[转]Python下载百度新歌100的代码

lshboo 发表于 2017-5-6 10:11:29

http://images.cnblogs.com/cnblogs_com/maplye/Images/OutliningIndicators/None.gif#!/usr/bin/python
http://images.cnblogs.com/cnblogs_com/maplye/Images/OutliningIndicators/None.gif# -*- coding: utf-8 -*-
http://images.cnblogs.com/cnblogs_com/maplye/Images/OutliningIndicators/None.gif# Copyright (c) 2006 UbuntuChina <http://www.ubuntu.org.cn>
http://images.cnblogs.com/cnblogs_com/maplye/Images/OutliningIndicators/None.gif# License: GPLv2
http://images.cnblogs.com/cnblogs_com/maplye/Images/OutliningIndicators/None.gif# Author: oneleaf <oneleaf AT gmail.com>
http://images.cnblogs.com/cnblogs_com/maplye/Images/OutliningIndicators/None.gif
http://images.cnblogs.com/cnblogs_com/maplye/Images/OutliningIndicators/None.gifimport httplib
http://images.cnblogs.com/cnblogs_com/maplye/Images/OutliningIndicators/None.gifimport re
http://images.cnblogs.com/cnblogs_com/maplye/Images/OutliningIndicators/None.gifimport urllib
http://images.cnblogs.com/cnblogs_com/maplye/Images/OutliningIndicators/None.gifimport os
http://images.cnblogs.com/cnblogs_com/maplye/Images/OutliningIndicators/None.gifimport locale
http://images.cnblogs.com/cnblogs_com/maplye/Images/OutliningIndicators/None.gif
http://images.cnblogs.com/cnblogs_com/maplye/Images/OutliningIndicators/None.gifdef getdownurl(url):
http://images.cnblogs.com/cnblogs_com/maplye/Images/OutliningIndicators/None.gif    urllist=[]
http://images.cnblogs.com/cnblogs_com/maplye/Images/OutliningIndicators/None.gif    conn = httplib.HTTPConnection('mp3.baidu.com')
http://images.cnblogs.com/cnblogs_com/maplye/Images/OutliningIndicators/None.gif    conn.request("GET",url)
http://images.cnblogs.com/cnblogs_com/maplye/Images/OutliningIndicators/None.gif    response = conn.getresponse()
http://images.cnblogs.com/cnblogs_com/maplye/Images/OutliningIndicators/None.gif    html=response.read()
http://images.cnblogs.com/cnblogs_com/maplye/Images/OutliningIndicators/None.gif    conn.close()
http://images.cnblogs.com/cnblogs_com/maplye/Images/OutliningIndicators/None.gif    expression='http://220.181.27.54/m(.*)</a>'
http://images.cnblogs.com/cnblogs_com/maplye/Images/OutliningIndicators/None.gif    listSentence = re.findall(expression, html)
http://images.cnblogs.com/cnblogs_com/maplye/Images/OutliningIndicators/None.gif    lineno=0
http://images.cnblogs.com/cnblogs_com/maplye/Images/OutliningIndicators/None.gif    while lineno<len(listSentence):
http://images.cnblogs.com/cnblogs_com/maplye/Images/OutliningIndicators/None.gif        mp3url=re.search('title=(.*)onclick',listSentence)
http://images.cnblogs.com/cnblogs_com/maplye/Images/OutliningIndicators/None.gif        if mp3url:
http://images.cnblogs.com/cnblogs_com/maplye/Images/OutliningIndicators/None.gif           mp3url=mp3url.group(0)
http://images.cnblogs.com/cnblogs_com/maplye/Images/OutliningIndicators/None.gif           mp3url=re.search('http(\S*)',mp3url)
http://images.cnblogs.com/cnblogs_com/maplye/Images/OutliningIndicators/None.gif           if mp3url:
http://images.cnblogs.com/cnblogs_com/maplye/Images/OutliningIndicators/None.gif              mp3url=mp3url.group(0)
http://images.cnblogs.com/cnblogs_com/maplye/Images/OutliningIndicators/None.gif              try:
http://images.cnblogs.com/cnblogs_com/maplye/Images/OutliningIndicators/None.gif                  mp3url=mp3url.decode('gbk')
http://images.cnblogs.com/cnblogs_com/maplye/Images/OutliningIndicators/None.gif              except:pass
http://images.cnblogs.com/cnblogs_com/maplye/Images/OutliningIndicators/None.gif              urllist.append(mp3url)
http://images.cnblogs.com/cnblogs_com/maplye/Images/OutliningIndicators/None.gif        lineno+=2
http://images.cnblogs.com/cnblogs_com/maplye/Images/OutliningIndicators/None.gif    return urllist
http://images.cnblogs.com/cnblogs_com/maplye/Images/OutliningIndicators/None.gif
http://images.cnblogs.com/cnblogs_com/maplye/Images/OutliningIndicators/None.gifdef downmp3(url,author,name,filelist):
http://images.cnblogs.com/cnblogs_com/maplye/Images/OutliningIndicators/None.gif    filename=author+"-"+name;
http://images.cnblogs.com/cnblogs_com/maplye/Images/OutliningIndicators/None.gif    for i in filelist:
http://images.cnblogs.com/cnblogs_com/maplye/Images/OutliningIndicators/None.gif        name=unicode(i,locale.getpreferredencoding())
http://images.cnblogs.com/cnblogs_com/maplye/Images/OutliningIndicators/None.gif        if name.find(filename) == 0:
http://images.cnblogs.com/cnblogs_com/maplye/Images/OutliningIndicators/None.gif            print u"文件已经下载，忽略。"
http://images.cnblogs.com/cnblogs_com/maplye/Images/OutliningIndicators/None.gif            return 1
http://images.cnblogs.com/cnblogs_com/maplye/Images/OutliningIndicators/None.gif    urllists=getdownurl(url)
http://images.cnblogs.com/cnblogs_com/maplye/Images/OutliningIndicators/None.gif    for i in urllists:
http://images.cnblogs.com/cnblogs_com/maplye/Images/OutliningIndicators/None.gif        print u"正在连接",i
http://images.cnblogs.com/cnblogs_com/maplye/Images/OutliningIndicators/None.gif
http://images.cnblogs.com/cnblogs_com/maplye/Images/OutliningIndicators/None.gif        ext=i[-4:]
http://images.cnblogs.com/cnblogs_com/maplye/Images/OutliningIndicators/None.gif        try:
http://images.cnblogs.com/cnblogs_com/maplye/Images/OutliningIndicators/None.gif            urlopen = urllib.URLopener()
http://images.cnblogs.com/cnblogs_com/maplye/Images/OutliningIndicators/None.gif            fp=urlopen.open(i)
http://images.cnblogs.com/cnblogs_com/maplye/Images/OutliningIndicators/None.gif            data = fp.read()
http://images.cnblogs.com/cnblogs_com/maplye/Images/OutliningIndicators/None.gif            fp.close()
http://images.cnblogs.com/cnblogs_com/maplye/Images/OutliningIndicators/None.gif            filename=filename+ext;
http://images.cnblogs.com/cnblogs_com/maplye/Images/OutliningIndicators/None.gif            file=open(filename,'w+b')
http://images.cnblogs.com/cnblogs_com/maplye/Images/OutliningIndicators/None.gif            file.write(data)
http://images.cnblogs.com/cnblogs_com/maplye/Images/OutliningIndicators/None.gif            file.close()
http://images.cnblogs.com/cnblogs_com/maplye/Images/OutliningIndicators/None.gif            print u"下载成功!"
http://images.cnblogs.com/cnblogs_com/maplye/Images/OutliningIndicators/None.gif            return 1
http://images.cnblogs.com/cnblogs_com/maplye/Images/OutliningIndicators/None.gif        except:
http://images.cnblogs.com/cnblogs_com/maplye/Images/OutliningIndicators/None.gif            continue
http://images.cnblogs.com/cnblogs_com/maplye/Images/OutliningIndicators/None.gif    return 0
http://images.cnblogs.com/cnblogs_com/maplye/Images/OutliningIndicators/None.gif
http://images.cnblogs.com/cnblogs_com/maplye/Images/OutliningIndicators/None.gifif __name__ == "__main__":
http://images.cnblogs.com/cnblogs_com/maplye/Images/OutliningIndicators/None.gif    conn = httplib.HTTPConnection('list.mp3.baidu.com')
http://images.cnblogs.com/cnblogs_com/maplye/Images/OutliningIndicators/None.gif    conn.request("GET",'/list/newhits.html?id=1')
http://images.cnblogs.com/cnblogs_com/maplye/Images/OutliningIndicators/None.gif    response = conn.getresponse()
http://images.cnblogs.com/cnblogs_com/maplye/Images/OutliningIndicators/None.gif    html=response.read().decode('gbk')
http://images.cnblogs.com/cnblogs_com/maplye/Images/OutliningIndicators/None.gif    conn.close()
http://images.cnblogs.com/cnblogs_com/maplye/Images/OutliningIndicators/None.gif    expression='<a href="http://mp3.baidu.com/m(.*)</a>'
http://images.cnblogs.com/cnblogs_com/maplye/Images/OutliningIndicators/None.gif    listSentence = re.findall(expression, html)
http://images.cnblogs.com/cnblogs_com/maplye/Images/OutliningIndicators/None.gif    lineno=0
http://images.cnblogs.com/cnblogs_com/maplye/Images/OutliningIndicators/None.gif    while lineno<len(listSentence):
http://images.cnblogs.com/cnblogs_com/maplye/Images/OutliningIndicators/None.gif       url=re.search('(.*)target',listSentence)
http://images.cnblogs.com/cnblogs_com/maplye/Images/OutliningIndicators/None.gif       url='/m'+url.group(0)[:-8]
http://images.cnblogs.com/cnblogs_com/maplye/Images/OutliningIndicators/None.gif       name=re.search('blank>(.*)',listSentence)
http://images.cnblogs.com/cnblogs_com/maplye/Images/OutliningIndicators/None.gif       name=name.group(0)[6:]
http://images.cnblogs.com/cnblogs_com/maplye/Images/OutliningIndicators/None.gif       author=re.search('blank>(.*)',listSentence+1])
http://images.cnblogs.com/cnblogs_com/maplye/Images/OutliningIndicators/None.gif       author=author.group(0)[6:]
http://images.cnblogs.com/cnblogs_com/maplye/Images/OutliningIndicators/None.gif       print u"开始下载",author,name
http://images.cnblogs.com/cnblogs_com/maplye/Images/OutliningIndicators/None.gif       filelist=os.listdir('.');
http://images.cnblogs.com/cnblogs_com/maplye/Images/OutliningIndicators/None.gif       if downmp3(url,author,name,filelist)==0:
http://images.cnblogs.com/cnblogs_com/maplye/Images/OutliningIndicators/None.gif          print u"下载",author,name,u'失败！'
http://images.cnblogs.com/cnblogs_com/maplye/Images/OutliningIndicators/None.gif       lineno+=2
http://images.cnblogs.com/cnblogs_com/maplye/Images/OutliningIndicators/None.gif

页: [1]

运维网's Archiver

[转]Python下载百度新歌100的代码