[thesixtyone] Add new extractor (closes #3781)

This commit is contained in:
Naglis Jonaitis 2014-10-04 22:40:36 +03:00
parent e9be9a6acd
commit 5e69192ef7
2 changed files with 101 additions and 0 deletions

View File

@ -371,6 +371,7 @@
from .testurl import TestURLIE from .testurl import TestURLIE
from .tf1 import TF1IE from .tf1 import TF1IE
from .theplatform import ThePlatformIE from .theplatform import ThePlatformIE
from .thesixtyone import TheSixtyOneIE
from .thisav import ThisAVIE from .thisav import ThisAVIE
from .tinypic import TinyPicIE from .tinypic import TinyPicIE
from .tlc import TlcIE, TlcDeIE from .tlc import TlcIE, TlcDeIE

View File

@ -0,0 +1,100 @@
# 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')),
}