xiami_vip.py

#!/usr/bin/env python2
# vim: set fileencoding=utf8

import re, sys, os, urllib2, random, time, datetime
from mutagen.id3 import ID3,TRCK,TIT2,TALB,TPE1,APIC
from HTMLParser import HTMLParser

email = ''
password = ''

#############################################################
# from https://gist.github.com/lepture/1014329
#############################################################
# {{{
#!/usr/bin/env python
# -*- coding: utf-8 -*-
#
# Copyright (c) 2011, lepture.com
#
# Redistribution and use in source and binary forms, with or without
# modification, are permitted provided that the following conditions
# are met:
#
#    * Redistributions of source code must retain the above copyright
#      notice, this list of conditions and the following disclaimer.
#    * Redistributions in binary form must reproduce the above
#      copyright notice, this list of conditions and the following
#      disclaimer in the documentation and/or other materials provided
#      with the distribution.
#    * Neither the name of the author nor the names of its contributors
#      may be used to endorse or promote products derived from this
#      software without specific prior written permission.
#
# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
# "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
# LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
# A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
# HOLDER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
# SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
# LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
# DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
# THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
# (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
# OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.


import urllib
import httplib
from contextlib import closing
from Cookie import SimpleCookie

ua = 'Mozilla/5.0 (X11; Linux i686) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/28.0.1500.95 Safari/537.36'

checkin_headers = {
    'User-Agent': ua,
    'Content-Length': '0',
    'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8',
    'X-Requested-With': 'XMLHttpRequest',
    'Host': 'www.xiami.com',
    'Origin': 'http://www.xiami.com/',
    'Referer': 'http://www.xiami.com/',
    'Content-Length': '0',
}

class Xiami(object):
    def __init__(self, email, password):
        self.email = email
        self.password = password
        self._auth = None

    def login(self):
        print 'login ....'
        _form = {
            'email': self.email,
            'password': self.password,
            'LoginButton': '登录',
        }
        data = urllib.urlencode(_form)
        headers = {'User-Agent': ua}
        headers['Referer'] = 'http://www.xiami.com/web/login'
        headers['Content-Type'] = 'application/x-www-form-urlencoded'
        with closing(httplib.HTTPConnection('www.xiami.com')) as conn:
            conn.request('POST', '/web/login', data, headers)
            res = conn.getresponse()
            cookie = res.getheader('Set-Cookie')
            self._auth = SimpleCookie(cookie)['member_auth'].value
            print 'login success'
            return self._auth

    def checkin(self):
        if not self._auth:
            self.login()
        headers = checkin_headers
        headers['Cookie'] = 'member_auth=%s; t_sign_auth=1' % self._auth
        with closing(httplib.HTTPConnection('www.xiami.com')) as conn:
            conn.request('POST', '/task/signin', None, headers)
            res = conn.getresponse()
            return res.read()

# }}}
########################################################

def init(email, password):
    home = os.path.expanduser('~')
    cookie_dir = os.path.join(home, '.Xiami.cookie')
    xm = Xiami(email, password)
    if os.path.exists(cookie_dir):
        f = open(cookie_dir).read().split('\n')
        tm_s = (int(datetime.datetime.now().strftime('%s')) - int(f[0])) > 18000
        xm._auth = f[1]
        member_auth = xm._auth
        auth = xm.checkin()
        if auth != '0' or tm_s:
            member_auth = xm.login()
            if member_auth != f[1]: print '  --> member_auth is new one.'
            tm = datetime.datetime.now().strftime('%s')
            open(cookie_dir, 'w').write(tm + '\n' + member_auth)
            return member_auth
        else:
            return member_auth
    else:
        member_auth = xm.login()
        tm = datetime.datetime.now().strftime('%s')
        open(cookie_dir, 'w').write(tm + '\n' + member_auth)
        return member_auth

cookie = 'member_auth=%s' % init(email, password)

opener = urllib2.build_opener()
opener.addheaders = [('Accept', 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8'), ('User-Agent', ua), ('Cookie', cookie)]

s = '\x1b[1;%dm%s\x1b[0m'

re_id = re.compile(r'song_id>(\d+)<')
re_title = re.compile(r'title><!\[CDATA\[(.+?)\]\]')
re_artist = re.compile(r'artist><!\[CDATA\[(.+?)\]\]')
re_album_name = re.compile(r'album_name><!\[CDATA\[(.+?)\]\]')
re_pic = re.compile(r'pic>(.+?)<')
re_song = re.compile(r'"location":"(.+?)"')

parser = HTMLParser()
template_info = 'http://www.xiami.com/song/playlist/id/%s/type/%s'
template_parse = 'http://www.xiami.com/song/gethqsong/sid/%s'
template_wgets = 'wget -nv -c -U "' + ua + '" -O "%s" %s'


def decry(row, encryed_url):
    url = encryed_url
    urllen = len(url)
    rows = int(row)

    cols_base = urllen / rows  # basic column count
    rows_ex = urllen % rows    # count of rows that have 1 more column

    matrix = []
    for r in xrange(rows):
        length = cols_base + 1 if r < rows_ex else cols_base
        matrix.append(url[:length])
        url = url[length:]

    url = ''
    for i in xrange(urllen):
        url += matrix[i % rows][i / rows]

    return urllib.unquote(url).replace('^', '0')

def song_infos(code, tp):
    infos = []
    api_xml = opener.open(template_info % (code, tp)).read()
    for i in api_xml.split('<track>\n')[1:]:
        t = {}
        t['id_'] = re_id.findall(i)[0].strip()
        t['title'] = re_title.findall(i)[0].strip()
        t['artist'] = re_artist.findall(i)[0].strip()
        t['album_name'] = re_album_name.findall(i)[0].strip()
        tt = re_pic.findall(i)[0].strip()
        t['pic'] = re.sub(r'_\d\.jpg$', '.jpg', tt)
        infos.append(t)
    return infos

def modified_sname(sname):
    sname = parser.unescape(sname)
    sname = sname.replace('/', ' - ')
    sname = sname.replace('\\', '')
    sname = sname.replace('"', '\\"')
    try:
        sname = sname.encode('utf8')
    except UnicodeDecodeError:
        pass
    if len(sname) >= 250:
        return sname[:243] + '...mp3'
    else:
        return sname

def modified_id3(sname, info, track):
    id3 = ID3()
    id3.add(TRCK(encoding=3, text=track))
    id3.add(TIT2(encoding=3, text=info['title'].decode('utf8')))
    id3.add(TALB(encoding=3, text=info['album_name'].decode('utf8')))
    id3.add(TPE1(encoding=3, text=info['artist'].decode('utf8')))
    id3.add(APIC(encoding=3, mime='->', type=3, desc=u'Cover', data=info['pic']))
    id3.save(sname)

def download(code, tp):
    infos = song_infos(code, tp)
    size = len(infos)
    z = 0
    if size <= 9:
        z = 1
    elif size >= 10 and size <= 99:
        z = 2
    elif size >= 100 and size <= 999:
        z = 3
    else:
        z = 1

    ii = 1
    for i in infos:
        if i['id_'] != '':
            sname = str(ii).zfill(z) + '.' + i['title'] + ' - ' + i['artist'] + '.mp3'
            sname = modified_sname(sname)
            j = opener.open(template_parse % i['id_']).read()
            t = re_song.search(j)
            t = t.group(1)
            row = t[0]
            encryed_url = t[1:]
            durl = decry(row, encryed_url)
            num = random.randint(0,100) % 7
            col = s % (num + 90, sname)

            print '\n  ++ 正在下载: %s' % col
            wget = template_wgets % (sname, durl)
            status = os.system(wget)
            time.sleep(10)
            if status not in [0, 2048]:     # other http-errors, such as 302.
                print '\n\n ----### ERROR ==> %d ###--- \n\n' % status
                print '  ===> ', wget
                break

            modified_id3(sname, i, str(ii))
            ii += 1

def main(url):
    if 'showcollect/' in url:
        code = re.search(r'showcollect/id/(\d+)', url).group(1)
        tp = '3'
        download(code, tp)
    elif 'album/' in url:
        code = re.search(r'album/(\d+)', url).group(1)
        tp = '1'
        download(code, tp)
    elif 'artist/' in url:
        code = re.search(r'artist/(\d+)', url).group(1)
        tp = '2'
        download(code, tp)  # 下载该歌手最火的前20首歌
    else:
        code = re.search(r'song/(\d+)', url).group(1)
        tp = '0'
        download(code, tp)

if __name__ == '__main__':
    argv = sys.argv
    if argv[1] == '-a' and argv[2]:
        main(argv[2])
    else:
        print 'Usage:\n  -a url       download any list of xiami.com'