xiami_vip.py

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

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

cookie = 'member_auth='

opener = urllib2.build_opener()
opener.addheaders = [('Accept', 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8'), ('User-Agent', 'Mozilla/5.0 (X11; Linux i686) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/28.0.1500.95 Safari/537.36'), ('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 Mozilla/5.0 -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)
            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)  # 该歌手热门歌曲中的前20首
    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'