yt-dlp/youtube_dl/extractor/qqmusic.py

116 lines
3.9 KiB
Python
Raw Normal View History

2015-03-17 12:03:29 +01:00
# coding: utf-8
from __future__ import unicode_literals
2015-03-18 06:56:02 +01:00
import random
import time
2015-03-18 07:59:33 +01:00
import re
2015-03-18 06:56:02 +01:00
2015-03-17 12:03:29 +01:00
from .common import InfoExtractor
from ..utils import strip_jsonp
2015-03-18 07:59:33 +01:00
from ..compat import compat_urllib_request
2015-03-17 12:03:29 +01:00
class QQMusicIE(InfoExtractor):
_VALID_URL = r'http://y.qq.com/#type=song&mid=(?P<id>[0-9A-Za-z]+)'
_TESTS = [{
'url': 'http://y.qq.com/#type=song&mid=004295Et37taLD',
'md5': 'bed90b6db2a7a7a7e11bc585f471f63a',
'info_dict': {
'id': '004295Et37taLD',
'ext': 'm4a',
'title': '可惜没如果',
'upload_date': '20141227',
'creator': '林俊杰',
}
}]
2015-03-18 06:56:02 +01:00
# Reference: m_r_GetRUin() in top_player.js
# http://imgcache.gtimg.cn/music/portal_v3/y/top_player.js
@staticmethod
def m_r_get_ruin():
curMs = int(time.time() * 1000) % 1000
return int(round(random.random() * 2147483647) * curMs % 1E10)
2015-03-17 12:03:29 +01:00
def _real_extract(self, url):
mid = self._match_id(url)
detail_info_page = self._download_webpage(
'http://s.plcloud.music.qq.com/fcgi-bin/fcg_yqq_song_detail_info.fcg?songmid=%s&play=0' % mid,
2015-03-18 07:59:33 +01:00
mid, note='Download song detail info',
2015-03-17 12:03:29 +01:00
errnote='Unable to get song detail info')
song_name = self._html_search_regex(
r"songname:\s*'([^']+)'", detail_info_page, 'song name')
publish_time = self._html_search_regex(
r'发行时间:(\d{4}-\d{2}-\d{2})', detail_info_page,
'publish time').replace('-', '')
singer = self._html_search_regex(
r"singer:\s*'([^']+)", detail_info_page, 'singer')
2015-03-18 06:56:02 +01:00
guid = self.m_r_get_ruin()
2015-03-17 12:03:29 +01:00
vkey = self._download_json(
'http://base.music.qq.com/fcgi-bin/fcg_musicexpress.fcg?json=3&guid=%s' % guid,
mid, note='Retrieve vkey', errnote='Unable to get vkey',
transform_source=strip_jsonp)['key']
song_url = 'http://cc.stream.qqmusic.qq.com/C200%s.m4a?vkey=%s&guid=%s&fromtag=0' % (mid, vkey, guid)
return {
'id': mid,
'url': song_url,
'title': song_name,
'upload_date': publish_time,
'creator': singer,
}
2015-03-18 07:59:33 +01:00
class QQMusicSingerIE(InfoExtractor):
_VALID_URL = r'http://y.qq.com/#type=singer&mid=(?P<id>[0-9A-Za-z]+)'
_TEST = {
'url': 'http://y.qq.com/#type=singer&mid=001BLpXF2DyJe2',
'info_dict': {
'id': '001BLpXF2DyJe2',
'title': '林俊杰',
'description': 'md5:2a222d89ba4455a3af19940c0481bb78',
},
'playlist_count': 12,
}
def _real_extract(self, url):
mid = self._match_id(url)
singer_page = self._download_webpage(
'http://y.qq.com/y/static/singer/%s/%s/%s.html' % (mid[-2], mid[-1], mid),
'Download singer page')
entries = []
for item in re.findall(r'<span class="data">([^<>]+)</span>', singer_page):
song_mid = item.split('|')[-5]
entries.append(self.url_result(
'http://y.qq.com/#type=song&mid=' + song_mid, 'QQMusic', song_mid))
singer_name = self._html_search_regex(
r"singername\s*:\s*'([^']+)'", singer_page, 'singer name',
default=None)
singer_id = self._html_search_regex(
r"singerid\s*:\s*'([0-9]+)'", singer_page, 'singer id',
default=None)
singer_desc = None
if singer_id:
req = compat_urllib_request.Request(
'http://s.plcloud.music.qq.com/fcgi-bin/fcg_get_singer_desc.fcg?utf8=1&outCharset=utf-8&format=xml&singerid=%s' % singer_id)
req.add_header(
'Referer', 'http://s.plcloud.music.qq.com/xhr_proxy_utf8.html')
singer_desc_page = self._download_xml(
req, 'Donwload singer description XML')
singer_desc = singer_desc_page.find('./data/info/desc').text
return self.playlist_result(entries, mid, singer_name, singer_desc)