github/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-21 20:46:36 -05:00
Code Issues Projects Releases Packages Wiki Activity

[tagesschau] Add support for audio

Browse source
This commit is contained in:
Sergey M․ 2015-07-23 01:01:04 +06:00
parent a083b859e4
commit a47b602b08
1 changed files with 24 additions and 13 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

37
youtube_dl/extractor/tagesschau.py
View file

@ -30,6 +30,16 @@ class TagesschauIE(InfoExtractor):
'title': 'Sendung: tagesschau \t04.12.2014 20:00 Uhr', 'title': 'Sendung: tagesschau \t04.12.2014 20:00 Uhr',
'thumbnail': 're:^http:.*\.jpg$', 'thumbnail': 're:^http:.*\.jpg$',
}, },
}, {
'url': 'http://www.tagesschau.de/multimedia/politikimradio/audio-18407.html',
'md5': 'aef45de271c4bf0a5db834aa40bf774c',
'info_dict': {
'id': '18407',
'ext': 'mp3',
'title': 'Flüchtlingsdebatte: Hitzig, aber wenig hilfreich',
'description': 'Flüchtlingsdebatte: Hitzig, aber wenig hilfreich',
'thumbnail': 're:^https?:.*\.jpg$',
},
}, { }, {
'url': 'http://www.tagesschau.de/multimedia/sendung/tsg-3771.html', 'url': 'http://www.tagesschau.de/multimedia/sendung/tsg-3771.html',
'only_matching': True, 'only_matching': True,
@ -51,9 +61,6 @@ class TagesschauIE(InfoExtractor):
}, { }, {
'url': 'http://www.tagesschau.de/multimedia/video/video-102303~_bab-sendung-211.html', 'url': 'http://www.tagesschau.de/multimedia/video/video-102303~_bab-sendung-211.html',
'only_matching': True, 'only_matching': True,
}, {
'url': 'http://www.tagesschau.de/multimedia/politikimradio/audio-18407.html',
'only_matching': True,
}] }]
_FORMATS = { _FORMATS = {
@ -73,19 +80,26 @@ def _real_extract(self, url):
playerpage = self._download_webpage( playerpage = self._download_webpage(
player_url, display_id, 'Downloading player page') player_url, display_id, 'Downloading player page')
medias = re.findall(
r'"(http://media.+?)", type:"video/(.+?)", quality:"(.+?)"',
playerpage)
formats = [] formats = []
for url, ext, res in medias: for media in re.finditer(
r'''(?x)
(?P<q_url>["\'])(?P<url>http://media.+?)(?P=q_url)
,\s*type:(?P<q_type>["\'])(?P<type>video|audio)/(?P<ext>.+?)(?P=q_type)
(?:,\s*quality:(?P<q_quality>["\'])(?P<quality>.+?)(?P=q_quality))?
''', playerpage):
url = media.group('url')
type_ = media.group('type')
ext = media.group('ext')
res = media.group('quality')
f = { f = {
'format_id': res + '_' + ext, 'format_id': '%s_%s' % (res, ext) if res else ext,
'url': url, 'url': url,
'ext': ext, 'ext': ext,
'vcodec': 'none' if type_ == 'audio' else None,
} }
f.update(self._FORMATS.get(res, {})) f.update(self._FORMATS.get(res, {}))
formats.append(f) formats.append(f)
thumbnail_fn = re.findall(r'"(/multimedia/.+?\.jpg)"', playerpage)[-1] thumbnail = self._og_search_thumbnail(playerpage)
title = self._og_search_title(webpage).strip() title = self._og_search_title(webpage).strip()
description = self._og_search_description(webpage).strip() description = self._og_search_description(webpage).strip()
else: else:
@ -123,9 +137,7 @@ def _real_extract(self, url):
'filesize_approx': parse_filesize(m.group('filesize_approx')), 'filesize_approx': parse_filesize(m.group('filesize_approx')),
}) })
formats.append(format) formats.append(format)
thumbnail_fn = self._search_regex( thumbnail = self._og_search_thumbnail(webpage)
r'(?s)<img alt="Sendungsbild".*?src="([^"]+)"',
webpage, 'thumbnail', fatal=False)
description = self._html_search_regex( description = self._html_search_regex(
r'(?s)<p class="teasertext">(.*?)</p>', r'(?s)<p class="teasertext">(.*?)</p>',
webpage, 'description', default=None) webpage, 'description', default=None)
@ -133,7 +145,6 @@ def _real_extract(self, url):
r'<span class="headline".*?>(.*?)</span>', webpage, 'title') r'<span class="headline".*?>(.*?)</span>', webpage, 'title')
self._sort_formats(formats) self._sort_formats(formats)
thumbnail = 'http://www.tagesschau.de' + thumbnail_fn
return { return {
'id': display_id, 'id': display_id,