Akkariin/youtube-dl
1
0
Fork 0
mirror of https://github.com/l1ving/youtube-dl synced 2025-02-02 22:32:54 +08:00
Code Issues Releases Wiki Activity

[SverigesRadio] Add new extractor

Browse Source
This commit is contained in:
burnoutberni 2018-09-07 23:52:43 +02:00
parent 2d4fe594c6
commit c1ddcce4b1
No known key found for this signature in database
GPG Key ID: 0624B5FEF71461FB
2 changed files with 77 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
youtube_dl/extractor/extractors.py
View File

@ -1061,6 +1061,10 @@ from .streamcz import StreamCZIE
from .streetvoice import StreetVoiceIE
from .stretchinternet import StretchInternetIE
from .sunporno import SunPornoIE
from .sverigesradio import (
SverigesRadioArtikelIE,
SverigesRadioAvsnittIE,
)
from .svt import (
SVTIE,
SVTPageIE,

72
youtube_dl/extractor/sverigesradio.py Normal file
View File

@ -0,0 +1,72 @@
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
class SverigesRadioIE(InfoExtractor):
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
json = self._download_json('https://sverigesradio.se/sida/playerajax/getaudiourl?type=' + self.SR_type + '&quality=high&format=iis&id=' + video_id, video_id)
audioUrl = json.get('audioUrl')
# TODO more code goes here, for example ...
# title = self._html_search_regex(r'<h1>(.+?)</h1>', webpage, 'title')
return {
'url': audioUrl,
'id': video_id,
'title': self._og_search_title(webpage),
# TODO more properties (see youtube_dl/extractor/common.py)
}
class SverigesRadioArtikelIE(SverigesRadioIE):
_VALID_URL = r'https?://(?:www\.)?sverigesradio\.se/sida/artikel.aspx\?(.*)artikel=(?P<id>[0-9]*)'
_TEST = {
'url': 'https://sverigesradio.se/sida/artikel.aspx?programid=83&artikel=7038546',
'md5': '6a4917e1923fccb080e5a206a5afa542',
'info_dict': {
'id': '7038546',
'ext': 'm4a',
'title': 'Esa Teittinen: Sanningen har inte kommit fram - Nyheter (Ekot)',
# TODO more properties, either as:
# * A value
# * MD5 checksum; start the string with md5:
# * A regular expression; start the string with re:
# * Any Python type (for example int or float)
}
}
SR_type = 'publication'
class SverigesRadioAvsnittIE(SverigesRadioIE):
_VALID_URL = r'https?://(?:www\.)?sverigesradio\.se/sida/avsnitt/(?P<id>[0-9]*)'
_TESTS = [{
'url': 'https://sverigesradio.se/sida/avsnitt/1140922?programid=1300',
'md5': '20dc4d8db24228f846be390b0c59a07c',
'info_dict': {
'id': '1140922',
'ext': 'mp3',
'title': 'Metoo och valen - Konflikt',
# TODO more properties, either as:
# * A value
# * MD5 checksum; start the string with md5:
# * A regular expression; start the string with re:
# * Any Python type (for example int or float)
}
}, {
'url': 'https://sverigesradio.se/sida/avsnitt/1140948?programid=4772',
'md5': 'b360f34e1931cbd6dbf9c502a4b2e35d',
'info_dict': {
'id': '1140948',
'ext': 'm4a',
'title': 'Anne Sofie von Otter – efter Benny Fredrikssons död - Söndagsintervjun',
# TODO more properties, either as:
# * A value
# * MD5 checksum; start the string with md5:
# * A regular expression; start the string with re:
# * Any Python type (for example int or float)
}
},
]
SR_type = 'episode'