获得豆瓣FM加心歌曲信息的py脚本
2011年4月13日 18:37
update at 2012.2.29: 传送门 to isnowfy大牛的方法
参考各种资料写的,有个小缺点是需要输入有多少页加心歌曲
改改输出格式应该可以用小众软件里介绍的E音乐盒批量下载吧
当时不知道这个软件,只好又写个爬谷歌音乐的,然后手动下载,真是蛋疼
python 2.7 + BeautifulSoupct
# coding: utf-8
from BeautifulSoup import BeautifulSoup
import urllib,urllib2,cookielib
loginurl='http://www.douban.com/accounts/login'
url='http://douban.fm/mine?start=%d&type=liked'
captchaurl='http://www.douban.com/misc/captcha?id=%s&size=s'
email=raw_input('email:')
passwd=raw_input('passwd:')
pages=int(raw_input('pages:'))
cookie_support= urllib2.HTTPCookieProcessor(cookielib.CookieJar())
opener = urllib2.build_opener(cookie_support, urllib2.HTTPHandler)
urllib2.install_opener(opener)
content=urllib2.urlopen(loginurl).read()
postdata=urllib.urlencode({
'source':'simple',
'form_email':email,
'form_password':passwd,
#'captcha-id':captchaid,
#'captcha-solution':raw_input('code in pic:'),
#'user_login':'登录',
})
req = urllib2.Request( url = loginurl, data = postdata)
content=urllib2.urlopen(req).read()
if opener.open(req).geturl() == 'http://www.douban.com/':
print 'login success!'
for i in range(pages):
content=urllib2.urlopen(url % (i*9,)).read()
soup=BeautifulSoup(str(content))
for tr in soup.findAll('tr')[1:]:
td=tr.findAll('td')
print td[0].string,td[1].span.string #,td[1].a.string # title artist album
else:
print 'login fault'
update:登录方式有变化,douban现在会对频繁登录的ip加验证码,总之此代码有时效性,仅供参考
另附一个从baidu爬歌曲url的脚本,把上面脚本的结果保存成文件,再用这个脚本得到url,最后再用downthemall或迅雷批量下载,多么蛋疼
# coding: utf-8
import sys,os,urllib2,xml
from xml.dom import minidom
lc = sys.getfilesystemencoding()
baseurl0="http://box.zhangmen.baidu.com/x?op=7&mode=1&count=1&listid=&title=%s"
baseurl1="http://box.zhangmen.baidu.com/x?op=12&count=1&mtype=4&title=%s"
f=open('list.txt','r')
for eachline in f.readlines():
song=eachline#raw_input('Song name:').decode(lc).encode('gbk')
try:
data=urllib2.urlopen(baseurl0 % urllib2.quote(song))
data=data.read().replace('gb2312','utf-8').decode('gbk').encode('utf8')
except:
print 'failed on '+eachline
continue
doc=minidom.parseString(data) # 丫真挑剔
names=doc.getElementsByTagName('name')
if not names:
print 'failed on '+eachline
continue
count=0
#for i in names:
#print count,i.firstChild.nodeValue.replace('$',' ').encode(lc)
#count+=1
choice=0#int(raw_input('\nyour choice:'))
data=urllib2.urlopen(baseurl1 % urllib2.quote(names[choice].firstChild.nodeValue.encode('gbk')))
data=data.read().replace('gb2312','utf-8').decode('gbk').encode('utf8')
doc=minidom.parseString(data)
urls=doc.getElementsByTagName('url')
#print '\n song urls:'
#for i in urls:
i=urls[0]
try:
t=i.childNodes
pos=t[0].firstChild.nodeValue.rfind('/')
prefix=t[0].firstChild.nodeValue[0:pos+1]
suffix=t[1].firstChild.nodeValue
print prefix+suffix
except:
print 'failed on '+eachline
raw_input('\nEnter to exit ...')
