可可熊的窝

百度搜藏有不少问题，其中一个就是不能导出。

因为电脑丢了以前浏览器里的书签都没了，不过在百度测试搜藏的时候我用自己浏览器里的书签试过，刚好里面还有旧一点的书签，今天突然想起这事打算把把书签导出来，没想到竟然没有这个功能，今天没什么事就自己写了个工具，可以导出百度的搜藏，只需要手动确定用户名,程序里可以指定导出时使用的标签，因为没有登录，所以需要先把你所有的书签设置为公开：

[cocobear@cocobear cang]$ cat cang.py
[cocobear@cocobear cang]$ cat cang.py
#!/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    = "cocobear_cn"         #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+\">(.+?).*dc\d+\">(.*?)",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("</p></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())

该程序可以把百度搜藏导出为Opera使用的adr格式书签，以及html格式的书签，可以方便导入Opera浏览器，以及delicious(de.licio.us)等网上书签。

代码下载
?: 运算符表示“查找子模式的匹配字符串，但不包括反向引用中的匹配结果”
.*是贪婪匹配
.*?非贪婪匹配