1
0
mirror of https://codeberg.org/polarisfm/youtube-dl synced 2024-12-24 07:17:55 +01:00
youtube-dl/youtube_dl/extractor/freesound.py

80 lines
2.4 KiB
Python
Raw Normal View History

2014-02-10 21:03:14 +01:00
from __future__ import unicode_literals
2013-07-15 17:16:44 +02:00
import re
from .common import InfoExtractor
from ..utils import (
float_or_none,
get_element_by_class,
get_element_by_id,
unified_strdate,
)
2014-02-10 21:03:14 +01:00
2013-07-15 17:16:44 +02:00
2013-07-15 21:33:45 +02:00
class FreesoundIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?freesound\.org/people/[^/]+/sounds/(?P<id>[^/]+)'
2013-07-15 17:17:09 +02:00
_TEST = {
2014-02-10 21:03:14 +01:00
'url': 'http://www.freesound.org/people/miklovan/sounds/194503/',
'md5': '12280ceb42c81f19a515c745eae07650',
'info_dict': {
'id': '194503',
'ext': 'mp3',
'title': 'gulls in the city.wav',
'description': 'the sounds of seagulls in the city',
'duration': 130.233,
'uploader': 'miklovan',
'upload_date': '20130715',
'tags': list,
2013-07-15 17:17:09 +02:00
}
}
2013-07-15 17:16:44 +02:00
def _real_extract(self, url):
audio_id = self._match_id(url)
webpage = self._download_webpage(url, audio_id)
audio_url = self._og_search_property('audio', webpage, 'song url')
title = self._og_search_property('audio:title', webpage, 'song title')
2014-02-10 21:03:14 +01:00
description = self._html_search_regex(
r'(?s)id=["\']sound_description["\'][^>]*>(.+?)</div>',
webpage, 'description', fatal=False)
2013-07-15 17:16:44 +02:00
duration = float_or_none(
get_element_by_class('duration', webpage), scale=1000)
upload_date = unified_strdate(get_element_by_id('sound_date', webpage))
uploader = self._og_search_property(
'audio:artist', webpage, 'uploader', fatal=False)
channels = self._html_search_regex(
r'Channels</dt><dd>(.+?)</dd>', webpage,
'channels info', fatal=False)
tags_str = get_element_by_class('tags', webpage)
tags = re.findall(r'<a[^>]+>([^<]+)', tags_str) if tags_str else None
audio_urls = [audio_url]
LQ_FORMAT = '-lq.mp3'
if LQ_FORMAT in audio_url:
audio_urls.append(audio_url.replace(LQ_FORMAT, '-hq.mp3'))
formats = [{
'url': format_url,
'format_note': channels,
'quality': quality,
} for quality, format_url in enumerate(audio_urls)]
self._sort_formats(formats)
2014-02-10 21:03:14 +01:00
return {
'id': audio_id,
2014-02-10 21:03:14 +01:00
'title': title,
2013-07-15 21:33:45 +02:00
'description': description,
'duration': duration,
'uploader': uploader,
'upload_date': upload_date,
'tags': tags,
'formats': formats,
2014-02-10 21:03:14 +01:00
}