X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/467f1716f3b46ffc038848b9b08a833a7811be09..32569172c58bbc32bcc4fdb64af8615f98c4cccb:/youtube_dl/extractor/freesound.py?ds=sidebyside diff --git a/youtube_dl/extractor/freesound.py b/youtube_dl/extractor/freesound.py index de14b12..138b6bc 100644 --- a/youtube_dl/extractor/freesound.py +++ b/youtube_dl/extractor/freesound.py @@ -1,36 +1,79 @@ +from __future__ import unicode_literals + import re from .common import InfoExtractor -from ..utils import determine_ext +from ..utils import ( + float_or_none, + get_element_by_class, + get_element_by_id, + unified_strdate, +) + class FreesoundIE(InfoExtractor): - _VALID_URL = r'(?:https?://)?(?:www\.)?freesound\.org/people/([^/]+)/sounds/(?P[^/]+)' + _VALID_URL = r'https?://(?:www\.)?freesound\.org/people/[^/]+/sounds/(?P[^/]+)' _TEST = { - u'url': u'http://www.freesound.org/people/miklovan/sounds/194503/', - u'file': u'194503.mp3', - u'md5': u'12280ceb42c81f19a515c745eae07650', - u'info_dict': { - u"title": u"gulls in the city.wav", - u"uploader" : u"miklovan", - u'description': u'the sounds of seagulls in the city', + '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, } } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - music_id = mobj.group('id') - webpage = self._download_webpage(url, music_id) - title = self._html_search_regex(r'
.*?(.+?)', - webpage, 'music title', flags=re.DOTALL) - music_url = self._og_search_property('audio', webpage, 'music url') - description = self._html_search_regex(r'
(.*?)
', - webpage, 'description', fatal=False, flags=re.DOTALL) - - return [{ - 'id': music_id, - 'title': title, - 'url': music_url, - 'uploader': self._og_search_property('audio:artist', webpage, 'music uploader'), - 'ext': determine_ext(music_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') + + description = self._html_search_regex( + r'(?s)id=["\']sound_description["\'][^>]*>(.+?)
', + webpage, 'description', fatal=False) + + 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
(.+?)
', webpage, + 'channels info', fatal=False) + + tags_str = get_element_by_class('tags', webpage) + tags = re.findall(r']+>([^<]+)', 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) + + return { + 'id': audio_id, + 'title': title, 'description': description, - }] + 'duration': duration, + 'uploader': uploader, + 'upload_date': upload_date, + 'tags': tags, + 'formats': formats, + }