etc/yt-dlp
0
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-27 03:03:01 +00:00
Code Issues Projects Releases Wiki Activity

[tagesschau] add support for more video types

Browse source 
I found that currently only tagesschau videos are played. There are some
more shows hosted on tagesschau.de (see [0] for example) which are
easily playable by adjusting the regex. So this patch adds support for:
* tagesthemen
* tagesschau vor 20 Jahren
* tagesschau (mit Gebärdensprache)
* nachtmagazin

Note that some videos don't provide a description, so in order for the
tests to succeed, an ExtractorError needs to get caught.

[0]: http://www.tagesschau.de/multimedia/video/videoarchiv2~_date-20150714.html
This commit is contained in:
Roland Hieber 2015-07-19 03:34:22 +02:00
parent 4b0f45f667
commit e89d7e3029
1 changed files with 50 additions and 5 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

55
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/(?:sendung/(ts|tsg|tt|nm)|video/video|tsvorzwanzig)(?P<id>-?[0-9]+)\.html'
_TESTS = [{
'url': 'http://www.tagesschau.de/multimedia/video/video1399128.html',
@ -30,6 +30,46 @@ class TagesschauIE(InfoExtractor):
'title': 'Sendung: tagesschau \t04.12.2014 20:00 Uhr',
'thumbnail': 're:^http:.*\.jpg$',
}
}, {
'url': 'http://www.tagesschau.de/multimedia/sendung/tsg-3771.html',
'md5': '90757268b49ef56deae90c7b48928d58',
'info_dict': {
'id': '3771',
'ext': 'mp4',
'description': '',
'title': 'Sendung: tagesschau (mit Gebärdensprache) \t14.07.2015 20:00 Uhr',
'thumbnail': 're:^http:.*\.jpg$',
}
}, {
'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$',
}
}, {
'url': 'http://www.tagesschau.de/multimedia/sendung/nm-3475.html',
'md5': '8a8875a568f0a5ae5ceef93c501a225f',
'info_dict': {
'id': '3475',
'ext': 'mp4',
'description': 'md5:ed149f5649cda3dac86813a9d777e131',
'title': 'Sendung: nachtmagazin \t15.07.2015 00:15 Uhr',
'thumbnail': 're:^http:.*\.jpg$',
}
}, {
'url': 'http://www.tagesschau.de/multimedia/tsvorzwanzig-959.html',
'md5': 'be4d6f0421f2acd8abe25ea29f6f015b',
'info_dict': {
'id': '959',
'ext': 'mp4',
'description': '',
'title': 'Sendung: tagesschau vor 20 Jahren \t14.07.2015 22:45 Uhr',
'thumbnail': 're:^http:.*\.jpg$',
}
}]
_FORMATS = {
@ -102,9 +142,14 @@ def _real_extract(self, url):
thumbnail_fn = self._search_regex(
r'(?s)<img alt="Sendungsbild".*?src="([^"]+)"',
webpage, 'thumbnail', fatal=False)
description = self._html_search_regex(
r'(?s)<p class="teasertext">(.*?)</p>',
webpage, 'description', fatal=False)
# there are some videos without description
description = ""
try:
description = self._html_search_regex(
r'(?s)<p class="teasertext">(.*?)</p>',
webpage, 'description', fatal=False)
except ExtractorError:
pass
title = self._html_search_regex(
r'<span class="headline".*?>(.*?)</span>', webpage, 'title')