afe6616c --- /dev/null +++ b/youtube_dl/extractor/volat.py @@ -0,0 +1,40 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor + + +class VolAtIE(InfoExtractor): + print("wtf") + _VALID_URL = r'https?://(?:www\.)?vol\.at/(?P[0-9]+)' + _TEST = { + 'url': 'http://www.vol.at/blue-man-group/5593454', + 'md5': 'TODO: md5 sum of the first 10241 bytes of the video file (use --test)', + 'info_dict': { + 'id': '5593454', + 'ext': 'mp4', + 'title': '"Blau ist mysteriƶs": Die Blue Man Group im Interview', + 'thumbnail': r're:^https?://.*\.jpg$', + # TODO more properties, either as: + # * A value + # * MD5 checksum; start the string with md5: + # * A regular expression; start the string with re: + # * Any Python type (for example int or float) + } + } + + def _real_extract(self, url): + print("hello test") + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) + + # TODO more code goes here, for example ... + title = self._html_search_regex(r'

(.+?)

', webpage, 'title') + + return { + 'id': video_id, + 'title': title, + 'description': self._og_search_description(webpage), + 'uploader': self._search_regex(r']+id="uploader"[^>]*>([^<]+)<', webpage, 'uploader', fatal=False), + # TODO more properties (see youtube_dl/extractor/common.py) + }