[tagesschau] Relax _VALID_URL and simplify

This commit is contained in:
Sergey M․ 2015-07-23 00:30:48 +06:00
parent c356620ec1
commit 948199deac
1 changed files with 17 additions and 45 deletions

View File

@ -8,7 +8,7 @@ from ..utils import parse_filesize, ExtractorError
class TagesschauIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?tagesschau\.de/multimedia/(?:sendung/(ts|tsg|tt|nm|bab/bab)|video/video|tsvorzwanzig)(?P<id>-?[0-9]+)(?:~[-_a-zA-Z0-9]*)?\.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',
@ -29,57 +29,31 @@ class TagesschauIE(InfoExtractor):
'description': 'md5:695c01bfd98b7e313c501386327aea59',
'title': 'Sendung: tagesschau \t04.12.2014 20:00 Uhr',
'thumbnail': 're:^http:.*\.jpg$',
}
},
}, {
'url': 'http://www.tagesschau.de/multimedia/sendung/tsg-3771.html',
'md5': '90757268b49ef56deae90c7b48928d58',
'info_dict': {
'id': '3771',
'ext': 'mp4',
'description': None,
'title': 'Sendung: tagesschau (mit Gebärdensprache) \t14.07.2015 20:00 Uhr',
'thumbnail': 're:^http:.*\.jpg$',
}
'only_matching': True,
}, {
'url': 'http://www.tagesschau.de/multimedia/sendung/tt-3827.html',
'md5': '6e3ebdc75e8d67da966a8d06721eda71',
'info_dict': {
'id': '3827',
'ext': 'mp4',
'description': 'md5:d511d0e278b0ad341a95ad9ab992ce66',
'title': 'Sendung: tagesthemen \t14.07.2015 22:15 Uhr',
'thumbnail': 're:^http:.*\.jpg$',
}
'only_matching': True,
}, {
'url': 'http://www.tagesschau.de/multimedia/sendung/nm-3475.html',
'md5': '8a8875a568f0a5ae5ceef93c501a225f',
'info_dict': {
'id': '3475',
'ext': 'mp4',
'description': 'md5:ed149f5649cda3dac86813a9d777e131',
'title': 'Sendung: nachtmagazin \t15.07.2015 00:15 Uhr',
'thumbnail': 're:^http:.*\.jpg$',
}
'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',
'md5': 'be4d6f0421f2acd8abe25ea29f6f015b',
'info_dict': {
'id': '959',
'ext': 'mp4',
'description': None,
'title': 'Sendung: tagesschau vor 20 Jahren \t14.07.2015 22:45 Uhr',
'thumbnail': 're:^http:.*\.jpg$',
}
'only_matching': True,
}, {
'url': 'http://www.tagesschau.de/multimedia/sendung/bab/bab-3299~_bab-sendung-209.html',
'md5': '42e3757018d9908581481a80cc1806da',
'info_dict': {
'id': '3299',
'ext': 'mp4',
'description': None,
'title': 'Nach dem Referendum: Schaltgespräch nach Athen',
'thumbnail': 're:^http:.*\.jpg$',
}
'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 = {
@ -152,11 +126,9 @@ class TagesschauIE(InfoExtractor):
thumbnail_fn = self._search_regex(
r'(?s)<img alt="Sendungsbild".*?src="([^"]+)"',
webpage, 'thumbnail', fatal=False)
# there are some videos without description
description = ""
description = self._html_search_regex(
r'(?s)<p class="teasertext">(.*?)</p>',
webpage, 'description', fatal=False, default=None)
webpage, 'description', default=None)
title = self._html_search_regex(
r'<span class="headline".*?>(.*?)</span>', webpage, 'title')