1
0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-09 12:42:28 +01:00
yt-dlp/youtube_dl/extractor/thesixtyone.py

101 lines
2.9 KiB
Python
Raw Normal View History

# coding: utf-8
from __future__ import unicode_literals
import json
import re
from .common import InfoExtractor
from ..utils import unified_strdate
class TheSixtyOneIE(InfoExtractor):
_VALID_URL = r'''(?x)https?://(?:www\.)?thesixtyone\.com/
(?:.*?/)*
(?:
s|
song/comments/list|
song
)/(?P<id>[A-Za-z0-9]+)/?$'''
_SONG_URL_TEMPLATE = 'http://thesixtyone.com/s/{0:}'
_SONG_FILE_URL_TEMPLATE = 'http://{audio_server:}.thesixtyone.com/thesixtyone_production/audio/{0:}_stream'
_THUMBNAIL_URL_TEMPLATE = '{photo_base_url:}_desktop'
_TESTS = [
{
'url': 'http://www.thesixtyone.com/s/SrE3zD7s1jt/',
'md5': '821cc43b0530d3222e3e2b70bb4622ea',
'info_dict': {
'id': 'SrE3zD7s1jt',
'ext': 'mp3',
'title': 'CASIO - Unicorn War Mixtape',
'thumbnail': 're:^https?://.*_desktop$',
'upload_date': '20071217',
'duration': 3208,
}
},
{
'url': 'http://www.thesixtyone.com/song/comments/list/SrE3zD7s1jt',
'only_matching': True,
},
{
'url': 'http://www.thesixtyone.com/s/ULoiyjuJWli#/s/SrE3zD7s1jt/',
'only_matching': True,
},
{
'url': 'http://www.thesixtyone.com/#/s/SrE3zD7s1jt/',
'only_matching': True,
},
{
'url': 'http://www.thesixtyone.com/song/SrE3zD7s1jt/',
'only_matching': True,
},
]
_DECODE_MAP = {
"x": "a",
"m": "b",
"w": "c",
"q": "d",
"n": "e",
"p": "f",
"a": "0",
"h": "1",
"e": "2",
"u": "3",
"s": "4",
"i": "5",
"o": "6",
"y": "7",
"r": "8",
"c": "9"
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
song_id = mobj.group('id')
webpage = self._download_webpage(
self._SONG_URL_TEMPLATE.format(song_id), song_id)
song_data = json.loads(self._search_regex(
r'"%s":\s(\{.*?\})' % song_id, webpage, 'song_data'))
keys = [self._DECODE_MAP.get(s, s) for s in song_data['key']]
url = self._SONG_FILE_URL_TEMPLATE.format(
"".join(reversed(keys)), **song_data)
formats = [{
'format_id': 'sd',
'url': url,
'ext': 'mp3',
}]
return {
'id': song_id,
'title': '{artist:} - {name:}'.format(**song_data),
'formats': formats,
'comment_count': song_data.get('comments_count'),
'duration': song_data.get('play_time'),
'like_count': song_data.get('score'),
'thumbnail': self._THUMBNAIL_URL_TEMPLATE.format(**song_data),
'upload_date': unified_strdate(song_data.get('publish_date')),
}