#!/usr/bin/env python
#encoding=utf-8
#Using GPL v2
#Author: cocobear.cn@gmail.com

import urllib2,urllib,cookielib,httplib
import sys,re
import gzip,StringIO

user    = "cocobearc"         #user whose bookmarks you want get
tag     = "from cang2html"      #tag that you want to mark
id      = 0
def cang2html(name,url,description):
    global user
    file_name = user+".html"
    f = open(file_name,"a")
    f.write("\t<DT><A HREF=\""+url+"\">"+name+"</A>\n")
    if description:
        f.write("\t<DD>"+description+"</DD>\n")
    f.close()

def cang2adr(name,url,description):
    global user,id
    file_name = user+".adr"
    f = open(file_name,"a")
    f.write("#URL\n")
    f.write("\tID="+str(id)+"\n")
    f.write("NAME="+name+"\n\t"+"URL="+url+"\n")
    if description:
        f.write("\tDESCRIPTION="+description+"\n")
    f.close()
    id+=1

def process_data(data):

    result = re.findall("((?:http|ftp|https|file)://.*)\" target.*lnk\d+\">(.+?)</font>.*dc\d+\">(.*?)</div>",data)
    #print len(result)
    for url,name,description in result:
        #print name,url,description
        cang2html(name,url,description)
        cang2adr(name,url,description)

def get_data(user,opener,page):
    url = "http://cang.baidu.com/"+user+"/page/"+str(page)
    gziped_data = opener.open(url).read()
    gziped_stream = StringIO.StringIO(gziped_data)
    data = gzip.GzipFile(fileobj=gziped_stream).read()
    return data.decode('gbk').encode('utf-8')


def init():
    httplib.HTTPConnection.debuglevel  =  1 
    cookie = cookielib.CookieJar()
    opener = urllib2.build_opener(urllib2.HTTPCookieProcessor(cookie))

    exheaders = [("User-Agent","Opera/9.27 (X11; Linux x86_64; U; en)"),("Connection","Keep-Alive"),("Referer","http://cang.baidu.com"),("Accept","text/html, application/xml;q=0.9, application/xhtml+xml, */*;q=0.1"),("Accept-Charset","iso-8859-1, utf-8, utf-16, *;q=0.1"),("Cookie2","$Version=1"),("Accept-Encoding","deflate, gzip, x-gzip, identity, *;q=0"),]

    opener.addheaders = exheaders
    urllib2.install_opener(opener)
    return opener

   
def create_adr_file(name):
    global tag,id

    f = open(name,"w")
    f.write("""Opera Hotlist version 2.0
Options: encoding = utf8, version=3
""")
    f.write("#FOLDER\n")
    f.write("\tID="+str(id)+"\n")
    id+=1
    f.write("\tNAME="+tag+"\n")
    f.close()

def create_html_file(name):
    global tag

    f = open(name,"w")
    f.write("""<!DOCTYPE NETSCAPE-Bookmark-file-1>
<META HTTP-EQUIV="Content-Type" CONTENT="text/html; charset=UTF-8">
<!--This is an automatically generated file.
It will be read and overwritten.
Code write by cocobear with Python
Edit the file carefully!-->
<TITLE>Generated by cang2html</TITLE>
""")
    f.write("<H1>"+tag+"</H1>\n")
    f.write("<DL><P>\n")
    f.close()

def end_html_file(name):
    
    f = open(name,"a")
    f.write("</DL><P>\n")
    f.close()

def main(argv=None):
    global user,tag
    
    opener=init()
    data = get_data(user,opener,1)
    match = re.search("（共(\d+)条）",data)
    if match:
        total = int(match.group(1))
    else:
        print "User has no bookmars!"
        return 1
    print "Total %d bookmarks" % total
    print "Start getting ......"

    create_html_file(user+".html")
    create_adr_file(user+".adr")

    process_data(data)
    if total % 10 != 0:
        for i in range(1,10):
            if (total+i) % 10 == 0:
                total+=i
    total/=10

    for i in range(2,total+1):
        data = get_data(user,opener,i)
        #print "process %d" % i
        process_data(data)

    end_html_file(user+".html")
    #end_adr_file(user+".adr")

    print "Success!\nLook %s.html for your bookmarks" % user
    print "Success!\nLook %s.adr for your bookmarks" % user


if __name__ == "__main__":
    sys.exit(main())