github/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-12-29 15:50:46 +00:00
Code Issues Projects Releases Packages Wiki Activity

Merge branch 'rohieb-patch/enhance-tagesschau-regex'

Browse source
This commit is contained in:
Sergey M․ 2015-07-23 00:31:09 +06:00
commit a083b859e4
1 changed files with 28 additions and 4 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

32
youtube_dl/extractor/tagesschau.py
View file

@ -4,11 +4,11 @@
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 @@ def _real_extract(self, url):
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')