python写的批量下载baidu mp3的程序 至少到09-9-18仍然可用
windows平台下的Py2.6 移植到linux应该也很容易默认10线程下载
其中多线程下载部分 是参考 http://hi.baidu.com/zjw0358/blog
mydown.py
#!/usr/bin/env python
# coding=utf-8
import httplib,urllib,urllib2
import re,os
from downmp3 import GetSize,DownMp3
def BaiduUrlDecode(enurl):
import string
from urllib import unquote
k = u'0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz'
decoded = ''
# print enurl
try:
key = k.index(u't') - k.index(enurl)
for i in range(enurl.__len__()):
char = enurl
if char in k:
decoded += k[(k.index(char) + key) % 62]
else:
decoded += char
except IndexError:
print 'enurl IndexError:',enurl,'$'
# print 'enurl',enurl
return unquote(decoded.encode('gbk'))
def BadiuUrlProcess(baidu_url):
import re
from urllib import quote
match_CHchar = r'([^:._,~`!@#\|{}\^\*\(\);%/\"\'\[\]\+\=\?\-\$\&\\\w]+)' #匹配中文
ch_pattern = re.compile(match_CHchar)
page_url = baidu_url
if ch_pattern.search(baidu_url):
page_url = ch_pattern.sub(quote(ch_pattern.search(baidu_url).groups().encode('gbk')),baidu_url)
return page_url
if __name__ == "__main__":
print """ 支持百度MP3的大部分列表音乐的下载，默认采用10线程下载
新歌top100
歌曲top500
歌手top200 (暂不支持下载)
中文金曲榜
经典老歌
热舞dj
流金岁月
电视金曲
歌曲列表
退出
--by auxten auxtenwpcgmailcom
""".decode('utf-8').encode('gbk')
id = int(raw_input('输入你想下载的list的编号: '.decode('utf-8').encode('gbk')))
if id == 1: topid = '/list/newhits.html?id=1?top1'
elif id == 2: topid = '/topso/mp3topsong.html?id=1?top2'
elif id == 3: topid = '/list/tvs.html?id=1?top5';exit(1)
elif id == 4: topid = '/list/bangping.html?id=1'#;exit(1)
elif id == 5: topid = '/list/oldsong.html?top6'
elif id == 6: topid = '/list/dj.html'
elif id == 7: topid = '/list/liujinsuiyue.html'
elif id == 8: topid = '/list/tvs.html?id=1?top5'
elif id == 9: topid = '/list/tvs.html?id=1?top5'#;exit(1)
elif id == 0: exit(1)
# topid = '/list/oldsong.html?top6'
# topid = '/list/tvs.html?id=1?top5'
print "Processing please wait.:)"
errorlist = []
conn = httplib.HTTPConnection('list.mp3.baidu.com')
conn.request("GET",topid)
response = conn.getresponse()
html = response.read().decode('gb18030')
# print html.encode('gbk')
conn.close()
match_type1 = r'">(\d{,3})\.' #编号
match_type2 = r'">(\d{,3})\.[\s\S]*?(.*?)[^)].*' #no url songname for 流金岁月
match_type3 = r'">(\d{,3})\.[\s\S]*?(.*?)[^)].*">(.*)\)' #name+author
match_type4 = r'[\s]*?(\d{,3})[\s\S]*?(.*?)[\s\S]*?target="_blank">(.*?)' #no url songname singer 中文金曲榜
list_number = re.findall(match_type1, html)
list_all = re.findall(match_type3, html)
if list_all == []:
# print 'list_all empty1!'
list_all = re.findall(match_type2, html)
if list_all == []:
# print 'list_all empty2!'
list_all = re.findall(match_type4, html)
# print 'list_all',list_all
# print 'list_all__len__',list_all.__len__()
conn = httplib.HTTPConnection('mp3.baidu.com')
songnumlst = range(0,list_all.__len__())
for num in songnumlst:
try:
try: authorname = '-'+list_all
except IndexError:
authorname = ''
print list_all.encode('gbk'),list_all.encode('gbk'),authorname.encode('gbk')
# print num
conn.request("GET",BadiuUrlProcess(list_all))
# print "URL!",BadiuUrlProcess(list_all).encode('gbk')
response = conn.getresponse()
html = response.read().decode('gb18030')
conn.close()
# print html.encode('gbk')
html = re.search(r'
页:
[1]