#!/usr/bin/python# -*- coding: utf-8 -*-''' 百度中批量下載某歌手的歌(目前只下載第一頁，可以自行拓展) @author:admin @qq: 1243385033'''import threading, urllib2, os,re,sysfrom bs4 import BeautifulSoupfrom Queue import Queue'''目標歌手'''SINGER = u'亞東''''保存路徑'''SAVE_FOLDER = 'F:/music/'# 查詢urlsearch_url = "http://music.baidu.com/search/song?key=%s&s=1"# 百度音樂播放盒urlsong_url = "http://box.zhangmen.baidu.com/x?op=12&count=1&mtype=1&title="class Downloader(threading.Thread):  def __init__(self, task):    threading.Thread.__init__(self)    self.task = task  def run(self):    '''覆蓋父類的run方法'''    while True:      url = self.task.get()      self.download(url)      self.task.task_done()  def build_path(self, filename):    join = os.path.join    parentPath=join(SAVE_FOLDER,SINGER)    filename = filename + '.mp3'    myPath = join(parentPath, filename)    return myPath  def download(self, url):    '''下載文件'''    sub_url = url.items()    f_name = sub_url[0][0]    req_url = sub_url[0][1]    handle = urllib2.urlopen(req_url)    # 保存路徑    save_path = self.build_path(f_name)    with open(save_path, "wb") as handler:      while True:        chunk = handle.read(1024)        if not chunk:          break        handler.write(chunk)        msg = u"已經(jīng)從 %s下載完成" % req_url      sys.stdout.write(msg)      sys.stdout.flush()class HttpRequest:  def __init__(self):    self.task = []    self.reg_decode = re.compile('<decode>.*?CDATA/[(.*?)/]].*?</decode>')    self.reg_encode = re.compile('<encode>.*?CDATA/[(.*?)/]].*?</encode>')    self.init()    self.target_url = search_url % urllib2.quote(self.encode2utf8(SINGER))  def encode2utf8(self,source):    if source and isinstance(source,(str,unicode)):      source=source.encode("utf8")      return source    return source  def mkDir(self, dir_name):    if not os.path.exists(dir_name):      os.mkdir(dir_name)  def init(self):    self.mkDir(SAVE_FOLDER)    subPath = os.path.join(SAVE_FOLDER, SINGER)    self.mkDir(subPath)  def http_request(self):    global song_url    '''發(fā)起請求'''    response=urllib2.urlopen(self.target_url)    # 獲取頭信息    content = response.read()    response.close()    # 使用BeautifulSoup    html = BeautifulSoup(content, from_encoding="utf8")    # 提取HTML標簽    span_tag = html.find_all('div', {"monkey":"song-list"})[0].find_all('span', class_='song-title')      # 遍歷List    for a_tag in span_tag:      song_name = unicode(a_tag.find_all("a")[0].get_text())      song_url = song_url + urllib2.quote(self.encode2utf8(song_name))      song_url = song_url + '$$' + urllib2.quote(self.encode2utf8(SINGER)) + '$$$$&url=&listenreelect=0&.r=0.1696378872729838'      xmlfile = urllib2.urlopen(song_url)      xml_content = xmlfile.read()      xmlfile.close()      url1 = re.findall(self.reg_encode, xml_content)      url2 = re.findall(self.reg_decode, xml_content)      if not url1 or not url2:        continue      url = url1[0][:url1[0].rindex('/') + 1] + url2[0]      self.task.append({song_name:url})    return self.taskdef start_download(urls):  #創(chuàng)建一個隊列  quene=Queue()  #獲取list的大小  size=len(urls)  #開啟線程  for _ in xrange(size):    t=Downloader(quene)    t.setDaemon(True)    t.start()  #入隊列  for url in urls:    quene.put(url)  quene.join()if __name__=='__main__':  http=HttpRequest()  urls=http.http_request()  start_download(urls)