import requests,os,time,sys,re
from scrapy.selector import Selector

class wangyiyun():
  def __init__(self):
    self.headers = {
      'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/55.0.2883.87 Safari/537.36',
      'Referer': 'http://music.163.com/'}
    self.main_url='http://music.163.com/'
    self.session = requests.Session()
    self.session.headers=self.headers

  def get_songurls(self,playlist):
    '''進入所選歌單頁面，得出歌單里每首歌各自的ID 形式就是“song?id=64006"'''
    url=self.main_url+'playlist?id=%d'% playlist
    re= self.session.get(url)  #直接用session進入網頁，懶得構造了
    sel=Selector(text=re.text)  #用scrapy的Selector，懶得用BS4了
    songurls=sel.xpath('//ul[@class="f-hide"]/li/a/@href').extract()
    return songurls  #所有歌曲組成的list
    ##['/song?id=64006', '/song?id=63959', '/song?id=25642714', '/song?id=63914', '/song?id=4878122', '/song?id=63650']

  def get_songinfo(self,songurl):
    '''根據songid進入每首歌信息的網址，得到歌曲的信息
    return：'64006'，'陳小春-失戀王'''
    url=self.main_url+songurl
    re=self.session.get(url)
    sel=Selector(text=re.text)
    song_id = url.split('=')[1]
    song_name = sel.xpath("http://em[@class='f-ff2']/text()").extract_first()
    singer= '&'.join(sel.xpath("http://p[@class='des s-fc4']/span/a/text()").extract())
    songname=singer+'-'+song_name
    return str(song_id),songname

  def download_song(self, songurl, dir_path):
    '''根據歌曲url，下載mp3文件'''
    song_id, songname = self.get_songinfo(songurl) # 根據歌曲url得出ID、歌名
    song_url = 'http://music.163.com/song/media/outer/url?id=%s.mp3'%song_id
    path = dir_path + os.sep + songname + '.mp3' # 文件路徑
    requests.urlretrieve(song_url, path) # 下載文件

  def work(self, playlist):
    songurls = self.get_songurls(playlist) # 輸入歌單編號，得到歌單所有歌曲的url
    dir_path = r'C:\Users\Administrator\Desktop'
    for songurl in songurls:
      self.download_song(songurl, dir_path) # 下載歌曲

if __name__ == '__main__':
  d = wangyiyun()
  d.work(2214059025)