From 15e5d19a9be129d53066b8af0b9d73c67354381a Mon Sep 17 00:00:00 2001 From: carsten demming Date: Tue, 20 Feb 2018 23:51:15 +0100 Subject: [PATCH] - WIP - successfully extracted title --- youtube_dl/extractor/volat.py | 13 +++---------- 1 file changed, 3 insertions(+), 10 deletions(-) diff --git a/youtube_dl/extractor/volat.py b/youtube_dl/extractor/volat.py index 8afe6616c..76193f105 100644 --- a/youtube_dl/extractor/volat.py +++ b/youtube_dl/extractor/volat.py @@ -5,8 +5,7 @@ from .common import InfoExtractor class VolAtIE(InfoExtractor): - print("wtf") - _VALID_URL = r'https?://(?:www\.)?vol\.at/(?P[0-9]+)' + _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)', @@ -14,7 +13,6 @@ class VolAtIE(InfoExtractor): 'id': '5593454', 'ext': 'mp4', 'title': '"Blau ist mysteriös": 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: @@ -24,17 +22,12 @@ class VolAtIE(InfoExtractor): } 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') - + title = self._og_search_title(webpage) return { 'id': video_id, - 'title': title, - 'description': self._og_search_description(webpage), - 'uploader': self._search_regex(r']+id="uploader"[^>]*>([^<]+)<', webpage, 'uploader', fatal=False), + 'title': title # TODO more properties (see youtube_dl/extractor/common.py) }