forked from PeterDing/iScript
-
Notifications
You must be signed in to change notification settings - Fork 3
/
music.baidu.com.py
executable file
·262 lines (240 loc) · 10.8 KB
/
music.baidu.com.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
#!/usr/bin/env python2
# vim: set fileencoding=utf8
import re
import sys
import os
import random
import time
import json
import urllib2
import logging
import argparse
import select
from mutagen.id3 import ID3,TRCK,TIT2,TALB,TPE1,APIC,TDRC,COMM,TCOM,TCON,TSST,WXXX,TSRC
from HTMLParser import HTMLParser
parser = HTMLParser()
s = u'\x1b[1;%dm%s\x1b[0m' # terminual color template
headers = {
"Accept":"text/html,application/xhtml+xml,application/xml; \
q=0.9,image/webp,*/*;q=0.8",
"Accept-Encoding":"text/html",
"Accept-Language":"en-US,en;q=0.8,zh-CN;q=0.6,zh;q=0.4,zh-TW;q=0.2",
"Content-Type":"application/x-www-form-urlencoded",
"Referer":"http://www.baidu.com/",
"User-Agent":"Mozilla/5.0 (X11; Linux i686) AppleWebKit/537.36 \
(KHTML, like Gecko) Chrome/32.0.1700.77 Safari/537.36"
}
############################################################
# wget exit status
wget_es = {
0:"No problems occurred.",
2:"User interference.",
1<<8:"Generic error code.",
2<<8:"Parse error - for instance, when parsing command-line \
optio.wgetrc or .netrc...",
3<<8:"File I/O error.",
4<<8:"Network failure.",
5<<8:"SSL verification failure.",
6<<8:"Username/password authentication failure.",
7<<8:"Protocol errors.",
8<<8:"Server issued an error response."
}
############################################################
def modificate_text(text):
text = parser.unescape(text)
text = re.sub(r'//*', '-', text)
text = text.replace('/', '-')
text = text.replace('\\', '-')
text = re.sub(r'\s\s+', ' ', text)
return text
def modificate_file_name_for_wget(file_name):
file_name = re.sub(r'\s*:\s*', u' - ', file_name) # for FAT file system
file_name = file_name.replace('?', '') # for FAT file system
file_name = file_name.replace('"', '\'') # for FAT file system
return file_name
def z_index(song_infos):
size = len(song_infos)
if size <= 9:
return 1
elif size >= 10 and size <= 99:
return 2
elif size >= 100 and size <= 999:
return 3
else:
return 1
class baidu_music(object):
def __init__(self, url):
self.url = url
self.song_infos = []
self.json_url = ''
self.dir_ = os.getcwd().decode('utf8')
self.template_wgets = 'wget -nv -U "%s" -O "%s.tmp" %s' % (headers['User-Agent'], '%s', '%s')
self.template_album = 'http://music.baidu.com/album/%s'
if args.flac:
self.template_api = 'http://music.baidu.com/data/music/fmlink?songIds=%s&type=flac'
elif args.low:
self.template_api = 'http://music.baidu.com/data/music/fmlink?songIds=%s&type=mp3'
elif args.high:
self.template_api = 'http://music.baidu.com/data/music/fmlink?songIds=%s&type=mp3&rate=320'
else:
self.template_api = 'http://music.baidu.com/data/music/fmlink?songIds=%s&type=mp3&rate=320'
self.album_id = ''
self.song_id = ''
self.download = self.play if args.play else self.download
def get_songidlist(self, id_):
html = self.opener.open(self.template_album % id_).read()
songidlist = re.findall(r'/song/(\d+)', html)
api_json = self.opener.open(self.template_api % ','.join(songidlist)).read()
api_json = json.loads(api_json)
infos = api_json['data']['songList']
return infos
def get_cover(self, url):
i = 1
while True:
cover_data = self.opener.open(url).read()
if cover_data[:5] != '<?xml':
return cover_data
if i >= 10:
logging.info(" |--> Error: can't get cover image")
print s % (91, " |--> Error: can't get cover image")
sys.exit(0)
i += 1
def modified_id3(self, file_name, info):
id3 = ID3()
id3.add(TRCK(encoding=3, text=info['track']))
id3.add(TIT2(encoding=3, text=info['song_name']))
id3.add(TALB(encoding=3, text=info['album_name']))
id3.add(TPE1(encoding=3, text=info['artist_name']))
id3.add(COMM(encoding=3, desc=u'Comment', text=info['song_url']))
id3.add(APIC(encoding=3, mime=u'image/jpg', type=3, desc=u'Cover', data=self.get_cover(info['album_pic_url'])))
id3.save(file_name)
def url_parser(self):
if '/album/' in self.url:
self.album_id = re.search(r'/album/(\d+)', self.url).group(1)
print(s % (92, u'\n -- 正在分析专辑信息 ...'))
self.get_album_infos()
elif '/song/' in self.url:
self.song_id = re.search(r'/song/(\d+)', self.url).group(1)
print(s % (92, u'\n -- 正在分析歌曲信息 ...'))
self.get_song_infos()
else:
print(s % (91, u' 请正确输入baidu网址.'))
def get_song_infos(self):
logging.info('url -> http://music.baidu.com/song/%s' % self.song_id)
api_json = self.opener.open(self.template_api % self.song_id).read()
j = json.loads(api_json)
song_info = {}
song_info['song_id'] = unicode(j['data']['songList'][0]['songId'])
song_info['track'] = u''
song_info['song_url'] = u'http://music.baidu.com/song/' + song_info['song_id']
song_info['song_name'] = modificate_text(j['data']['songList'][0]['songName']).strip()
song_info['album_name'] = modificate_text(j['data']['songList'][0]['albumName']).strip()
song_info['artist_name'] = modificate_text(j['data']['songList'][0]['artistName']).strip()
song_info['album_pic_url'] = j['data']['songList'][0]['songPicRadio']
if args.flac:
song_info['file_name'] = song_info['song_name'] + ' - ' + song_info['artist_name'] + '.flac'
else:
song_info['file_name'] = song_info['song_name'] + ' - ' + song_info['artist_name'] + '.mp3'
song_info['durl'] = j['data']['songList'][0]['songLink']
self.song_infos.append(song_info)
self.download()
def get_album_infos(self):
logging.info('url -> http://music.baidu.com/album/%s' % self.album_id)
songidlist = self.get_songidlist(self.album_id)
z = z_index(songidlist)
ii = 1
for i in songidlist:
song_info = {}
song_info['song_id'] = unicode(i['songId'])
song_info['song_url'] = u'http://music.baidu.com/song/' + song_info['song_id']
song_info['track'] = unicode(ii)
song_info['song_name'] = modificate_text(i['songName']).strip()
song_info['artist_name'] = modificate_text(i['artistName']).strip()
song_info['album_pic_url'] = i['songPicRadio']
if args.flac:
song_info['file_name'] = song_info['track'].zfill(z) + '.' + song_info['song_name'] + ' - ' + song_info['artist_name'] + '.flac'
else:
song_info['file_name'] = song_info['track'].zfill(z) + '.' + song_info['song_name'] + ' - ' + song_info['artist_name'] + '.mp3'
song_info['album_name'] = modificate_text(i['albumName']).strip()
song_info['durl'] = i['songLink']
self.song_infos.append(song_info)
ii += 1
d = modificate_text(self.song_infos[0]['album_name'] + ' - ' + self.song_infos[0]['artist_name'])
self.dir_ = os.path.join(os.getcwd().decode('utf8'), d)
self.download()
def display_infos(self, i):
print '\n ----------------'
print ' >>', s % (94, i['file_name'])
print ' >>', s % (95, i['album_name'])
print ' >>', s % (92, 'http://music.baidu.com/song/%s' % i['song_id'])
print ''
def play(self):
for i in self.song_infos:
durl = i['durl']
self.display_infos(i)
os.system('mpv --really-quiet %s' % durl)
timeout = 1
ii, _, _ = select.select([sys.stdin], [], [], timeout)
if ii:
sys.exit(0)
else:
pass
def download(self):
dir_ = modificate_file_name_for_wget(self.dir_)
cwd = os.getcwd().decode('utf8')
csongs = len(self.song_infos)
if dir_ != cwd:
if not os.path.exists(dir_):
os.mkdir(dir_)
print(s % (97, u'\n >> ' + str(csongs) + u' 首歌曲将要下载.'))
logging.info('directory: %s' % dir_)
logging.info('total songs: %d' % csongs)
ii = 1
for i in self.song_infos:
t = modificate_file_name_for_wget(i['file_name'])
file_name = os.path.join(dir_, t)
if os.path.exists(file_name): ## if file exists, no get_durl
ii += 1
continue
file_name_for_wget = file_name.replace('`', '\`')
if 'zhangmenshiting.baidu.com' in i['durl']:
num = random.randint(0,100) % 7
col = s % (num + 90, i['file_name'])
print(u'\n ++ 正在下载: %s' % col)
logging.info(' #%d -> %s' % (ii, i['file_name'].encode('utf8')))
wget = self.template_wgets % (file_name_for_wget, i['durl'])
wget = wget.encode('utf8')
status = os.system(wget)
if status != 0: # other http-errors, such as 302.
wget_exit_status_info = wget_es[status]
logging.info(' \\\n \\->WARN: status: %d (%s), command: %s' % (status, wget_exit_status_info, wget))
print('\n\n ----### \x1b[1;91mERROR\x1b[0m ==> \x1b[1;91m%d (%s)\x1b[0m ###--- \n\n' % (status, wget_exit_status_info))
print(' ===> ' + wget)
break
else:
os.rename('%s.tmp' % file_name, file_name)
self.modified_id3(file_name, i)
ii += 1
#time.sleep(10)
else:
print s % (91, ' !! Oops, you are unlucky, the song is not from zhangmenshiting.baidu.com')
def main(url):
x = baidu_music(url)
opener = urllib2.build_opener()
opener.addheaders = headers.items()
x.opener = opener
x.url_parser()
logging.info(' ########### work is over ###########\n')
if __name__ == '__main__':
log_file = os.path.join(os.path.expanduser('~'), '.baidu.music.log')
logging.basicConfig(filename=log_file, level=10, format='%(asctime)s %(message)s')
print(s % (91, u'程序运行日志在 %s' % log_file))
p = argparse.ArgumentParser(description='downloading any music.baidu.com')
p.add_argument('url', help='any url of music.baidu.com')
p.add_argument('-f', '--flac', action='store_true', help='download flac')
p.add_argument('-i', '--high', action='store_true', help='download 320')
p.add_argument('-l', '--low', action='store_true', help='download 128')
p.add_argument('-p', '--play', action='store_true', \
help='play with mpv')
args = p.parse_args()
main(args.url)