今日头条ajax技术内as ,cp，_cp_signature参数分析、破解及python爬取频道数据
相信很多人在爬今日头条的时候就遇到了一个难题，就是找到了消息头后，有3个加密的参数（as ,cp，_cp_signature），如下图：
找到的请求URL是：
https://www.toutiao.com/api/pc/feed/?max_behot_time=1535349295&category=__all__&utm_source=toutiao&widen=1&tadrequire=false&as=A1F56BD8E379234&cp=5B831962B354CE1&_signature=PRRukBAUZp609VcKGFWglD0Ubo
以上共有
max_behot_time；category；utm_source；widen；tadrequir；as；cp；_signature；8个参数；
max_behot_time 可以看出是10位数字的时间戳；
category 是对应的频道名，可以在首页找到
utm_source 固定是toutiao,widen固定是1，tadrequire固定是false，剩下的就是as,cp,_cp_signature三个参数了；
要破解这三个参数，我们需要找下JS的代码里是否有相关信息，于是通过搜索“_signature”找到了对应的JS加密代码：
function e(t) {
var e = ascp.getHoney()
, i = "";
window.TAC && (i = TAC.sign("refresh" === t ? 0 : r.params.max_behot_time_tmp)),
r.params = _.extend({}, r.params, {
as: e.as,
cp: e.cp,
max_behot_time: "refresh" === t ? 0 : r.params.max_behot_time_tmp,
_signature: i
}可以看到as和cp是由ascp.getHoney函数传递的，我们继续找下getHoney这个函数；
!function(t) {
var e = {};
e.getHoney = function() {
var t = Math.floor((new Date).getTime() / 1e3)
, e = t.toString(16).toUpperCase()
, i = md5(t).toString().toUpperCase();
if (8 != e.length)
return {
as: "479BB4B7254C150",
cp: "7E0AC8874BB0985"
};
for (var n = i.slice(0, 5), a = i.slice(-5), s = "", o = 0; 5 > o; o++)
s += n[o] + e[o];
for (var r = "", c = 0; 5 > c; c++)
r += e[c + 3] + a[c];
return {
as: "A1" + s + e.slice(-3),
cp: e.slice(0, 3) + r + "E1"
}
}
,
t.ascp = e
}(window, document)根据以上JS代码，可以写成python代码：
def getHoney(): #####根据JS脚本破解as ,cp
t = int(time.time()) #获取当前时间
#t=1534389637
#print(t)
e =str('%X' % t) ##格式化时间
#print(e)
m1 = hashlib.md5() ##MD5加密
m1.update(str(t).encode(encoding='utf-8')) ##转化格式
i = str(m1.hexdigest()).upper() ####转化大写
#print(i)
n=i[0:5] ##获取前5位字符
a=i[-5:] ##获取后5位字符
s=''
r=''
for x in range(0,5): ##交叉组合字符
s+=n[x]+e[x]
r+=e[x+3]+a[x]
eas='A1'+ s+ e[-3:]
ecp=e[0:3]+r+'E1'
#print(eas)
#print(ecp)
return eas,ecp 接下来就是破解_cp_signature，经过搜索找不到对应的JS脚本，百度很久后找到了个大牛（太阳雨2012 ）自己破解的JS代码，
navigator = {
// WT-JS_DEBUG v1.7.5 - NLiger2018
appCodeName: "Mozilla",
appMinorVersion: "0",
appName: "Netscape",
appVersion: "5.0 (Windows NT 10.0; WOW64; Trident/7.0; .NET4.0C; .NET4.0E; .NET CLR 2.0.50727; .NET CLR 3.0.30729; .NET CLR 3.5.30729; InfoPath.3; rv:11.0) like Gecko",
browserLanguage: "zh-CN",
cookieEnabled: true,
cpuClass: "x86",
language: "zh-CN",
maxTouchPoints: 0,
msManipulationViewsEnabled: true,
msMaxTouchPoints: 0,
msPointerEnabled: true,
onLine: true,
platform: "Win32",
pointerEnabled: true,
product: "Gecko",
systemLanguage: "zh-CN",
userAgent: "Mozilla/5.0 (Windows NT 10.0; WOW64; Trident/7.0; .NET4.0C; .NET4.0E; .NET CLR 2.0.50727; .NET CLR 3.0.30729; .NET CLR 3.5.30729; InfoPath.3; rv:11.0) like Gecko",
userLanguage: "zh-CN",
vendor: "",
vendorSub: "",
webdriver: false
}, window = this, window.navigator = navigator;
if (typeof JSON !== "object") {
JSON = {};
}(function () {
"use strict";
var rx_one = /^[\],:{}\s]*$/;
var rx_two = /\\(?:["\\\/bfnrt]|u[0-9a-fA-F]{4})/g;
var rx_three = /"[^"\\\n\r]*"|true|false|null|-?\d+(?:\.\d*)?(?:[eE][+\-]?\d+)?/g;
var rx_four = /(?:^|:|,)(?:\s*\[)+/g;
var rx_escapable = /[\\"\u0000-\u001f\u007f-\u009f\u00ad\u0600-\u0604\u070f\u17b4\u17b5\u200c-\u200f\u2028-\u202f\u2060-\u206f\ufeff\ufff0-\uffff]/g;
var rx_dangerous = /[\u0000\u00ad\u0600-\u0604\u070f\u17b4\u17b5\u200c-\u200f\u2028-\u202f\u2060-\u206f\ufeff\ufff0-\uffff]/g;
function f(n) {
return n < 10 ? "0" + n : n;
}
function this_value() {
return this.valueOf();
}
if (typeof Date.prototype.toJSON !== "function") {
Date.prototype.toJSON = function () {
return isFinite(this.valueOf()) ? this.getUTCFullYear() + "-" + f(this.getUTCMonth() + 1) + "-" + f(this.getUTCDate()) + "T" + f(this.getUTCHours()) + ":" + f(this.getUTCMinutes()) + ":" + f(this.getUTCSeconds()) + "Z" : null;
};
Boolean.prototype.toJSON = this_value;
Number.prototype.toJSON = this_value;
String.prototype.toJSON = this_value;
}
var gap;
var indent;
var meta;
var rep;
function quote(string) {
rx_escapable.lastIndex = 0;
return rx_escapable.test(string) ? "\"" + string.replace(rx_escapable, function (a) {
var c = meta[a];
return typeof c === "string" ? c : "\\u" + ("0000" + a.charCodeAt(0).toString(16)).slice(-4);
}) + "\"" : "\"" + string + "\"";
}
function str(key, holder) {
var i;
var k;
var v;
var length;
var mind = gap;
var partial;
var value = holder[key];
if (value && typeof value === "object" && typeof value.toJSON === "function") {
value = value.toJSON(key);
}
if (typeof rep === "function") {
value = rep.call(holder, key, value);
}
switch (typeof value) {
case "string":
return quote(value);
case "number":
return isFinite(value) ? String(value) : "null";
case "boolean":
case "null":
return String(value);
case "object":
if (!value) {
return "null";
}
gap += indent;
partial = [];
if (Object.prototype.toString.apply(value) === "[object Array]") {
length = value.length;
for (i = 0; i < length; i += 1) {
partial[i] = str(i, value) || "null";
}
v = partial.length === 0 ? "[]" : gap ? "[\n" + gap + partial.join(",\n" + gap) + "\n" + mind + "]" : "[" + partial.join(",") + "]";
gap = mind;
return v;
}
if (rep && typeof rep === "object") {
length = rep.length;
for (i = 0; i < length; i += 1) {
if (typeof rep[i] === "string") {
k = rep[i];
v = str(k, value);
if (v) {
partial.push(quote(k) + (gap ? ": " : ":") + v);
}
}
}
} else {
for (k in value) {
if (Object.prototype.hasOwnProperty.call(value, k)) {
v = str(k, value);
if (v) {
partial.push(quote(k) + (gap ? ": " : ":") + v);
}
}
}
}
v = partial.length === 0 ? "{}" : gap ? "{\n" + gap + partial.join(",\n" + gap) + "\n" + mind + "}" : "{" + partial.join(",") + "}";
gap = mind;
return v;
}
}
if (typeof JSON.stringify !== "function") {
meta = {
"\b": "\\b",
"\t": "\\t",
"\n": "\\n",
"\f": "\\f",
"\r": "\\r",
"\"": "\\\"",
"\\": "\\\\"
};
JSON.stringify = function (value, replacer, space) {
var i;
gap = "";
indent = "";
if (typeof space === "number") {
for (i = 0; i < space; i += 1) {
indent += " ";
}
} else if (typeof space === "string") {
indent = space;
}
rep = replacer;
if (replacer && typeof replacer !== "function" && (typeof replacer !== "object" || typeof replacer.length !== "number")) {
throw new Error("JSON.stringify");
}
return str("", {
"": value
});
};
}
if (typeof JSON.parse !== "function") {
JSON.parse = function (text, reviver) {
var j;
function walk(holder, key) {
var k;
var v;
var value = holder[key];
if (value && typeof value === "object") {
for (k in value) {
if (Object.prototype.hasOwnProperty.call(value, k)) {
v = walk(value, k);
if (v !== undefined) {
value[k] = v;
} else {
delete value[k];
}
}
}
}
return reviver.call(holder, key, value);
}
text = String(text);
rx_dangerous.lastIndex = 0;
if (rx_dangerous.test(text)) {
text = text.replace(rx_dangerous, function (a) {
return "\\u" + ("0000" + a.charCodeAt(0).toString(16)).slice(-4);
});
}
if (rx_one.test(text.replace(rx_two, "@").replace(rx_three, "]").replace(rx_four, ""))) {
j = eval("(" + text + ")");
return (typeof reviver === "function") ? walk({
"": j
}, "") : j;
}
throw new SyntaxError("JSON.parse");
};
}
}());
var CryptoJS = CryptoJS || (function (Math, undefined) {
var C = {};
var C_lib = C.lib = {};
var Base = C_lib.Base = (function () {
function F() {};
return {
extend: function (overrides) {
F.prototype = this;
var subtype = new F();
if (overrides) {
subtype.mixIn(overrides);
}
if (!subtype.hasOwnProperty('init') || this.init === subtype.init) {
subtype.init = function () {
subtype.$super.init.apply(this, arguments);
};
}
subtype.init.prototype = subtype;
subtype.$super = this;
return subtype;
}, create: function () {
var instance = this.extend();
instance.init.apply(instance, arguments);
return instance;
}, init: function () {}, mixIn: function (properties) {
for (var propertyName in properties) {
if (properties.hasOwnProperty(propertyName)) {
this[propertyName] = properties[propertyName];
}
}
if (properties.hasOwnProperty('toString')) {
this.toString = properties.toString;
}
}, clone: function () {
return this.init.prototype.extend(this);
}
};
}());
var WordArray = C_lib.WordArray = Base.extend({
init: function (words, sigBytes) {
words = this.words = words || [];
if (sigBytes != undefined) {
this.sigBytes = sigBytes;
} else {
this.sigBytes = words.length * 4;
}
}, toString: function (encoder) {
return (encoder || Hex).stringify(this);
}, concat: function (wordArray) {
var thisWords = this.words;
var thatWords = wordArray.words;
var thisSigBytes = this.sigBytes;
var thatSigBytes = wordArray.sigBytes;
this.clamp();
if (thisSigBytes % 4) {
for (var i = 0; i < thatSigBytes; i++) {
var thatByte = (thatWords[i >>> 2] >>> (24 - (i % 4) * 8)) & 0xff;
thisWords[(thisSigBytes + i) >>> 2] |= thatByte << (24 - ((thisSigBytes + i) % 4) * 8);
}
} else if (thatWords.length > 0xffff) {
for (var i = 0; i < thatSigBytes; i += 4) {
thisWords[(thisSigBytes + i) >>> 2] = thatWords[i >>> 2];
}
} else {
thisWords.push.apply(thisWords, thatWords);
}
this.sigBytes += thatSigBytes;
return this;
}, clamp: function () {
var words = this.words;
var sigBytes = this.sigBytes;
words[sigBytes >>> 2] &= 0xffffffff << (32 - (sigBytes % 4) * 8);
words.length = Math.ceil(sigBytes / 4);
}, clone: function () {
var clone = Base.clone.call(this);
clone.words = this.words.slice(0);
return clone;
}, random: function (nBytes) {
var words = [];
var r = (function (m_w) {
var m_w = m_w;
var m_z = 0x3ade68b1;
var mask = 0xffffffff;
return function () {
m_z = (0x9069 * (m_z & 0xFFFF) + (m_z >> 0x10)) & mask;
m_w = (0x4650 * (m_w & 0xFFFF) + (m_w >> 0x10)) & mask;
var result = ((m_z << 0x10) + m_w) & mask;
result /= 0x100000000;
result += 0.5;
return result * (Math.random() > .5 ? 1 : -1);
}
});
for (var i = 0, rcache; i < nBytes; i += 4) {
var _r = r((rcache || Math.random()) * 0x100000000);
rcache = _r() * 0x3ade67b7;
words.push((_r() * 0x100000000) | 0);
}
return new WordArray.init(words, nBytes);
}
});
var C_enc = C.enc = {};
var Hex = C_enc.Hex = {
stringify: function (wordArray) {
var words = wordArray.words;
var sigBytes = wordArray.sigBytes;
var hexChars = [];
for (var i = 0; i < sigBytes; i++) {
var bite = (words[i >>> 2] >>> (24 - (i % 4) * 8)) & 0xff;
hexChars.push((bite >>> 4).toString(16));
hexChars.push((bite & 0x0f).toString(16));
}
return hexChars.join('');
}, parse: function (hexStr) {
var hexStrLength = hexStr.length;
var words = [];
for (var i = 0; i < hexStrLength; i += 2) {
words[i >>> 3] |= parseInt(hexStr.substr(i, 2), 16) << (24 - (i % 8) * 4);
}
return new WordArray.init(words, hexStrLength / 2);
}
};
var Latin1 = C_enc.Latin1 = {
stringify: function (wordArray) {
var words = wordArray.words;
var sigBytes = wordArray.sigBytes;
var latin1Chars = [];
for (var i = 0; i < sigBytes; i++) {
var bite = (words[i >>> 2] >>> (24 - (i % 4) * 8)) & 0xff;
latin1Chars.push(String.fromCharCode(bite));
}
return latin1Chars.join('');
}, parse: function (latin1Str) {
var latin1StrLength = latin1Str.length;
var words = [];
for (var i = 0; i < latin1StrLength; i++) {
words[i >>> 2] |= (latin1Str.charCodeAt(i) & 0xff) << (24 - (i % 4) * 8);
}
return new WordArray.init(words, latin1StrLength);
}
};
var Utf8 = C_enc.Utf8 = {
stringify: function (wordArray) {
try {
return decodeURIComponent(escape(Latin1.stringify(wordArray)));
} catch (e) {
throw new Error('Malformed UTF-8 data');
}
}, parse: function (utf8Str) {
return Latin1.parse(unescape(encodeURIComponent(utf8Str)));
}
};
var BufferedBlockAlgorithm = C_lib.BufferedBlockAlgorithm = Base.extend({
reset: function () {
this._data = new WordArray.init();
this._nDataBytes = 0;
}, _append: function (data) {
if (typeof data == 'string') {
data = Utf8.parse(data);
}
this._data.concat(data);
this._nDataBytes += data.sigBytes;
}, _process: function (doFlush) {
var data = this._data;
var dataWords = data.words;
var dataSigBytes = data.sigBytes;
var blockSize = this.blockSize;
var blockSizeBytes = blockSize * 4;
var nBlocksReady = dataSigBytes / blockSizeBytes;
if (doFlush) {
nBlocksReady = Math.ceil(nBlocksReady);
} else {
nBlocksReady = Math.max((nBlocksReady | 0) - this._minBufferSize, 0);
}
var nWordsReady = nBlocksReady * blockSize;
var nBytesReady = Math.min(nWordsReady * 4, dataSigBytes);
if (nWordsReady) {
for (var offset = 0; offset < nWordsReady; offset += blockSize) {
this._doProcessBlock(dataWords, offset);
}
var processedWords = dataWords.splice(0, nWordsReady);
data.sigBytes -= nBytesReady;
}
return new WordArray.init(processedWords, nBytesReady);
}, clone: function () {
var clone = Base.clone.call(this);
clone._data = this._data.clone();
return clone;
}, _minBufferSize: 0
});
var Hasher = C_lib.Hasher = BufferedBlockAlgorithm.extend({
cfg: Base.extend(),
init: function (cfg) {
this.cfg = this.cfg.extend(cfg);
this.reset();
}, reset: function () {
BufferedBlockAlgorithm.reset.call(this);
this._doReset();
}, update: function (messageUpdate) {
this._append(messageUpdate);
this._process();
return this;
}, finalize: function (messageUpdate) {
if (messageUpdate) {
this._append(messageUpdate);
}
var hash = this._doFinalize();
return hash;
}, blockSize: 512 / 32,
_createHelper: function (hasher) {
return function (message, cfg) {
return new hasher.init(cfg).finalize(message);
};
}, _createHmacHelper: function (hasher) {
return function (message, key) {
return new C_algo.HMAC.init(hasher, key).finalize(message);
};
}
});
var C_algo = C.algo = {};
return C;
}(Math));
(function (Math) {
var C = CryptoJS;
var C_lib = C.lib;
var WordArray = C_lib.WordArray;
var Hasher = C_lib.Hasher;
var C_algo = C.algo;
var T = [];
(function () {
for (var i = 0; i < 64; i++) {
T[i] = (Math.abs(Math.sin(i + 1)) * 0x100000000) | 0;
}
}());
var MD5 = C_algo.MD5 = Hasher.extend({
_doReset: function () {
this._hash = new WordArray.init([0x67452301, 0xefcdab89, 0x98badcfe, 0x10325476]);
}, _doProcessBlock: function (M, offset) {
for (var i = 0; i < 16; i++) {
var offset_i = offset + i;
var M_offset_i = M[offset_i];
M[offset_i] = ((((M_offset_i << 8) | (M_offset_i >>> 24)) & 0x00ff00ff) | (((M_offset_i << 24) | (M_offset_i >>> 8)) & 0xff00ff00));
}
var H = this._hash.words;
var M_offset_0 = M[offset + 0];
var M_offset_1 = M[offset + 1];
var M_offset_2 = M[offset + 2];
var M_offset_3 = M[offset + 3];
var M_offset_4 = M[offset + 4];
var M_offset_5 = M[offset + 5];
var M_offset_6 = M[offset + 6];
var M_offset_7 = M[offset + 7];
var M_offset_8 = M[offset + 8];
var M_offset_9 = M[offset + 9];
var M_offset_10 = M[offset + 10];
var M_offset_11 = M[offset + 11];
var M_offset_12 = M[offset + 12];
var M_offset_13 = M[offset + 13];
var M_offset_14 = M[offset + 14];
var M_offset_15 = M[offset + 15];
var a = H[0];
var b = H[1];
var c = H[2];
var d = H[3];
a = FF(a, b, c, d, M_offset_0, 7, T[0]);
d = FF(d, a, b, c, M_offset_1, 12, T[1]);
c = FF(c, d, a, b, M_offset_2, 17, T[2]);
b = FF(b, c, d, a, M_offset_3, 22, T[3]);
a = FF(a, b, c, d, M_offset_4, 7, T[4]);
d = FF(d, a, b, c, M_offset_5, 12, T[5]);
c = FF(c, d, a, b, M_offset_6, 17, T[6]);
b = FF(b, c, d, a, M_offset_7, 22, T[7]);
a = FF(a, b, c, d, M_offset_8, 7, T[8]);
d = FF(d, a, b, c, M_offset_9, 12, T[9]);
c = FF(c, d, a, b, M_offset_10, 17, T[10]);
b = FF(b, c, d, a, M_offset_11, 22, T[11]);
a = FF(a, b, c, d, M_offset_12, 7, T[12]);
d = FF(d, a, b, c, M_offset_13, 12, T[13]);
c = FF(c, d, a, b, M_offset_14, 17, T[14]);
b = FF(b, c, d, a, M_offset_15, 22, T[15]);
a = GG(a, b, c, d, M_offset_1, 5, T[16]);
d = GG(d, a, b, c, M_offset_6, 9, T[17]);
c = GG(c, d, a, b, M_offset_11, 14, T[18]);
b = GG(b, c, d, a, M_offset_0, 20, T[19]);
a = GG(a, b, c, d, M_offset_5, 5, T[20]);
d = GG(d, a, b, c, M_offset_10, 9, T[21]);
c = GG(c, d, a, b, M_offset_15, 14, T[22]);
b = GG(b, c, d, a, M_offset_4, 20, T[23]);
a = GG(a, b, c, d, M_offset_9, 5, T[24]);
d = GG(d, a, b, c, M_offset_14, 9, T[25]);
c = GG(c, d, a, b, M_offset_3, 14, T[26]);
b = GG(b, c, d, a, M_offset_8, 20, T[27]);
a = GG(a, b, c, d, M_offset_13, 5, T[28]);
d = GG(d, a, b, c, M_offset_2, 9, T[29]);
c = GG(c, d, a, b, M_offset_7, 14, T[30]);
b = GG(b, c, d, a, M_offset_12, 20, T[31]);
a = HH(a, b, c, d, M_offset_5, 4, T[32]);
d = HH(d, a, b, c, M_offset_8, 11, T[33]);
c = HH(c, d, a, b, M_offset_11, 16, T[34]);
b = HH(b, c, d, a, M_offset_14, 23, T[35]);
a = HH(a, b, c, d, M_offset_1, 4, T[36]);
d = HH(d, a, b, c, M_offset_4, 11, T[37]);
c = HH(c, d, a, b, M_offset_7, 16, T[38]);
b = HH(b, c, d, a, M_offset_10, 23, T[39]);
a = HH(a, b, c, d, M_offset_13, 4, T[40]);
d = HH(d, a, b, c, M_offset_0, 11, T[41]);
c = HH(c, d, a, b, M_offset_3, 16, T[42]);
b = HH(b, c, d, a, M_offset_6, 23, T[43]);
a = HH(a, b, c, d, M_offset_9, 4, T[44]);
d = HH(d, a, b, c, M_offset_12, 11, T[45]);
c = HH(c, d, a, b, M_offset_15, 16, T[46]);
b = HH(b, c, d, a, M_offset_2, 23, T[47]);
a = II(a, b, c, d, M_offset_0, 6, T[48]);
d = II(d, a, b, c, M_offset_7, 10, T[49]);
c = II(c, d, a, b, M_offset_14, 15, T[50]);
b = II(b, c, d, a, M_offset_5, 21, T[51]);
a = II(a, b, c, d, M_offset_12, 6, T[52]);
d = II(d, a, b, c, M_offset_3, 10, T[53]);
c = II(c, d, a, b, M_offset_10, 15, T[54]);
b = II(b, c, d, a, M_offset_1, 21, T[55]);
a = II(a, b, c, d, M_offset_8, 6, T[56]);
d = II(d, a, b, c, M_offset_15, 10, T[57]);
c = II(c, d, a, b, M_offset_6, 15, T[58]);
b = II(b, c, d, a, M_offset_13, 21, T[59]);
a = II(a, b, c, d, M_offset_4, 6, T[60]);
d = II(d, a, b, c, M_offset_11, 10, T[61]);
c = II(c, d, a, b, M_offset_2, 15, T[62]);
b = II(b, c, d, a, M_offset_9, 21, T[63]);
H[0] = (H[0] + a) | 0;
H[1] = (H[1] + b) | 0;
H[2] = (H[2] + c) | 0;
H[3] = (H[3] + d) | 0;
}, _doFinalize: function () {
var data = this._data;
var dataWords = data.words;
var nBitsTotal = this._nDataBytes * 8;
var nBitsLeft = data.sigBytes * 8;
dataWords[nBitsLeft >>> 5] |= 0x80 << (24 - nBitsLeft % 32);
var nBitsTotalH = Math.floor(nBitsTotal / 0x100000000);
var nBitsTotalL = nBitsTotal;
dataWords[(((nBitsLeft + 64) >>> 9) << 4) + 15] = ((((nBitsTotalH << 8) | (nBitsTotalH >>> 24)) & 0x00ff00ff) | (((nBitsTotalH << 24) | (nBitsTotalH >>> 8)) & 0xff00ff00));
dataWords[(((nBitsLeft + 64) >>> 9) << 4) + 14] = ((((nBitsTotalL << 8) | (nBitsTotalL >>> 24)) & 0x00ff00ff) | (((nBitsTotalL << 24) | (nBitsTotalL >>> 8)) & 0xff00ff00));
data.sigBytes = (dataWords.length + 1) * 4;
this._process();
var hash = this._hash;
var H = hash.words;
for (var i = 0; i < 4; i++) {
var H_i = H[i];
H[i] = (((H_i << 8) | (H_i >>> 24)) & 0x00ff00ff) | (((H_i << 24) | (H_i >>> 8)) & 0xff00ff00);
}
return hash;
}, clone: function () {
var clone = Hasher.clone.call(this);
clone._hash = this._hash.clone();
return clone;
}
});
function FF(a, b, c, d, x, s, t) {
var n = a + ((b & c) | (~b & d)) + x + t;
return ((n << s) | (n >>> (32 - s))) + b;
}
function GG(a, b, c, d, x, s, t) {
var n = a + ((b & d) | (c & ~d)) + x + t;
return ((n << s) | (n >>> (32 - s))) + b;
}
function HH(a, b, c, d, x, s, t) {
var n = a + (b ^ c ^ d) + x + t;
return ((n << s) | (n >>> (32 - s))) + b;
}
function II(a, b, c, d, x, s, t) {
var n = a + (c ^ (b | ~d)) + x + t;
return ((n << s) | (n >>> (32 - s))) + b;
}
C.MD5 = Hasher._createHelper(MD5);
C.HmacMD5 = Hasher._createHmacHelper(MD5);
}(Math));
function get_as_cp_signature() {
var getHoney = function () {
var t = Math.floor((new Date).getTime() / 1e3),
e = t.toString(16).toUpperCase(),
i = CryptoJS.MD5(t + '').toString().toUpperCase();
if (8 != e.length) return {
as: "479BB4B7254C150",
cp: "7E0AC8874BB0985"
};
for (var n = i.slice(0, 5), a = i.slice(-5), s = "", o = 0; 5 > o; o++)
s += n.substr(o, 1) + e.substr(o, 1);
for (var r = "", c = 0; 5 > c; c++)
r += e.substr(c + 3, 1) + a.substr(c, 1);
return {
as: "A1" + s + e.slice(-3),
cp: e.slice(0, 3) + r + "E1"
}
}
function e(e, a, r) {
return (b[e] || (b[e] = t("x,y", "return x " + e + " y")))(r, a)
}
function a(e, a, r) {
return (k[r] || (k[r] = t("x,y", "return new x[y](" + Array(r + 1).join(",x[++y]").substr(1) + ")")))(e, a)
}
function r(e, a, r) {
var n, t, s = {},
b = s.d = r ? r.d + 1 : 0;
for (s["$" + b] = s,
t = 0; t < b; t++)
s[n = "$" + t] = r[n];
for (t = 0,
b = s.length = a.length; t < b; t++)
s[t] = a[t];
return c(e, 0, s)
}
function c(t, b, k) {
function u(e) {
v[x++] = e
}
function f() {
return g = t.charCodeAt(b++) - 32,
t.substring(b, b += g)
}
function l() {
try {
y = c(t, b, k)
} catch (e) {
h = e,
y = l
}
}
for (var h, y, d, g, v = [], x = 0;;)
switch (g = t.charCodeAt(b++) - 32) {
case 1:
u(!v[--x]);
break;
case 4:
v[x++] = f();
break;
case 5:
u(function (e) {
var a = 0,
r = e.length;
return function () {
var c = a < r;
return c && u(e[a++]),
c
}
}(v[--x]));
break;
case 6:
y = v[--x],
u(v[--x](y));
break;
case 8:
if (g = t.charCodeAt(b++) - 32,
l(),
b += g,
g = t.charCodeAt(b++) - 32,
y === c)
b += g;
else if (y !== l)
return y;
break;
case 9:
v[x++] = c;
break;
case 10:
u(s(v[--x]));
break;
case 11:
y = v[--x],
u(v[--x] + y);
break;
case 12:
for (y = f(),
d = [],
g = 0; g < y.length; g++)
d[g] = y.charCodeAt(g) ^ g + y.length;
u(String.fromCharCode.apply(null, d));
break;
case 13:
y = v[--x],
h = delete v[--x][y];
break;
case 14:
v[x++] = t.charCodeAt(b++) - 32;
break;
case 59:
u((g = t.charCodeAt(b++) - 32) ? (y = x,
v.slice(x -= g, y)) : []);
break;
case 61:
u(v[--x][t.charCodeAt(b++) - 32]);
break;
case 62:
g = v[--x],
k[0] = 65599 * k[0] + k[1].charCodeAt(g) >>> 0;
break;
case 65:
h = v[--x],
y = v[--x],
v[--x][y] = h;
break;
case 66:
u(e(t.substr(b++, 1), v[--x], v[--x]));
break;
case 67:
y = v[--x];
d = v[--x];
g = v[--x];
u(g.x === c ? r(g.y, y, k) : g.apply(d, y));
break;
case 68:
u(e((g = t.substr(b++, 1)) < "<" ? (b--,
f()) : g + g, v[--x], v[--x]));
break;
case 70:
u(!1);
break;
case 71:
v[x++] = n;
break;
case 72:
v[x++] = +f();
break;
case 73:
u(parseInt(f(), 36));
break;
case 75:
if (v[--x]) {
b++;
break
}
case 74:
g = t.charCodeAt(b++) - 32 << 16 >> 16,
b += g;
break;
case 76:
u(k[t.charCodeAt(b++) - 32]);
break;
case 77:
y = v[--x],
u(v[--x][y]);
break;
case 78:
g = t.charCodeAt(b++) - 32,
u(a(v, x -= g + 1, g));
break;
case 79:
g = t.charCodeAt(b++) - 32,
u(k["$" + g]);
break;
case 81:
h = v[--x],
v[--x][f()] = h;
break;
case 82:
u(v[--x][f()]);
break;
case 83:
h = v[--x],
k[t.charCodeAt(b++) - 32] = h;
break;
case 84:
v[x++] = !0;
break;
case 85:
v[x++] = void 0;
break;
case 86:
u(v[x - 1]);
break;
case 88:
h = v[--x],
y = v[--x],
v[x++] = h,
v[x++] = y;
break;
case 89:
u(function () {
function e() {
return r(e.y, arguments, k)
}
return e.y = f(),
e.x = c,
e
}());
break;
case 90:
v[x++] = null;
break;
case 91:
v[x++] = h;
break;
case 93:
h = v[--x];
break;
case 0:
return v[--x];
default:
u((g << 16 >> 16) - 16)
}
}
var n = window;
var t = n.Function,
s = Object.keys || function (e) {
var a = {},
r = 0;
for (var c in e)
a[r++] = c;
return a.length = r,
a
},
b = {},
k = {};
r(decodeURIComponent("gr%24Daten%20%D0%98b%2Fs!l%20y%CD%92y%C4%B9g%2C(lfi~ah%60%7Bmv%2C-n%7CjqewVxp%7Brvmmx%2C%26eff%7Fkx%5B!cs%22l%22.Pq%25widthl%22%40q%26heightl%22vr*getContextx%24%222d%5B!cs%23l%23%2C*%3B%3F%7Cu.%7Cuc%7Buq%24fontl%23vr(fillTextx%24%24%E9%BE%98%E0%B8%91%E0%B8%A0%EA%B2%BD2%3C%5B%23c%7Dl%232q*shadowBlurl%231q-shadowOffsetXl%23%24%24limeq%2BshadowColorl%23vr%23arcx88802%5B%25c%7Dl%23vr%26strokex%5B%20c%7Dl%22v%2C)%7DeOmyoZB%5Dmx%5B%20cs!0s%24l%24Pb%3Ck7l%20l!r%26lengthb%25%5El%241%2Bs%24j%02l%20%20s%23i%241ek1s%24gr%23tack4)zgr%23tac%24!%20%2B0o!%5B%23cj%3Fo%20%5D!l%24b%25s%22o%20%5D!l%22l%24b*b%5E0d%23%3E%3E%3Es!0s%25yA0s%22l%22l!r%26lengthb%3Ck%2Bl%22%5El%221%2Bs%22j%05l%20%20s%26l%26z0l!%24%20%2B%5B%22cs'(0l%23i'1ps9wxb%26s()%20%26%7Bs)%2Fs(gr%26Stringr%2CfromCharCodes)0s*yWl%20._b%26s%20o!%5D)l%20l%20Jb%3Ck%24.aj%3Bl%20.Tb%3Ck%24.gj%2Fl%20.%5Eb%3Ck%26i%22-4j!%1F%2B%26%20s%2ByPo!%5D%2Bs!l!l%20Hd%3E%26l!l%20Bd%3E%26%2Bl!l%20%3Cd%3E%26%2Bl!l%206d%3E%26%2Bl!l%20%26%2B%20s%2Cy%3Do!o!%5D%2Fq%2213o!l%20q%2210o!%5D%2Cl%202d%3E%26%20s.%7Bs-yMo!o!%5D0q%2213o!%5D*Ld%3Cl%204d%23%3E%3E%3Eb%7Cs!o!l%20q%2210o!%5D%2Cl!%26%20s%2FyIo!o!%5D.q%2213o!%5D%2Co!%5D*Jd%3Cl%206d%23%3E%3E%3Eb%7C%26o!%5D%2Bl%20%26%2B%20s0l-l!%26l-l!i'1z141z4b%2F%40d%3Cl%22b%7C%26%2Bl-l(l!b%5E%26%2Bl-l%26zl'g%2C)gk%7Dejo%7B%7Fcm%2C)%7Cyn~Lij~em%5B%22cl%24b%25%40d%3Cl%26zl'l%20%24%20%2B%5B%22cl%24b%25b%7C%26%2Bl-l%258d%3C%40b%7Cl!b%5E%26%2B%20q%24sign%20"), [TAC = {}]);
var params = getHoney();
params._signature = TAC.sign(0);
return JSON.stringify(params);
}
将以上代码，保存为JS文件，通过安装execjs 库即可运行JS代码（其实破解as,cp也可以直接复制源JS代码运行破解，不需要自行对代码翻译破解），
python编译JS代码：
import execjs
def get_js(self):
f = open(r"E:\toutiao\toutiao-TAC.sign.js", 'r', encoding='UTF-8') ##打开JS文件
line = f.readline()
htmlstr = ''
while line:
htmlstr = htmlstr + line
line = f.readline()
ctx = execjs.compile(htmlstr)
return ctx.call('get_as_cp_signature')完成破解后，即可正常爬虫，完整代码：
#!coding=utf-8
import requests
import re
import json
import math
import random
import time
from requests.packages.urllib3.exceptions import InsecureRequestWarning
import pandas as pd
requests.packages.urllib3.disable_warnings(InsecureRequestWarning) ###禁止提醒SSL警告
import hashlib
import execjs
class toutiao(object):
def __init__(self,path,url):
self.path = path # CSV保存地址
self.url=url
self.s = requests.session()
headers = {'Accept': '*/*',
'Accept-Language': 'zh-CN',
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64; Trident/7.0; .NET4.0C; .NET4.0E; .NET CLR 2.0.50727; .NET CLR 3.0.30729; .NET CLR 3.5.30729; InfoPath.3; rv:11.0) like Gecko',
'Connection': 'Keep-Alive',
}
self.s.headers.update(headers)
self.channel=re.search('ch/(.*?)/',url).group(1)
def closes(self):
self.s.close()
def getdata(self): #获取数据
req = self.s.get(url=self.url, verify=False)
#print (self.s.headers)
#print(req.text)
headers = {'referer': self.url}
max_behot_time='0'
signature='.1.hXgAApDNVcKHe5jmqy.9f4U'
eas = 'A1E56B6786B47FE'
ecp = '5B7674A7FF2E9E1'
self.s.headers.update(headers)
title = []
source = []
source_url = []
comments_count = []
tag = []
chinese_tag = []
label = []
abstract = []
behot_time = []
nowtime = []
duration = []
for i in range(0,30): ##获取页数
Honey = json.loads(self.get_js())
# eas = self.getHoney(int(max_behot_time))[0]
# ecp = self.getHoney(int(max_behot_time))[1]
eas = Honey['as']
ecp = Honey['cp']
signature = Honey['_signature']
url='https://www.toutiao.com/api/pc/feed/?category={}&utm_source=toutiao&widen=1&max_behot_time={}&max_behot_time_tmp={}&tadrequire=true&as={}&cp={}&_signature={}'.format(self.channel,max_behot_time,max_behot_time,eas,ecp,signature)
req=self.s.get(url=url, verify=False)
time.sleep(random.random() * 2+2)
print(req.text)
print(url)
j=json.loads(req.text)
for k in range(0, 10):
now=time.time()
if j['data'][k]['tag'] != 'ad':
title.append(j['data'][k]['title']) ##标题
source.append(j['data'][k]['source']) ##作者
source_url.append('https://www.toutiao.com/'+j['data'][k]['source_url']) ##文章链接
try:
comments_count.append(j['data'][k]['comments_count']) ###评论
except:
comments_count.append(0)
tag.append(j['data'][k]['tag']) ###频道名
try:
chinese_tag.append(j['data'][k]['chinese_tag']) ##频道中文名
except:
chinese_tag.append('')
try:
label.append(j['data'][k]['label']) ## 标签
except:
label.append('')
try:
abstract.append(j['data'][k]['abstract']) ###文章摘要
except:
abstract.append('')
behot=int(j['data'][k]['behot_time'])
behot_time.append(time.strftime("%Y-%m-%d %H:%M:%S", time.localtime(behot))) ####发布时间
nowtime.append(time.strftime("%Y-%m-%d %H:%M:%S",time.localtime(now))) ##抓取时间
duration.append(now-behot) ##发布时长
time.sleep(2)
#max_behot_time=str(j['next']['max_behot_time'])
print('------------'+str(j['next']['max_behot_time']))
print(title)
print(source)
print(source_url)
print(comments_count)
print(tag)
print(chinese_tag)
print(label)
print(abstract)
print(behot_time)
print(nowtime)
print(duration)
data={'title':title,'source':source,'source_url':source_url,'comments_count':comments_count,'tag':tag,
'chinese_tag':chinese_tag,'label':label,'abstract':abstract,'behot_time':behot_time,'nowtime':nowtime,'duration':duration,
}
df=pd.DataFrame(data=data)
df.to_csv(self.path+r'\toutiao.csv',encoding='GB18030',index=0)
def getHoney(self,t): #####根据JS脚本破解as ,cp
#t = int(time.time()) #获取当前时间
#t=1534389637
#print(t)
e =str('%X' % t) ##格式化时间
#print(e)
m1 = hashlib.md5() ##MD5加密
m1.update(str(t).encode(encoding='utf-8')) ##转化格式
i = str(m1.hexdigest()).upper() ####转化大写
#print(i)
n=i[0:5] ##获取前5位
a=i[-5:] ##获取后5位
s=''
r=''
for x in range(0,5):
s+=n[x]+e[x]
r+=e[x+3]+a[x]
eas='A1'+ s+ e[-3:]
ecp=e[0:3]+r+'E1'
#print(eas)
#print(ecp)
return eas,ecp
def get_js(self):
f = open(r"E:\toutiao\toutiao-TAC.sign.js", 'r', encoding='UTF-8')
line = f.readline()
htmlstr = ''
while line:
htmlstr = htmlstr + line
line = f.readline()
ctx = execjs.compile(htmlstr)
return ctx.call('get_as_cp_signature')
if __name__=='__main__':
path=r'E:\toutiao'
url='https://www.toutiao.com/ch/news_tech/'
t=toutiao(path,url)
t.getdata()
t.closes()
GitHub：https://github.com/linyhuan/Crawler