add support for Baidu Music (with lyrics), fix #1

README.md

@@ -44,6 +44,7 @@ Fork me on GitHub: <https://github.com/soimort/you-get>
 * Sohu (搜狐视频) <http://tv.sohu.com>
 * 56 (56网) <http://www.56.com>
 * Xiami (虾米) <http://www.xiami.com>
+* Baidu (百度音乐) <http://music.baidu.com>
 
 ## Dependencies
 
@@ -255,6 +256,8 @@ You-Get基于优酷下载脚本[iambus/youku-lixian](https://github.com/iambus/y
 * 搜狐视频 <http://tv.sohu.com>
 * 56网 <http://www.56.com>
 * 虾米 <http://www.xiami.com>
+* 百度音乐 <http://music.baidu.com>
+
 
 ## 依赖
 

README.txt

@@ -47,6 +47,7 @@ Supported Sites (As of Now)
 * Sohu (搜狐视频) http://tv.sohu.com
 * 56 (56网) http://www.56.com
 * Xiami (虾米) http://www.xiami.com
+* Baidu (百度音乐) <http://music.baidu.com>
 
 Dependencies
 ------------

src/you_get/__main__.py

@@ -50,6 +50,7 @@ def url_to_module(url):
         'vimeo': vimeo,
         'vine': vine,
         'xiami': xiami,
+        'baidu': baidu,
         'yinyuetai': yinyuetai,
         'youku': youku,
         'youtu': youtube,

src/you_get/downloader/__init__.py

@@ -29,6 +29,7 @@ from .vimeo import *
 from .vine import *
 from .w56 import *
 from .xiami import *
+from .baidu import *
 from .yinyuetai import *
 from .youku import *
 from .youtube import *

src/you_get/downloader/baidu.py

@@ -0,0 +1,78 @@
+#!/usr/bin/env python
+# -*- coding: utf-8 -*-
+
+__all__ = ['baidu_download']
+
+from ..common import *
+
+from urllib import parse
+
+def baidu_get_song_html(sid):
+    return get_html('http://music.baidu.com/song/%s/download?__o=%%2Fsong%%2F%s' % (sid, sid), faker = True)
+
+def baidu_get_song_url(html):
+    return r1(r'<a href="/data/music/file\?link=(.*)" id="download"', html)
+
+def baidu_get_song_artist(html):
+    return r1(r'singer_name:"(.*)"', html)
+
+def baidu_get_song_album(html):
+    return r1(r'ablum_name:"(.*)"', html)
+
+def baidu_get_song_title(html):
+    return r1(r'song_title:"(.*)"', html)
+
+def baidu_download_lyric(sid, file_name, output_dir):
+    html = get_html('http://music.baidu.com/song/' + sid)
+    href = r1(r'<a class="down-lrc-btn" data-lyricdata=\'{ "href":"(.*)" }\' href="#">', html)
+    if href:
+        lrc = get_html('http://music.baidu.com' + href)
+        if len(lrc) > 0:
+            with open(output_dir + "/" + file_name.replace('/', '-') + '.lrc', 'w') as x:
+                x.write(lrc)
+
+def baidu_download_song(sid, output_dir = '.', merge = True, info_only = False):
+    html = baidu_get_song_html(sid)
+    url = baidu_get_song_url(html)
+    title = baidu_get_song_title(html)
+    artist = baidu_get_song_artist(html)
+    album = baidu_get_song_album(html)
+    type, ext, size = url_info(url, faker = True)
+    print_info(site_info, title, type, size)
+    if not info_only:
+        file_name = "%s - %s - %s" % (title, album, artist)
+        download_urls([url], file_name, ext, size, output_dir, merge = merge, faker = True)
+        baidu_download_lyric(sid, file_name, output_dir)
+
+def baidu_download_album(aid, output_dir = '.', merge = True, info_only = False):
+    html = get_html('http://music.baidu.com/album/%s' % aid, faker = True)
+    album_name = r1(r'<h2 class="album-name">(.*)<\/h2>', html)
+    artist = r1(r'<span class="author_list" title="(.*)">', html)
+    output_dir = '%s/%s - %s' % (output_dir, artist, album_name)
+    ids = json.loads(r1(r'<span class="album-add" data-adddata=\'(.*)\'>', html).replace('&quot', '').replace(';', '"'))['ids']
+    track_nr = 1
+    for id in ids:
+        song_html = baidu_get_song_html(id)
+        song_url = baidu_get_song_url(song_html)
+        song_title = baidu_get_song_title(song_html)
+        file_name = '%02d.%s' % (track_nr, song_title)
+        type, ext, size = url_info(song_url, faker = True)
+        print_info(site_info, song_title, type, size)
+        if not info_only:
+            download_urls([song_url], file_name, ext, size, output_dir, merge = merge, faker = True)
+            baidu_download_lyric(id, file_name, output_dir)
+        track_nr += 1
+
+def baidu_download(url, output_dir = '.', stream_type = None, merge = True, info_only = False):
+
+    if re.match(r'http://music.baidu.com/album/\d+', url):
+        id = r1(r'http://music.baidu.com/album/(\d+)', url)
+        baidu_download_album(id, output_dir, merge, info_only)
+
+    if re.match('http://music.baidu.com/song/\d+', url):
+        id = r1(r'http://music.baidu.com/song/(\d+)', url)
+        baidu_download_song(id, output_dir, merge, info_only)
+
+site_info = "Baidu.com"
+download = baidu_download
+download_playlist = playlist_not_supported("baidu")