python 中国裁决文书网 爬虫,完整版!!!

代码:

import execjs
import requests
headers={
                "Accept":"*/*",
"Accept-Encoding":"gzip, deflate",
"Accept-Language":"zh-CN,zh;q=0.8",
"Cache-Control":"max-age=0",
"Connection":"keep-alive",
"Content-Length":"40",
"Content-Type":"application/x-www-form-urlencoded; charset=UTF-8",
"Cookie":"_gscu_2116842793=389615802hdkze57; _gscbrs_2116842793=1; Hm_lvt_d2caefee2de09b8a6ea438d74fd98db2=1538961580; ASP.NET_SessionId=rvjjcq0lq41gqsrphevulxqd; Hm_lpvt_d2caefee2de09b8a6ea438d74fd98db2=1538988174; vjkl5=a8289f8999ff4e57810148185fad76048086c78b",
"Host":"wenshu.court.gov.cn",
"Origin":"http://wenshu.court.gov.cn",
"Referer":"http://wenshu.court.gov.cn/list/list/?sorttype=1&number=&guid=690f1e5d-fc1b-c74024a3-b1c2ed7f4032&conditions=searchWord+QWJS+++%E5%85%A8%E6%96%87%E6%A3%80%E7%B4%A2:%E5%A4%A7%E8%BF%9E%20%E4%B8%9C%E8%BD%AF",
"User-Agent":"Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/49.0.2623.221 Safari/537.36 SE 2.X MetaSr 1.0",
"X-Requested-With":"XMLHttpRequest"
    }
def get_guid():
    ctx = execjs.compile("""
            var createGuid = function () {
            return (((1 + Math.random()) * 0x10000) | 0).toString(16).substring(1);
            }
            function aa(){
                return createGuid() + createGuid() + "-" + createGuid() + "-" + createGuid() + createGuid() + "-" + createGuid() + createGuid() + createGuid();;

            }
    """)
    func = ctx.call("aa")
    return  func

def get_number():

    guid=get_guid()
    url='http://wenshu.court.gov.cn/ValiCode/GetCode'
    data ={'guid':guid}
    res=requests.post(url,headers=headers,data=data)
    return res.text.strip()

def getvlx5():
    with open('getkey.js') as fp:
        js = fp.read()
        ctx = execjs.compile(js)
        vl5x = ctx.call("getKey", "a8289f8999ff4e57810148185fad76048086c78b")
        return vl5x

上面是分别获取 vlx5,number 和guid的三个参数

vl5x = ctx.call("getKey", "a8289f8999ff4e57810148185fad76048086c78b")

第二个参数是上面header中的cookies里面的 vlx5的值 所以每次请求都得获取最新的cookies ,第一个参数就是 getkey.js中的方法名,getKey代码在下面

def postUrl():
    guid = get_guid()
    print(guid)
    number = get_number()
    print(number)
    vl5x=getvlx5()
    print(vl5x)
    payload = {'Param': '案件类型:刑事案件', 'Index': '1','Page': '10', 'Order': '法院层级','Direction': 'asc', 'vl5x': vl5x,'number':number, 'guid': guid}
    res=requests.post("http://wenshu.court.gov.cn/List/ListContent",data=payload,headers=headers)
    print(res.text)

然后post请求,获取的就是json对象 其中值有

runEval的值(这个值 是总的一个列表就一个) 和每条信息对应的文书ID

下面的就是详情页 的url例如:

http://wenshu.court.gov.cn/content/content?DocID=c4f382e9-394c-408e-8ad5-a878010c71af&KeyWord= 

所以我们要获取的docID

headers={
                "Accept":"*/*",
"Accept-Encoding":"gzip, deflate",
"Accept-Language":"zh-CN,zh;q=0.8",
"Cache-Control":"max-age=0",
"Connection":"keep-alive",
"Content-Length":"40",
"Content-Type":"application/x-www-form-urlencoded; charset=UTF-8",
"Cookie":"_gscu_2116842793=389615802hdkze57; _gscbrs_2116842793=1; Hm_lvt_d2caefee2de09b8a6ea438d74fd98db2=1538961580; ASP.NET_SessionId=rvjjcq0lq41gqsrphevulxqd; Hm_lpvt_d2caefee2de09b8a6ea438d74fd98db2=1538988174; vjkl5=a8289f8999ff4e57810148185fad76048086c78b",
"Host":"wenshu.court.gov.cn",
"Origin":"http://wenshu.court.gov.cn",
"Referer":"http://wenshu.court.gov.cn/list/list/?sorttype=1&number=&guid=690f1e5d-fc1b-c74024a3-b1c2ed7f4032&conditions=searchWord+QWJS+++%E5%85%A8%E6%96%87%E6%A3%80%E7%B4%A2:%E5%A4%A7%E8%BF%9E%20%E4%B8%9C%E8%BD%AF",
"User-Agent":"Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/49.0.2623.221 Safari/537.36 SE 2.X MetaSr 1.0",
"X-Requested-With":"XMLHttpRequest"
    }
rid="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"
weshuid="DcKOwrcNw4BADMOEVlJ6woVSccO/wpHDrCsJEjjDgjcjwplvZ8Kzw4fDq8KiKzXDqMOgw6duPCskL8O3YcKrNyXCp2DDnMKhX8KwwppowoXCnS7DqMOUw7rCr8K+w4ATw4LDjkbCmsOqw6ZMwowKecOGHG3CvsO/HsOFwp8vw5BQAMOzwoJPEk7DssO2aBFew6F7w5dgEUrDrUnDtcObw6QxViVIwqpCBsK2w7fCp8KOwqPCuAHCosKGXcO8w7LCiCXDv8Onw5jDlFYAHw=="
payload = {'runEval': rid, 'docIds': weshuid}
res=requests.post("http://wenku.jwzlai.com/common/decode/docId",data=payload,headers=headers)
print(res.text)

rid就是runEval的值 都复制过来,a就是每条数据对应的文书ID 请求结果为下面

{"msg":"","code":0,"data":{"DcKOwrcNw4BADMOEVlJ6woVSccO/wpHDrCsJEjjDgjcjwplvZ8Kzw4fDq8KiKzXDqMOgw6duPCskL8O3YcKrNyXCp2DDnMKhX8KwwppowoXCnS7DqMOUw7rCr8K+w4ATw4LDjkbCmsOqw6ZMwowKecOGHG3CvsO/HsOFwp8vw5BQAMOzwoJPEk7DssO2aBFew6F7w5dgEUrDrUnDtcObw6QxViVIwqpCBsK2w7fCp8KOwqPCuAHCosKGXcO8w7LCiCXDv8Onw5jDlFYAHw==":"c4f382e9-394c-408e-8ad5-a878010c71af"}}

code是0就表示对了

最后文本请求 是这个url:http://wenshu.court.gov.cn/CreateContentJS/CreateContentJS.aspx?DocID=8252121f-8260-4241-b707-018d52d151ca

可能出现的错误 

remind key :出现这个就是表示上面的header 中的cookies过期了

请求docid的时候出现html文本 是nignx错误什么的 那表示 runEval和文书ID过期了 需要重新替换了 还有cookies过期

如果请求的文书ID对应的docid对应为空 那么就是cookies过期或runEval和文书ID过期了

怎么实施自动获取cookies 用的是selenium  可以自动获取 或者你自己模拟登陆 然后获取

哪个地方有问题 或者不明白 请留言 一起讨论

至于getKey.js  复制到一个js文件中 然后读取就行了

var return_key;
var _fxxx = function (p, a, c, k, e, d) { e = function (c) { return (c < a ? "" : e(parseInt(c / a))) + ((c = c % a) > 35 ? String.fromCharCode(c + 29) : c.toString(36)) }; if (!''.replace(/^/, String)) { while (c--) d[e(c)] = k[c] || e(c); k = [function (e) { return d[e] }]; e = function () { return '\\w+' }; c = 1; }; while (c--) if (k[c]) p = p.replace(new RegExp('\\b' + e(c) + '\\b', 'g'), k[c]); return p; };
function de(str, count, strReplace) {
    var arrReplace = strReplace.split('|');
    for (var i = 0; i < count; i++) {
        str = str.replace(new RegExp('\\{' + i + '\\}', 'g'), arrReplace[i]);
    }
    return str;
}
function getKey(key) {
    return_key = key;
    eval(de("eval(_fxxx('e n(7){9 d=0;j(9 i=0;i<7.k;i++){d+=(7.g(i)<<(i%m))}f d}e p(7){9 d=0;j(9 i=0;i<7.k;i++){d+=(7.g(i)<<(i%m))+i}f d}e E(7,o){9 d=0;j(9 i=0;i<7.k;i++){d+=(7.g(i)<<(i%m))+(i*o)}f d}e x(7,o){9 d=0;j(9 i=0;i<7.k;i++){d+=(7.g(i)<<(i%m))+(i+o-7.g(i))}f d}e z(7){9 7=7.8(5,5*5)+7.8((5+1)*(5+1),3);9 a=7.8(5)+7.8(-4);9 b=7.8(4)+a.8(-6);f h(7).8(4,l)}e w(7){9 7=7.8(5,5*5)+\"5\"+7.8(1,2)+\"1\"+7.8((5+1)*(5+1),3);9 a=7.8(5)+7.8(4);9 b=7.8(t)+a.8(-6);9 c=7.8(4)+a.8(6);f h(c).8(4,l)}e A(7){9 7=7.8(5,5*5)+\"r\"+7.8(1,2)+7.8((5+1)*(5+1),3);9 a=n(7.8(5))+7.8(4);9 b=n(7.8(5))+7.8(4);9 c=7.8(4)+b.8(5);f h(c).8(1,l)}e y(7){9 7=7.8(5,5*5)+\"r\"+7.8(1,2)+7.8((5+1)*(5+1),3);9 a=p(7.8(5))+7.8(4);9 b=7.8(4)+a.8(5);9 c=n(7.8(5))+7.8(4);f h(b).8(3,l)}e B(7){9 7=7.8(5,5*5)+\"2\"+7.8(1,2)+7.8((5+1)*(5+1),3);9 d=0;j(9 i=0;i<7.8(1).k;i++){d+=(7.g(i)<<(i%m))}9 s=d+7.8(4);9 d=0;9 a=7.8(5);j(9 i=0;i> 5] |= 0x80 << ((len) % 32);
    x[(((len + 64) >>> 9) << 4) + 14] = len;

    var a =  1732584193;
    var b = -271733879;
    var c = -1732584194;
    var d =  271733878;

    for(var i = 0; i < x.length; i += 16)
    {
        var olda = a;
        var oldb = b;
        var oldc = c;
        var oldd = d;

        a = md5_ff(a, b, c, d, x[i+ 0], 7 , -680876936);
        d = md5_ff(d, a, b, c, x[i+ 1], 12, -389564586);
        c = md5_ff(c, d, a, b, x[i+ 2], 17,  606105819);
        b = md5_ff(b, c, d, a, x[i+ 3], 22, -1044525330);
        a = md5_ff(a, b, c, d, x[i+ 4], 7 , -176418897);
        d = md5_ff(d, a, b, c, x[i+ 5], 12,  1200080426);
        c = md5_ff(c, d, a, b, x[i+ 6], 17, -1473231341);
        b = md5_ff(b, c, d, a, x[i+ 7], 22, -45705983);
        a = md5_ff(a, b, c, d, x[i+ 8], 7 ,  1770035416);
        d = md5_ff(d, a, b, c, x[i+ 9], 12, -1958414417);
        c = md5_ff(c, d, a, b, x[i+10], 17, -42063);
        b = md5_ff(b, c, d, a, x[i+11], 22, -1990404162);
        a = md5_ff(a, b, c, d, x[i+12], 7 ,  1804603682);
        d = md5_ff(d, a, b, c, x[i+13], 12, -40341101);
        c = md5_ff(c, d, a, b, x[i+14], 17, -1502002290);
        b = md5_ff(b, c, d, a, x[i+15], 22,  1236535329);

        a = md5_gg(a, b, c, d, x[i+ 1], 5 , -165796510);
        d = md5_gg(d, a, b, c, x[i+ 6], 9 , -1069501632);
        c = md5_gg(c, d, a, b, x[i+11], 14,  643717713);
        b = md5_gg(b, c, d, a, x[i+ 0], 20, -373897302);
        a = md5_gg(a, b, c, d, x[i+ 5], 5 , -701558691);
        d = md5_gg(d, a, b, c, x[i+10], 9 ,  38016083);
        c = md5_gg(c, d, a, b, x[i+15], 14, -660478335);
        b = md5_gg(b, c, d, a, x[i+ 4], 20, -405537848);
        a = md5_gg(a, b, c, d, x[i+ 9], 5 ,  568446438);
        d = md5_gg(d, a, b, c, x[i+14], 9 , -1019803690);
        c = md5_gg(c, d, a, b, x[i+ 3], 14, -187363961);
        b = md5_gg(b, c, d, a, x[i+ 8], 20,  1163531501);
        a = md5_gg(a, b, c, d, x[i+13], 5 , -1444681467);
        d = md5_gg(d, a, b, c, x[i+ 2], 9 , -51403784);
        c = md5_gg(c, d, a, b, x[i+ 7], 14,  1735328473);
        b = md5_gg(b, c, d, a, x[i+12], 20, -1926607734);

        a = md5_hh(a, b, c, d, x[i+ 5], 4 , -378558);
        d = md5_hh(d, a, b, c, x[i+ 8], 11, -2022574463);
        c = md5_hh(c, d, a, b, x[i+11], 16,  1839030562);
        b = md5_hh(b, c, d, a, x[i+14], 23, -35309556);
        a = md5_hh(a, b, c, d, x[i+ 1], 4 , -1530992060);
        d = md5_hh(d, a, b, c, x[i+ 4], 11,  1272893353);
        c = md5_hh(c, d, a, b, x[i+ 7], 16, -155497632);
        b = md5_hh(b, c, d, a, x[i+10], 23, -1094730640);
        a = md5_hh(a, b, c, d, x[i+13], 4 ,  681279174);
        d = md5_hh(d, a, b, c, x[i+ 0], 11, -358537222);
        c = md5_hh(c, d, a, b, x[i+ 3], 16, -722521979);
        b = md5_hh(b, c, d, a, x[i+ 6], 23,  76029189);
        a = md5_hh(a, b, c, d, x[i+ 9], 4 , -640364487);
        d = md5_hh(d, a, b, c, x[i+12], 11, -421815835);
        c = md5_hh(c, d, a, b, x[i+15], 16,  530742520);
        b = md5_hh(b, c, d, a, x[i+ 2], 23, -995338651);

        a = md5_ii(a, b, c, d, x[i+ 0], 6 , -198630844);
        d = md5_ii(d, a, b, c, x[i+ 7], 10,  1126891415);
        c = md5_ii(c, d, a, b, x[i+14], 15, -1416354905);
        b = md5_ii(b, c, d, a, x[i+ 5], 21, -57434055);
        a = md5_ii(a, b, c, d, x[i+12], 6 ,  1700485571);
        d = md5_ii(d, a, b, c, x[i+ 3], 10, -1894986606);
        c = md5_ii(c, d, a, b, x[i+10], 15, -1051523);
        b = md5_ii(b, c, d, a, x[i+ 1], 21, -2054922799);
        a = md5_ii(a, b, c, d, x[i+ 8], 6 ,  1873313359);
        d = md5_ii(d, a, b, c, x[i+15], 10, -30611744);
        c = md5_ii(c, d, a, b, x[i+ 6], 15, -1560198380);
        b = md5_ii(b, c, d, a, x[i+13], 21,  1309151649);
        a = md5_ii(a, b, c, d, x[i+ 4], 6 , -145523070);
        d = md5_ii(d, a, b, c, x[i+11], 10, -1120210379);
        c = md5_ii(c, d, a, b, x[i+ 2], 15,  718787259);
        b = md5_ii(b, c, d, a, x[i+ 9], 21, -343485551);

        a = safe_add(a, olda);
        b = safe_add(b, oldb);
        c = safe_add(c, oldc);
        d = safe_add(d, oldd);
    }
    return Array(a, b, c, d);

}

/*
 * These functions implement the four basic operations the algorithm uses.
 */
function md5_cmn(q, a, b, x, s, t)
{
    return safe_add(bit_rol(safe_add(safe_add(a, q), safe_add(x, t)), s),b);
}
function md5_ff(a, b, c, d, x, s, t)
{
    return md5_cmn((b & c) | ((~b) & d), a, b, x, s, t);
}
function md5_gg(a, b, c, d, x, s, t)
{
    return md5_cmn((b & d) | (c & (~d)), a, b, x, s, t);
}
function md5_hh(a, b, c, d, x, s, t)
{
    return md5_cmn(b ^ c ^ d, a, b, x, s, t);
}
function md5_ii(a, b, c, d, x, s, t)
{
    return md5_cmn(c ^ (b | (~d)), a, b, x, s, t);
}

/*
 * Calculate the HMAC-MD5, of a key and some data
 */
function core_hmac_md5(key, data)
{
    var bkey = str2binl(key);
    if(bkey.length > 16) bkey = core_md5(bkey, key.length * chrsz);

    var ipad = Array(16), opad = Array(16);
    for(var i = 0; i < 16; i++)
    {
        ipad[i] = bkey[i] ^ 0x36363636;
        opad[i] = bkey[i] ^ 0x5C5C5C5C;
    }

    var hash = core_md5(ipad.concat(str2binl(data)), 512 + data.length * chrsz);
    return core_md5(opad.concat(hash), 512 + 128);
}

/*
 * Add integers, wrapping at 2^32. This uses 16-bit operations internally
 * to work around bugs in some JS interpreters.
 */
function safe_add(x, y)
{
    var lsw = (x & 0xFFFF) + (y & 0xFFFF);
    var msw = (x >> 16) + (y >> 16) + (lsw >> 16);
    return (msw << 16) | (lsw & 0xFFFF);
}

/*
 * Bitwise rotate a 32-bit number to the left.
 */
function bit_rol(num, cnt)
{
    return (num << cnt) | (num >>> (32 - cnt));
}

/*
 * Convert a string to an array of little-endian words
 * If chrsz is ASCII, characters >255 have their hi-byte silently ignored.
 */
function str2binl(str)
{
    var bin = Array();
    var mask = (1 << chrsz) - 1;
    for(var i = 0; i < str.length * chrsz; i += chrsz)
        bin[i>>5] |= (str.charCodeAt(i / chrsz) & mask) << (i%32);
    return bin;
}

/*
 * Convert an array of little-endian words to a string
 */
function binl2str(bin)
{
    var str = "";
    var mask = (1 << chrsz) - 1;
    for(var i = 0; i < bin.length * 32; i += chrsz)
        str += String.fromCharCode((bin[i>>5] >>> (i % 32)) & mask);
    return str;
}

/*
 * Convert an array of little-endian words to a hex string.
 */
function binl2hex(binarray)
{
    var hex_tab = hexcase ? "0123456789ABCDEF" : "0123456789abcdef";
    var str = "";
    for(var i = 0; i < binarray.length * 4; i++)
    {
        str += hex_tab.charAt((binarray[i>>2] >> ((i%4)*8+4)) & 0xF) +
            hex_tab.charAt((binarray[i>>2] >> ((i%4)*8  )) & 0xF);
    }
    return str;
}

/*
 * Convert an array of little-endian words to a base-64 string
 */
function binl2b64(binarray)
{
    var tab = "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/";
    var str = "";
    for(var i = 0; i < binarray.length * 4; i += 3)
    {
        var triplet = (((binarray[i   >> 2] >> 8 * ( i   %4)) & 0xFF) << 16)
            | (((binarray[i+1 >> 2] >> 8 * ((i+1)%4)) & 0xFF) << 8 )
            |  ((binarray[i+2 >> 2] >> 8 * ((i+2)%4)) & 0xFF);
        for(var j = 0; j < 4; j++)
        {
            if(i * 8 + j * 6 > binarray.length * 32) str += b64pad;
            else str += tab.charAt((triplet >> 6*(3-j)) & 0x3F);
        }
    }
    return str;
}

/*
sha1.js*/
/*
 *   A   JavaScript   implementation   of   the   Secure   Hash   Algorithm,   SHA-1,   as   defined
 *   in   FIPS   PUB   180-1
 *   Version   2.1-BETA   Copyright   Paul   Johnston   2000   -   2002.
 *   Other   contributors:   Greg   Holt,   Andrew   Kepert,   Ydnar,   Lostinet
 *   Distributed   under   the   BSD   License
 *   See   http://pajhome.org.uk/crypt/md5   for   details.
 */
/*
 *   Configurable   variables.   You   may   need   to   tweak   these   to   be   compatible   with
 *   the   server-side,   but   the   defaults   work   in   most   cases.
 */
var hexcase = 0; /*   hex   output   format.   0   -   lowercase;   1   -   uppercase                 */
var b64pad = ""; /*   base-64   pad   character.   "="   for   strict   RFC   compliance       */
var chrsz = 8; /*   bits   per   input   character.   8   -   ASCII;   16   -   Unicode             */

/*
 *   These   are   the   functions   you'll   usually   want   to   call
 *   They   take   string   arguments   and   return   either   hex   or   base-64   encoded   strings
 */
function hex_sha1(s) {
    return binb2hex(core_sha1(str2binb(s), s.length * chrsz));
}

function b64_sha1(s) {
    return binb2b64(core_sha1(str2binb(s), s.length * chrsz));
}

function str_sha1(s) {
    return binb2str(core_sha1(str2binb(s), s.length * chrsz));
}

function hex_hmac_sha1(key, data) {
    return binb2hex(core_hmac_sha1(key, data));
}

function b64_hmac_sha1(key, data) {
    return binb2b64(core_hmac_sha1(key, data));
}

function str_hmac_sha1(key, data) {
    return binb2str(core_hmac_sha1(key, data));
}

/*
 *   Perform   a   simple   self-test   to   see   if   the   VM   is   working
 */
function sha1_vm_test() {
    return hex_sha1("abc") == "a9993e364706816aba3e25717850c26c9cd0d89d";
}

/*
 *   Calculate   the   SHA-1   of   an   array   of   big-endian   words,   and   a   bit   length
 */
function core_sha1(x, len) {
    /*   append   padding   */
    x[len >> 5] |= 0x80 << (24 - len % 32);
    x[((len + 64 >> 9) << 4) + 15] = len;

    var w = Array(80);
    var a = 1732584193;
    var b = -271733879;
    var c = -1732584194;
    var d = 271733878;
    var e = -1009589776;

    for (var i = 0; i < x.length; i += 16) {
        var olda = a;
        var oldb = b;
        var oldc = c;
        var oldd = d;
        var olde = e;

        for (var j = 0; j < 80; j++) {
            if (j < 16) w[j] = x[i + j];
            else w[j] = rol(w[j - 3] ^ w[j - 8] ^ w[j - 14] ^ w[j - 16], 1);
            var t = safe_add(safe_add(rol(a, 5), sha1_ft(j, b, c, d)), safe_add(safe_add(e, w[j]), sha1_kt(j)));
            e = d;
            d = c;
            c = rol(b, 30);
            b = a;
            a = t;
        }

        a = safe_add(a, olda);
        b = safe_add(b, oldb);
        c = safe_add(c, oldc);
        d = safe_add(d, oldd);
        e = safe_add(e, olde);
    }
    return Array(a, b, c, d, e);

}

/*
 *   Perform   the   appropriate   triplet   combination   function   for   the   current
 *   iteration
 */
function sha1_ft(t, b, c, d) {
    if (t < 20) return (b & c) | ((~b) & d);
    if (t < 40) return b ^ c ^ d;
    if (t < 60) return (b & c) | (b & d) | (c & d);
    return b ^ c ^ d;
}

/*
 *   Determine   the   appropriate   additive   constant   for   the   current   iteration
 */
function sha1_kt(t) {
    return (t < 20) ? 1518500249 : (t < 40) ? 1859775393 : (t < 60) ? -1894007588 : -899497514;
}

/*
 *   Calculate   the   HMAC-SHA1   of   a   key   and   some   data
 */
function core_hmac_sha1(key, data) {
    var bkey = str2binb(key);
    if (bkey.length > 16) bkey = core_sha1(bkey, key.length * chrsz);

    var ipad = Array(16),
        opad = Array(16);
    for (var i = 0; i < 16; i++) {
        ipad[i] = bkey[i] ^ 0x36363636;
        opad[i] = bkey[i] ^ 0x5C5C5C5C;
    }

    var hash = core_sha1(ipad.concat(str2binb(data)), 512 + data.length * chrsz);
    return core_sha1(opad.concat(hash), 512 + 160);
}

/*
 *   Add   integers,   wrapping   at   2^32.   This   uses   16-bit   operations   internally
 *   to   work   around   bugs   in   some   JS   interpreters.
 */
function safe_add(x, y) {
    var lsw = (x & 0xFFFF) + (y & 0xFFFF);
    var msw = (x >> 16) + (y >> 16) + (lsw >> 16);
    return (msw << 16) | (lsw & 0xFFFF);
}

/*
 *   Bitwise   rotate   a   32-bit   number   to   the   left.
 */
function rol(num, cnt) {
    return (num << cnt) | (num >>> (32 - cnt));
}

/*
 *   Convert   an   8-bit   or   16-bit   string   to   an   array   of   big-endian   words
 *   In   8-bit   function,   characters   >255   have   their   hi-byte   silently   ignored.
 */
function str2binb(str) {
    var bin = Array();
    var mask = (1 << chrsz) - 1;
    for (var i = 0; i < str.length * chrsz; i += chrsz)
        bin[i >> 5] |= (str.charCodeAt(i / chrsz) & mask) << (24 - i % 32);
    return bin;
}

/*
 *   Convert   an   array   of   big-endian   words   to   a   string
 */
function binb2str(bin) {
    var str = "";
    var mask = (1 << chrsz) - 1;
    for (var i = 0; i < bin.length * 32; i += chrsz)
        str += String.fromCharCode((bin[i >> 5] >>> (24 - i % 32)) & mask);
    return str;
}

/*
 *   Convert   an   array   of   big-endian   words   to   a   hex   string.
 */
function binb2hex(binarray) {
    var hex_tab = hexcase ? "0123456789ABCDEF" : "0123456789abcdef";
    var str = "";
    for (var i = 0; i < binarray.length * 4; i++) {
        str += hex_tab.charAt((binarray[i >> 2] >> ((3 - i % 4) * 8 + 4)) & 0xF) + hex_tab.charAt((binarray[i >> 2] >> ((3 - i % 4) * 8)) & 0xF);
    }
    return str;
}

/*
 *   Convert   an   array   of   big-endian   words   to   a   base-64   string
 */
function binb2b64(binarray) {
    var tab = "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/";
    var str = "";
    for (var i = 0; i < binarray.length * 4; i += 3) {
        var triplet = (((binarray[i >> 2] >> 8 * (3 - i % 4)) & 0xFF) << 16) | (((binarray[i + 1 >> 2] >> 8 * (3 - (i + 1) % 4)) & 0xFF) << 8) | ((binarray[i + 2 >> 2] >> 8 * (3 - (i + 2) % 4)) & 0xFF);
        for (var j = 0; j < 4; j++) {
            if (i * 8 + j * 6 > binarray.length * 32) str += b64pad;
            else str += tab.charAt((triplet >> 6 * (3 - j)) & 0x3F);
        }
    }
    return str;
}

/*
base64.js*/
function Base64() {

    // private property
    _keyStr = "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/=";

    // public method for encoding
    this.encode = function (input) {
        var output = "";
        var chr1, chr2, chr3, enc1, enc2, enc3, enc4;
        var i = 0;
        input = _utf8_encode(input);
        while (i < input.length) {
            chr1 = input.charCodeAt(i++);
            chr2 = input.charCodeAt(i++);
            chr3 = input.charCodeAt(i++);
            enc1 = chr1 >> 2;
            enc2 = ((chr1 & 3) << 4) | (chr2 >> 4);
            enc3 = ((chr2 & 15) << 2) | (chr3 >> 6);
            enc4 = chr3 & 63;
            if (isNaN(chr2)) {
                enc3 = enc4 = 64;
            } else if (isNaN(chr3)) {
                enc4 = 64;
            }
            output = output +
                _keyStr.charAt(enc1) + _keyStr.charAt(enc2) +
                _keyStr.charAt(enc3) + _keyStr.charAt(enc4);
        }
        return output;
    }

    // public method for decoding
    this.decode = function (input) {
        var output = "";
        var chr1, chr2, chr3;
        var enc1, enc2, enc3, enc4;
        var i = 0;
        input = input.replace(/[^A-Za-z0-9\+\/\=]/g, "");
        while (i < input.length) {
            enc1 = _keyStr.indexOf(input.charAt(i++));
            enc2 = _keyStr.indexOf(input.charAt(i++));
            enc3 = _keyStr.indexOf(input.charAt(i++));
            enc4 = _keyStr.indexOf(input.charAt(i++));
            chr1 = (enc1 << 2) | (enc2 >> 4);
            chr2 = ((enc2 & 15) << 4) | (enc3 >> 2);
            chr3 = ((enc3 & 3) << 6) | enc4;
            output = output + String.fromCharCode(chr1);
            if (enc3 != 64) {
                output = output + String.fromCharCode(chr2);
            }
            if (enc4 != 64) {
                output = output + String.fromCharCode(chr3);
            }
        }
        output = _utf8_decode(output);
        return output;
    }

    // private method for UTF-8 encoding
    _utf8_encode = function (string) {
        string = string.replace(/\r\n/g,"\n");
        var utftext = "";
        for (var n = 0; n < string.length; n++) {
            var c = string.charCodeAt(n);
            if (c < 128) {
                utftext += String.fromCharCode(c);
            } else if((c > 127) && (c < 2048)) {
                utftext += String.fromCharCode((c >> 6) | 192);
                utftext += String.fromCharCode((c & 63) | 128);
            } else {
                utftext += String.fromCharCode((c >> 12) | 224);
                utftext += String.fromCharCode(((c >> 6) & 63) | 128);
                utftext += String.fromCharCode((c & 63) | 128);
            }

        }
        return utftext;
    }

    // private method for UTF-8 decoding
    _utf8_decode = function (utftext) {
        var string = "";
        var i = 0;
        var c = c1 = c2 = 0;
        while ( i < utftext.length ) {
            c = utftext.charCodeAt(i);
            if (c < 128) {
                string += String.fromCharCode(c);
                i++;
            } else if((c > 191) && (c < 224)) {
                c2 = utftext.charCodeAt(i+1);
                string += String.fromCharCode(((c & 31) << 6) | (c2 & 63));
                i += 2;
            } else {
                c2 = utftext.charCodeAt(i+1);
                c3 = utftext.charCodeAt(i+2);
                string += String.fromCharCode(((c & 15) << 12) | ((c2 & 63) << 6) | (c3 & 63));
                i += 3;
            }
        }
        return string;
    }
}

 

你可能感兴趣的:(学习笔记)