Created
April 22, 2011 10:02
-
-
Save scturtle/936383 to your computer and use it in GitHub Desktop.
show all doubanFM favorite songs
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# coding: utf-8 | |
import cookielib,urllib2 | |
from cStringIO import StringIO | |
from pysqlite2 import dbapi2 as sqlite | |
from BeautifulSoup import BeautifulSoup | |
# a useful function from others | |
def sqlite2cookie(filename,host): | |
con = sqlite.connect(filename) | |
con.text_factory = str | |
cur = con.cursor() | |
cur.execute("select host, path, isSecure, expiry, name, value from moz_cookies where host like ?" | |
,['%%%s%%' % host]) | |
ftstr = ["FALSE","TRUE"] | |
s = StringIO() | |
s.write("""\ | |
# Netscape HTTP Cookie File | |
# http://www.netscape.com/newsref/std/cookie_spec.html | |
# This is a generated file! Do not edit. | |
""") | |
for item in cur.fetchall(): | |
s.write("%s\t%s\t%s\t%s\t%s\t%s\t%s\n" % ( | |
item[0], ftstr[item[0].startswith('.')], item[1], | |
ftstr[item[2]], item[3], item[4], item[5])) | |
s.seek(0) | |
cookie_jar = cookielib.MozillaCookieJar() | |
cookie_jar._really_load(s, '', True, True) | |
return cookie_jar | |
# get cookie | |
cookiejar = sqlite2cookie(u'E:\FirefoxPortable\Data\Profile\cookies.sqlite','douban') | |
opener = urllib2.build_opener(urllib2.HTTPCookieProcessor(cookiejar)) | |
urllib2.install_opener(opener) | |
# post cookie | |
url='http://douban.fm/mine' | |
req=urllib2.Request(url) | |
req.add_header('User-Agent','Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1)') | |
content=urllib2.urlopen(req).read() | |
# get it | |
url='http://douban.fm/mine?start=%d&type=liked' | |
pages=int(raw_input('pages of favs:')) | |
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 |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment