https://www.jianshu.com/p/0fb8a5daf617?from=timeline&isappinstalled=0
PRO-003:反爬虫实践-签名验证
本主题，通过爬取一个翻译网站，实现一个在线翻译程序为例，来说明下怎么处理签名验证的反爬虫技术分析过程。
- 签名校验的一般套路；
- 通过百度分析签名的实现原理；
- 用Python爬取百度的翻译结果；
一、签名校验的一般套路
二、百度翻译的签名算法分析
1、使用浏览器开发工具分析百度翻译
Safari浏览器开发菜单设置
方式一：使用浏览器系统菜单
打开浏览器开发工具方式一：使用浏览器系统菜单
方式二：使用右键弹出菜单
打开浏览器开发工具方式二：使用右键弹出菜单
红色区域就是开发工具视图
【网络】与【资源】标签在浏览器下载数据分析中比较常用。
【网络】标签功能用来跟踪浏览器网络请求与服务器响应的过程比较有用。
【资源】主要用来分析浏览器下载后的资源数据，分析结果比较有用。
【网络】标签显示【网络】视图，在其中可以选择XHR查看浏览器发起的异步请求，异步请求都是通过Javascript代码实现：
浏览器请求的【网络】功能视图
跟踪AJAX请求的信息显示视图
【预览】、【标题】、【Cookie】
【标题】中显示请求过程中相关信息包含：【摘要】【请求】【响应】与【请求数据】四个字段信息。
请求的URL确认
AJAX请求的数据包格式
sign与token。
【JS】资源的视图：
JS视图列出的JS资源
sign与token关键字（使用ctrl+f启动搜索视图）：
找到实现sign与token算法的js脚本
2、分析Javascript代码
define("translation:widget/translate/input/translate", function(t, a) { "use strict"; var e = t("translation:widget/translate/input/prompt"), n = t("translation:widget/translate/input/textarea"), r = t("translation:widget/common/util"), s = t("translation:widget/translate/output/output"), o = t("translation:widget/common/config/trans"), i = t("translation:widget/translate/input/processlang"), l = t("translation:widget/common/string"), u = t("translation:widget/translate/input/soundicon"), g = t("translation:widget/translate/input/hash"), c = t("translation:widget/common/environment"), d = t("translation:widget/translate/input/longtext"), p = t("translation:widget/common/sendLog"), y = t("translation:widget/translate/details/dictionary/simplemeans"), f = t("translation:widget/translate/history/history"), //======================================================================== m = t("translation:widget/translate/input/pGrab"), //======================================================================== h = t("translation:widget/translate/details/adLink/adLink"), w = { onTrans: function(t) { y.translateStopRepeat() || y.shutdownAudio(); var a = (n.getElem(), n.getVal()), e = this, s = t && t.transtype; if (r.isUrl(a)) return void this.translateWebPage(a); if (a.length > 0 && p.sendIndexDisplayLog({ action: "query" }), this.isQueryValid(a)) { var o = a; o.length > 50 && (o = l.cutByByte(o, 0, 50).replace(/[\uD800-\uDBFF]$/, "")); var i = { query: o }; $.ajax({ url: "/langdetect", type: "POST", data: I, success: function(t) { 0 === t.error && t.lan ? e.langIsDeteced(t.lan, a, s) : e.reponseQuery(a) } }) } }, isQueryValid: function(t) { return t ? !0 : !1 }, processQuery: function(t) { var a = t; if (l.getByte(t) > o.MAX_QUERY_COUNT) { c.set("needLongtextTip", !0); var e = t; a = l.cutByByte(t, 0, o.MAX_QUERY_COUNT).replace(/[\uD800-\uDBFF]$/, ""), e = l.cutByByte(e, o.MAX_QUERY_COUNT, o.MAX_QUERY_COUNT + 9), d.showTip({ query: e }) } return a }, langIsDeteced: function(t, a, n, r) { if (null !== t) { var s = $(".select-from-language .language-selected").attr("data-lang"), o = $(".select-to-language .language-selected").attr("data-lang"), l = !1; c.get("langChangedByUser") && t === o && (l = !0); var g = null; r && !c.get("fromLangIsAuto") && s !== t ? g = i.processOcrLang(t, s, o) : (e.show(t, s), g = i.getLang(t, s, o)), u.show(); var d = this, a = this.processQuery(a), //======================================================================== p = { from: g.fromLang, to: g.toLang, query: a, transtype: n, simple_means_flag: 3, sign: m(a), token: window.common.token }; //======================================================================== this.translateXHR && 4 !== this.translateXHR.readyState && this.translateXHR.abort(), this.translateXHR = $.ajax({ type: "POST", url: "/v2transapi", cache: !1, data: p }).done(function(t) { c.set("isInRtTransState", !0), d.translateSuccess(t, g.fromLang, g.toLang, a, l) }) } }, translateWebPage: function(t) { var a = "/"; "https:" === location.protocol && (a = "http://fanyi.baidu.com/"), document.location.href = [a + "transpage?", "query=" + encodeURIComponent(t), "&source=url", "&ie=utf8", "&from=" + $(".select-from-language .language-selected").attr("data-lang"), "&to=" + $(".select-to-language .language-selected").attr("data-lang"), "&render=1"].join("") }, textareaFocus: function() { n.focus() }, translateSuccess: function(t, a, e, r, i) { return n.getVal() ? (r && encodeURIComponent(r).length < o.MAX_URL_COUNT && f.add(a, e, $.trim(r)), f.hideHistory(), h.hide(), s.checkResponse({ res: t, from: a, to: e, query: r, badCaseByForce: I }), void g.setHash({ query: r })) : void c.set("isInRtTransState", !1) }, reponseQuery: function() {} }; a.onTranslate = function(t) { w.onTrans(t) }, a.translateAfterOcr = function(t, a) { _hmt.push(["_trackEvent", "首页", "59_首页页面_翻译query量_图片"]), w.langIsDeteced(t, a, void 0, !0) } }); m = t("translation:widget/translate/input/pGrab"), define("translation:widget/translate/input/pGrab", function(r, o, t) { "use strict"; function a(r) { if (Array.isArray(r)) { for (var o = 0, t = Array(r.length); o < r.length; o++) t[o] = r[o]; return t } return Array.from(r) } function n(r, o) { for (var t = 0; t < o.length - 2; t += 3) { var a = o.charAt(t + 2); a = a >= "a" ? a.charCodeAt(0) - 87 : Number(a), a = "+" === o.charAt(t + 1) ? r >>> a : r << a, r = "+" === o.charAt(t) ? r + a & 4294967295 : r ^ a } return r } function e(r) { var o = r.match(/[\uD800-\uDBFF][\uDC00-\uDFFF]/g); if (null === o) { var t = r.length; t > 30 && (r = "" + r.substr(0, 10) + r.substr(Math.floor(t / 2) - 5, 10) + r.substr(-10, 10)) } else { for (var e = r.split(/[\uD800-\uDBFF][\uDC00-\uDFFF]/), C = 0, h = e.length, f = []; h > C; C++) "" !== e[C] && f.push.apply(f, a(e[C].split(""))), C !== h - 1 && f.push(o[C]); var g = f.length; g > 30 && (r = f.slice(0, 10).join("") + f.slice(Math.floor(g / 2) - 5, Math.floor(g / 2) + 5).join("") + f.slice(-10).join("")) } var u = void 0, l = "" + String.fromCharCode(103) + String.fromCharCode(116) + String.fromCharCode(107); u = null !== i ? i : (i = window[l] || "") || ""; for (var d = u.split("."), m = Number(d[0]) || 0, s = Number(d[1]) || 0, S = [], c = 0, v = 0; v < r.length; v++) { var A = r.charCodeAt(v); 128 > A ? S[c++] = A : (2048 > A ? S[c++] = A >> 6 | 192 : (55296 === (64512 & A) && v + 1 < r.length && 56320 === (64512 & r.charCodeAt(v + 1)) ? (A = 65536 + ((1023 & A) << 10) + (1023 & r.charCodeAt(++v)), S[c++] = A >> 18 | 240, S[c++] = A >> 12 & 63 | 128) : S[c++] = A >> 12 | 224, S[c++] = A >> 6 & 63 | 128), S[c++] = 63 & A | 128) } for (var p = m, F = "" + String.fromCharCode(43) + String.fromCharCode(45) + String.fromCharCode(97) + ("" + String.fromCharCode(94) + String.fromCharCode(43) + String.fromCharCode(54)), D = "" + String.fromCharCode(43) + String.fromCharCode(45) + String.fromCharCode(51) + ("" + String.fromCharCode(94) + String.fromCharCode(43) + String.fromCharCode(98)) + ("" + String.fromCharCode(43) + String.fromCharCode(45) + String.fromCharCode(102)), b = 0; b < S.length; b++) p += S[b], p = n(p, F); return p = n(p, D), p ^= s, 0 > p && (p = (2147483647 & p) + 2147483648), p %= 1e6, p.toString() + "." + (p ^ m) } var i = null; t.exports = e }); t.exports = e p %= 1e6, p.toString() + "." + (p ^ m) 请求数据 MIME 类型: application/x-www-form-urlencoded; charset=UTF-8 from: en to: zh query: perfect transtype: realtime simple_means_flag: 3 ================================================ sign: 173319.411190 ================================================ token: 5132afa657f678cc1ed6c0caf37fc2a2 3、百度签名算法的处理技巧
>pip install js2py 
js2py模块安装过程
三、使用Python实现爬取百度翻译的信息
1、js2py的使用
#coding=utf-8 import js2py script=r''' a=20; f=function(param1,param2){ return param1+param2 } ''' #构造JS执行上下文环境 ctx = js2py.EvalJs() #加载脚本 ctx.execute(script) #访问变量 print(ctx.a) #20 #调用函数 print(ctx.f(45,55)) #100 2、使用requests获取window.common.token
http://fanyi.baidu.com/得到。由于主页得到的是一段HTML资源，所以获取window.common.token
使用正则表达式查找即可。下面是在主页中找到的token的定义：
window.common.token的定义
import requests import re #token识实在主页中加载 session = requests.Session() response = session.get("http://fanyi.baidu.com/") token = re.findall("token: ('.*'),",response.content.decode())[0] print(token) 3、在Python中调用百度js脚本得到签名
var u = void 0, //=========================================================== l = "" + String.fromCharCode(103) + String.fromCharCode(116) + String.fromCharCode(107); //=========================================================== u = null !== i ? i : (i = window[l] || "") || ""; //=========================================================== for (var d = u.split("."), m = Number(d[0]) || 0, s = Number(d[1]) || 0, S = [], c = 0, v = 0; v < r.length; v++) { var A = r.charCodeAt(v); 128 > A ? S[c++] = A : (2048 > A ? S[c++] = A >> 6 | 192 : (55296 === (64512 & A) && v + 1 < r.length && 56320 === (64512 & r.charCodeAt(v + 1)) ? (A = 65536 + ((1023 & A) << 10) + (1023 & r.charCodeAt(++v)), S[c++] = A >> 18 | 240, S[c++] = A >> 12 & 63 | 128) : S[c++] = A >> 12 | 224, S[c++] = A >> 6 & 63 | 128), S[c++] = 63 & A | 128) } for (var p = m, F = "" + String.fromCharCode(43) + String.fromCharCode(45) + String.fromCharCode(97) + ("" + String.fromCharCode(94) + String.fromCharCode(43) + String.fromCharCode(54)), D = "" + String.fromCharCode(43) + String.fromCharCode(45) + String.fromCharCode(51) + ("" + String.fromCharCode(94) + String.fromCharCode(43) + String.fromCharCode(98)) + ("" + String.fromCharCode(43) + String.fromCharCode(45) + String.fromCharCode(102)), b = 0; b < S.length; b++) p += S[b], p = n(p, F); return p = n(p, D), p ^= s, 0 > p && (p = (2147483647 & p) + 2147483648), p %= 1e6, p.toString() + "." + (p ^ m) 
window.gtk的定义
#coding=utf-8 import js2py import requests import re session = requests.Session() response = session.get("http://fanyi.baidu.com/") #获取window.gtk的值。 gtk = re.findall(";window.gtk = ('.*?');",response.content.decode())[0] #要翻译的单词 word = 'perfect' context = js2py.EvalJs() #从浏览器拷贝的签名生成函数脚本（r-raw表示原生字符串） js = r''' function a(r) { if (Array.isArray(r)) { for (var o = 0, t = Array(r.length); o < r.length; o++) t[o] = r[o]; return t } return Array.from(r) } function n(r, o) { for (var t = 0; t < o.length - 2; t += 3) { var a = o.charAt(t + 2); a = a >= "a" ? a.charCodeAt(0) - 87 : Number(a), a = "+" === o.charAt(t + 1) ? r >>> a : r << a, r = "+" === o.charAt(t) ? r + a & 4294967295 : r ^ a } return r } function e(r) { var o = r.match(/[\uD800-\uDBFF][\uDC00-\uDFFF]/g); if (null === o) { var t = r.length; t > 30 && (r = "" + r.substr(0, 10) + r.substr(Math.floor(t / 2) - 5, 10) + r.substr(-10, 10)) } else { for (var e = r.split(/[\uD800-\uDBFF][\uDC00-\uDFFF]/), C = 0, h = e.length, f = []; h > C; C++) "" !== e[C] && f.push.apply(f, a(e[C].split(""))), C !== h - 1 && f.push(o[C]); var g = f.length; g > 30 && (r = f.slice(0, 10).join("") + f.slice(Math.floor(g / 2) - 5, Math.floor(g / 2) + 5).join("") + f.slice(-10).join("")) } var u = void 0 , l = "" + String.fromCharCode(103) + String.fromCharCode(116) + String.fromCharCode(107); u ='null !== i ? i : (i = window[l] || "") || ""'; for (var d = u.split("."), m = Number(d[0]) || 0, s = Number(d[1]) || 0, S = [], c = 0, v = 0; v < r.length; v++) { var A = r.charCodeAt(v); 128 > A ? S[c++] = A : (2048 > A ? S[c++] = A >> 6 | 192 : (55296 === (64512 & A) && v + 1 < r.length && 56320 === (64512 & r.charCodeAt(v + 1)) ? (A = 65536 + ((1023 & A) << 10) + (1023 & r.charCodeAt(++v)), S[c++] = A >> 18 | 240, S[c++] = A >> 12 & 63 | 128) : S[c++] = A >> 12 | 224, S[c++] = A >> 6 & 63 | 128), S[c++] = 63 & A | 128) } for (var p = m, F = "" + String.fromCharCode(43) + String.fromCharCode(45) + String.fromCharCode(97) + ("" + String.fromCharCode(94) + String.fromCharCode(43) + String.fromCharCode(54)), D = "" + String.fromCharCode(43) + String.fromCharCode(45) + String.fromCharCode(51) + ("" + String.fromCharCode(94) + String.fromCharCode(43) + String.fromCharCode(98)) + ("" + String.fromCharCode(43) + String.fromCharCode(45) + String.fromCharCode(102)), b = 0; b < S.length; b++) p += S[b], p = n(p, F); return p = n(p, D), p ^= s, 0 > p && (p = (2147483647 & p) + 2147483648), p %= 1e6, p.toString() + "." + (p ^ m) } ''' #在javascript脚本中把u的值替换成window.gtk js = js.replace('\'null !== i ? i : (i = window[l] || "") || ""\'',gtk) #执行js context.execute(js) #调用函数得到sign sign = context.e(word) print(sign) #173319.411190 
程序计算的sing与浏览器器计算的sign完全一样
1）. sug请求简单的翻译，是免费的，可以随意获取，没有采取反爬虫技术。
免费的sug获取的翻译
2）. langdetect根据输入的字符，检测其语言。
3）. v2transapi提供功能更加强悍的翻译结果。包含下面图示中的使用箭头标示的四个翻译结果
v2transapi获得翻译效果
4、使用v2transapi实现功能更强的翻译
1）首先使用get方法请求百度翻译的首页https://fanyi.baidu.com/，从中获取两个信息token，gtk,其中的关键在于我们使用了从浏览器产生的headers格式。
2）然后使用gtk产生sign，并使用token与sign，以及其他数据构造请求数据，发去爬取请求，获得我们需要的数据。
import requests import re import js2py import json class SignAndToken: def __init__(self): #加载主页 self.session = requests.Session() self.headers={ "Cookie":"Hm_lpvt_64ecd82404c51e03dc91cb9e8c025574=1541668433; Hm_lvt_64ecd82404c51e03dc91cb9e8c025574=1541430897,1541471052,1541641285,1541668433; from_lang_often=%5B%7B%22value%22%3A%22de%22%2C%22text%22%3A%22%u5FB7%u8BED%22%7D%2C%7B%22value%22%3A%22zh%22%2C%22text%22%3A%22%u4E2D%u6587%22%7D%2C%7B%22value%22%3A%22en%22%2C%22text%22%3A%22%u82F1%u8BED%22%7D%5D; to_lang_often=%5B%7B%22value%22%3A%22en%22%2C%22text%22%3A%22%u82F1%u8BED%22%7D%2C%7B%22value%22%3A%22zh%22%2C%22text%22%3A%22%u4E2D%u6587%22%7D%5D; FANYI_WORD_SWITCH=1; HISTORY_SWITCH=1; REALTIME_TRANS_SWITCH=1; SOUND_PREFER_SWITCH=1; SOUND_SPD_SWITCH=1; locale=zh; BDORZ=B490B5EBF6F3CD402E515D22BCDA1598; H_PS_PSSID=1430_21119_27401_26350_22158; PSINO=1; delPer=0; BDRCVFR[feWj1Vr5u3D]=I67x6TjHwwYf0; BDUSS=hsVWV6czh0a1hOQ3BaYkhTM0FrOXhNYnBCUWFsMlY0clhlYkNvTkRKdENDUGxiQUFBQUFBJCQAAAAAAAAAAAEAAAAFyMhmAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAEJ70VtCe9FbY0; BIDUPSID=C53590ACE23DAC88DBE0C3D65AEBAA30; PSTM=1539535646; BAIDUID=DB00283B42FBC875B67496A00F47ABAB:FG=1", "Accept":"text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8", "Upgrade-Insecure-Requests":"1", "Host":"fanyi.baidu.com", "User-Agent":"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_6) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/12.0.1 Safari/605.1.15", "Accept-Language":"zh-cn", "Accept-Encoding": "gzip, deflate" } self.session.headers = self.headers response = self.session.get("https://fanyi.baidu.com/") #获取token self.token = re.findall("token: ('.*'),",response.content.decode())[0] self.token=self.token[1:-1] print(self.token) #获取gtk # 获取window.gtk的值。 self.gtk = re.findall(";window.gtk = ('.*?');", response.content.decode())[0] #初始化Javascript脚本执行上下文环境 self.context = js2py.EvalJs() def sign(self,word): # 从浏览器拷贝的签名生成函数脚本（r-raw表示原生字符串） js = r''' function a(r) { if (Array.isArray(r)) { for (var o = 0, t = Array(r.length); o < r.length; o++) t[o] = r[o]; return t } return Array.from(r) } function n(r, o) { for (var t = 0; t < o.length - 2; t += 3) { var a = o.charAt(t + 2); a = a >= "a" ? a.charCodeAt(0) - 87 : Number(a), a = "+" === o.charAt(t + 1) ? r >>> a : r << a, r = "+" === o.charAt(t) ? r + a & 4294967295 : r ^ a } return r } function e(r) { var o = r.match(/[\uD800-\uDBFF][\uDC00-\uDFFF]/g); if (null === o) { var t = r.length; t > 30 && (r = "" + r.substr(0, 10) + r.substr(Math.floor(t / 2) - 5, 10) + r.substr(-10, 10)) } else { for (var e = r.split(/[\uD800-\uDBFF][\uDC00-\uDFFF]/), C = 0, h = e.length, f = []; h > C; C++) "" !== e[C] && f.push.apply(f, a(e[C].split(""))), C !== h - 1 && f.push(o[C]); var g = f.length; g > 30 && (r = f.slice(0, 10).join("") + f.slice(Math.floor(g / 2) - 5, Math.floor(g / 2) + 5).join("") + f.slice(-10).join("")) } var u = void 0 , l = "" + String.fromCharCode(103) + String.fromCharCode(116) + String.fromCharCode(107); u ='null !== i ? i : (i = window[l] || "") || ""'; for (var d = u.split("."), m = Number(d[0]) || 0, s = Number(d[1]) || 0, S = [], c = 0, v = 0; v < r.length; v++) { var A = r.charCodeAt(v); 128 > A ? S[c++] = A : (2048 > A ? S[c++] = A >> 6 | 192 : (55296 === (64512 & A) && v + 1 < r.length && 56320 === (64512 & r.charCodeAt(v + 1)) ? (A = 65536 + ((1023 & A) << 10) + (1023 & r.charCodeAt(++v)), S[c++] = A >> 18 | 240, S[c++] = A >> 12 & 63 | 128) : S[c++] = A >> 12 | 224, S[c++] = A >> 6 & 63 | 128), S[c++] = 63 & A | 128) } for (var p = m, F = "" + String.fromCharCode(43) + String.fromCharCode(45) + String.fromCharCode(97) + ("" + String.fromCharCode(94) + String.fromCharCode(43) + String.fromCharCode(54)), D = "" + String.fromCharCode(43) + String.fromCharCode(45) + String.fromCharCode(51) + ("" + String.fromCharCode(94) + String.fromCharCode(43) + String.fromCharCode(98)) + ("" + String.fromCharCode(43) + String.fromCharCode(45) + String.fromCharCode(102)), b = 0; b < S.length; b++) p += S[b], p = n(p, F); return p = n(p, D), p ^= s, 0 > p && (p = (2147483647 & p) + 2147483648), p %= 1e6, p.toString() + "." + (p ^ m) } ''' # 在javascript脚本中把u的值替换成window.gtk js = js.replace('\'null !== i ? i : (i = window[l] || "") || ""\'', self.gtk) # 执行js self.context.execute(js) # 调用函数得到sign return self.context.e(word) class TranslateTool: def __init__(self): self.sign_token=SignAndToken() self.url="https://fanyi.baidu.com/v2transapi/" self.headers={ "Content-Type": "application/x-www-form-urlencoded; charset=UTF-8", "Accept":"*/*", "Host":"fanyi.baidu.com", "Accept-Language":"zh-cn", "Accept-Encoding":"gzip, deflate", "Origin":"https://fanyi.baidu.com", "Referer":"https://fanyi.baidu.com/", "Connection":"keep-alive", "User-Agent":"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_6) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/12.0.1 Safari/605.1.15", "X-Requested-With": "XMLHttpRequest", "Cookie":"Hm_lpvt_64ecd82404c51e03dc91cb9e8c025574=1541696184; Hm_lvt_64ecd82404c51e03dc91cb9e8c025574=1541430897,1541471052,1541641285,1541668433; from_lang_often=%5B%7B%22value%22%3A%22de%22%2C%22text%22%3A%22%u5FB7%u8BED%22%7D%2C%7B%22value%22%3A%22zh%22%2C%22text%22%3A%22%u4E2D%u6587%22%7D%2C%7B%22value%22%3A%22en%22%2C%22text%22%3A%22%u82F1%u8BED%22%7D%5D; to_lang_often=%5B%7B%22value%22%3A%22en%22%2C%22text%22%3A%22%u82F1%u8BED%22%7D%2C%7B%22value%22%3A%22zh%22%2C%22text%22%3A%22%u4E2D%u6587%22%7D%5D; FANYI_WORD_SWITCH=1; HISTORY_SWITCH=1; REALTIME_TRANS_SWITCH=1; SOUND_PREFER_SWITCH=1; SOUND_SPD_SWITCH=1; BDORZ=B490B5EBF6F3CD402E515D22BCDA1598; H_PS_PSSID=1430_21119_27401_26350_22158; PSINO=1; delPer=0; locale=zh; BDRCVFR[feWj1Vr5u3D]=I67x6TjHwwYf0; BDUSS=hsVWV6czh0a1hOQ3BaYkhTM0FrOXhNYnBCUWFsMlY0clhlYkNvTkRKdENDUGxiQUFBQUFBJCQAAAAAAAAAAAEAAAAFyMhmAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAEJ70VtCe9FbY0; BIDUPSID=C53590ACE23DAC88DBE0C3D65AEBAA30; PSTM=1539535646; BAIDUID=DB00283B42FBC875B67496A00F47ABAB:FG=1" } def translate(self,word): token=self.sign_token.token sign=self.sign_token.sign(word) #构造请求数据 data={ 'from': 'en', 'to': 'zh', 'query': word, 'transtype': 'realtime', 'simple_means_flag': 3, 'sign': sign, 'token': token } #response=requests.post(self.url,data=data,headers=self.headers) response=self.sign_token.session.post(self.url,data=data) return response.content tool=TranslateTool() re=json.loads(tool.translate("perfect").decode()) print(re) 
爬取得输出结果（数据很大很大）
爬取数据在sublime打开的结果
5、使用langdetect侦测输入的语言类型
MIME 类型: application/x-www-form-urlencoded; charset=UTF-8 kw: perfect #coding=utf-8 import requests import re import js2py import json # 构造请求数据 url="https://fanyi.baidu.com/langdetect" data = { 'query': '英雄' } response = requests.post(url, data=data) print(response.content.decode()) 
语言检测结果
6、使用sug实现简单翻译
MIME 类型: application/x-www-form-urlencoded; charset=UTF-8 kw: perfect #coding=utf-8 import requests import re import js2py import json # 构造请求数据 url="https://fanyi.baidu.com/sug" data = { 'kw': 'test' } response = requests.post(url, data=data) content=response.content.decode() data=json.loads(content)["data"] for item in data: print(item['v']) 
sug运行结果
资源
文章来源: 百度sign