抓取百度音乐频道歌曲url

参考了 http://blog.csdn.net/banguijun/article/details/11815263

后写了一个抓取fm音乐url的模块，得到所有频道歌曲的url。缺点是百度会变更url地址，失效后需要重新获取。话不多说上代码：

# -*- coding: UTF-8 -*-

'''

Created on 2013-12-3

从百度的频道中抓取歌曲的下载地址

@author:

'''

import urllib

import json

SAVEPATH='/home/gfc/musiclistnew.txt' # defines the storage location 定义存储位置 用时要修改为自己的文件存放地址

getlisturl = "http://fm.baidu.com/dev/api/?tn=playlist&format=json&id=" #get list url   获取频道列表url

getmusicrealurl = 'http://music.baidu.com/data/music/fmlink?type=mp3&rate=320&songIds=' #获取歌曲地址url

html = urllib.urlopen("http://fm.baidu.com/").read().decode("utf-8")

start = html.find("{", html.find("rawChannelList"))  # find javascript code of the channel list urls

end = html.find(";", start)

listjson = html[start:end].strip()  # cut spaces to get channel list json

data = json.loads(listjson)  # parse json

channel_id_list = []

for item in data['channel_list']:

#     print "Channel Name:\t", item['channel_name'], "Category:\t", item['cate']

    channel_id_list.append(item['channel_id'])  # get channel id

musiclistfile = open(SAVEPATH, 'w') # open file

for channel_id in channel_id_list:#循环频道列表

    musiclist = urllib.urlopen(getlisturl + channel_id).read().decode("utf-8")

    musicidslist = json.loads(musiclist)['list']

    musicUrlList = []

    for songid in musicidslist:#遍历频道歌曲列表

        getMusicUrls = urllib.urlopen(getmusicrealurl + str(songid['id'])).read()

        urlmusic = json.loads(getMusicUrls)

        musicUrl = urlmusic['data']['songList']

        for songlink in musicUrl:#取得歌曲url并写入文本文件

            musiclistfile.write(songlink['songLink'])

            musiclistfile.write('\n')

musiclistfile.close()