diff options
| author | Sergey M․ <dstftw@gmail.com> | 2015-07-23 00:31:09 +0600 |
|---|---|---|
| committer | Sergey M․ <dstftw@gmail.com> | 2015-07-23 00:31:09 +0600 |
| commit | a083b859e48525a87b29b93b7eb45b01f3cd3737 (patch) | |
| tree | 5f5303168e7991a78470789560611610cdae4c6d | |
| parent | f79ebf09a24f9bf0e91d0dc26782eeea02f10ad1 (diff) | |
| parent | 948199deac4d9ec6ba6bc4359ad43db7951a1c53 (diff) | |
Merge branch 'rohieb-patch/enhance-tagesschau-regex'
| -rw-r--r-- | youtube_dl/extractor/tagesschau.py | 32 |
1 files changed, 28 insertions, 4 deletions
diff --git a/youtube_dl/extractor/tagesschau.py b/youtube_dl/extractor/tagesschau.py index cf1b37a75..b84892364 100644 --- a/youtube_dl/extractor/tagesschau.py +++ b/youtube_dl/extractor/tagesschau.py @@ -4,11 +4,11 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..utils import parse_filesize +from ..utils import parse_filesize, ExtractorError class TagesschauIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?tagesschau\.de/multimedia/(?:sendung/ts|video/video)(?P<id>-?[0-9]+)\.html' + _VALID_URL = r'https?://(?:www\.)?tagesschau\.de/multimedia/(?:[^/]+/)*?[^/#?]+?(?P<id>-?[0-9]+)(?:~_[^/#?]+?)?\.html' _TESTS = [{ 'url': 'http://www.tagesschau.de/multimedia/video/video-102143.html', @@ -29,7 +29,31 @@ class TagesschauIE(InfoExtractor): 'description': 'md5:695c01bfd98b7e313c501386327aea59', 'title': 'Sendung: tagesschau \t04.12.2014 20:00 Uhr', 'thumbnail': 're:^http:.*\.jpg$', - } + }, + }, { + 'url': 'http://www.tagesschau.de/multimedia/sendung/tsg-3771.html', + 'only_matching': True, + }, { + 'url': 'http://www.tagesschau.de/multimedia/sendung/tt-3827.html', + 'only_matching': True, + }, { + 'url': 'http://www.tagesschau.de/multimedia/sendung/nm-3475.html', + 'only_matching': True, + }, { + 'url': 'http://www.tagesschau.de/multimedia/sendung/weltspiegel-3167.html', + 'only_matching': True, + }, { + 'url': 'http://www.tagesschau.de/multimedia/tsvorzwanzig-959.html', + 'only_matching': True, + }, { + 'url': 'http://www.tagesschau.de/multimedia/sendung/bab/bab-3299~_bab-sendung-209.html', + 'only_matching': True, + }, { + 'url': 'http://www.tagesschau.de/multimedia/video/video-102303~_bab-sendung-211.html', + 'only_matching': True, + }, { + 'url': 'http://www.tagesschau.de/multimedia/politikimradio/audio-18407.html', + 'only_matching': True, }] _FORMATS = { @@ -104,7 +128,7 @@ class TagesschauIE(InfoExtractor): webpage, 'thumbnail', fatal=False) description = self._html_search_regex( r'(?s)<p class="teasertext">(.*?)</p>', - webpage, 'description', fatal=False) + webpage, 'description', default=None) title = self._html_search_regex( r'<span class="headline".*?>(.*?)</span>', webpage, 'title') |