baidump3.py

用python实现的百度mp3搜索

# !/usr/bin/env python
# -*- coding: UTF-8 -*-
# author: watermoon
# date: 02/17/2009

import os, sys, re, string
from urllib import urlretrieve as URT
import urllib2
import urldecode

CODE = '0123456789ABCDEF'
QUERY = '(http:.*baidusg,)(.*)(&word=mp3.*sgid=1)'
MP3 = 'F=(\d+).*I="(\w{1}\w{2}\w{1}://\w+\..*\w{3})",J'

def gb2312(ch):				# Translate chinese input corresponding GB2312 code
	code = ''	# code = 'OX'
	code += CODE[ch/16]
	code += CODE[ch%16]
	return code

def format(word):			# translate into the format that baidu.com can recongnise
	code = ''
	i = 0
	l = len(word)
	while i < l:
		if ord(word[i]) < 127:
			if word[i] == ' ':
				code += '+'
			else:
				code += word[i]
		else:
			code += '%%%s' % gb2312(ord(word[i]))
		i += 1
	return code
	
def getWeb(url, tmp='.tmp'):		# get internet resource from server
	try:
		URT(url, tmp)
	except IOError:
		print 'Cannot fectch web page'
		sys.exit()
		
def getResource(url):
	req = urllib2.Request(url)
	try:
		response = urllib2.urlopen(req)
	except urllib2.URLError, e:
		print e.reason
	else:
		return response
		
def parseWeb(pat):			# parse and get the first link of result
	tmpfile = open('.tmp', 'r')
	lines = tmpfile.readlines()
	
	r = re.search(pat, lines)
	if r:
		tmpfile.close()
		os.remove('.tmp')
		return r
	tmpfile.close()
	os.remove('.tmp')
	return None
	
	
def urllib_one():
	word = raw_input('Search> ')
	url = 'http://mp3.baidu.com/m?f=ms&rn=&tn=baidump3&ct=134217728&word=%s&lm=0'\
			% format(word)
	getWeb(url)
	r = parseWeb(QUERY)
	if r:
		print 'Succeed in distilling query result url...'
		s = r.group(2)
		s = format(s)
		url = r.group(1) + s + r.group(3)
	else:
		print 'Fail to distill query url!'
		return
	
	getWeb(url)		# get to the last page where show the link
	r = parseWeb(MP3)
	if r:
		print 'Succeed in distilling url!'
		baidu = urldecode.codec()
		url = baidu.de_baidump3(int(r.group(1)), r.group(2))
		print 'Downloading mp3 file from: %s' % url
		getWeb(url, word+'_.mp3')

def urllib_two():
	word = raw_input('Search> ')
	url = 'http://mp3.baidu.com/m?f=ms&rn=&tn=baidump3&ct=134217728&word=%s&lm=0'\
			% format(word)
	print url
	res = getResource(url)
	data = res.read()
	
	#####
	r = re.search(QUERY, data)
	if r:
		print 'Succeed in distilling query result url...'
		s = r.group(2)
		s = format(s)
		url = r.group(1) + s + r.group(3)
	else:
		print 'Fail to distill query url!'
		return
		
	###
	print url
	res = getResource(url)
	data = res.read()
	r = re.search(MP3, data)
	
	###
	if r:
		print 'Succeed in distilling url!'
		baidu = urldecode.codec()
		print url
		url = baidu.de_baidump3(int(r.group(1)), r.group(2))
		print 'Downloading mp3 file from: %s' % url
		### download
		res = getResource(url)
		data = res.read()
		print 
		url = url[url.rfind('/')+1:]
		f = open(url, 'wb')
		f.write(data)
		f.close()
	
if __name__ == '__main__':
#	urllib_one()
	urllib_two()