diff --git a/baidu_translate/Baidufanyi.py b/baidu_translate/Baidufanyi.py new file mode 100644 index 0000000..45ba07e --- /dev/null +++ b/baidu_translate/Baidufanyi.py @@ -0,0 +1,94 @@ +# !/usr/bin/python3 +# -*- coding: utf-8 -*- + +""" +info: +author:CriseLYJ +github:https://github.com/CriseLYJ/ +""" + +""" +请求url分析 :https://fanyi.baidu.com/basetrans +请求方式分析 :POST +请求参数分析 : { +query: hello +from: en +to: zh +token: 6f5c83b84d69ad3633abdf18abcb030d +sign: 54706.276099} +请求头分析 +""" + +# 代码实现流程 +# 1. 实现面对对象构建爬虫对象 +# 2. 爬虫流程四步骤 +# 2.1 获取URl +# 2.2 发送请求获取响应 +# 2.3 从响应中提取数据 +# 2.4 保存数据 + +import requests +import js2py + +context = js2py.EvalJs() + + +class BaiDuTranslater(object): + """ + 百度翻译爬虫 + """ + + def __init__(self, query): + # 初始化 + self.url = "https://fanyi.baidu.com/basetrans" + self.query = query + self.headers = { + "User-Agent": "Mozilla/5.0 (iPhone; CPU iPhone OS 11_0 like Mac OS X) AppleWebKit/604.1.38 (KHTML, like Gecko) Version/11.0 Mobile/15A372 Safari/604.1", + "Referer": "https://fanyi.baidu.com/", + "Cookie": "BAIDUID=714BFAAF02DA927F583935C7A354949A:FG=1; BIDUPSID=714BFAAF02DA927F583935C7A354949A; PSTM=1553390486; delPer=0; PSINO=5; H_PS_PSSID=28742_1463_21125_18559_28723_28557_28697_28585_28640_28604_28626_22160; locale=zh; from_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; 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; REALTIME_TRANS_SWITCH=1; FANYI_WORD_SWITCH=1; HISTORY_SWITCH=1; SOUND_SPD_SWITCH=1; SOUND_PREFER_SWITCH=1; Hm_lvt_afd111fa62852d1f37001d1f980b6800=1553658863,1553766321,1553769980,1553770442; Hm_lpvt_afd111fa62852d1f37001d1f980b6800=1553770442; Hm_lvt_64ecd82404c51e03dc91cb9e8c025574=1553766258,1553766321,1553769980,1553770442; Hm_lpvt_64ecd82404c51e03dc91cb9e8c025574=1553770442" + } + + def make_sign(self): + # js逆向获取sign的值 + with open("translate.js", "r", encoding="utf-8") as f: + context.execute(f.read()) + + # 调用js中的函数生成sign + sign = context.a(self.query) + # 将sign加入到data中 + return sign + + def make_data(self, sign): + data = { + "query": self.query, + "from": "en", + "to": "zh", + "token": "6f5c83b84d69ad3633abdf18abcb030d", + "sign": sign + } + return data + + def get_content(self, data): + # 发送请求获取响应 + response = requests.post( + url=self.url, + headers=self.headers, + data=data + ) + return response.json()["trans"][0]["dst"] + + def run(self): + """运行程序""" + # 获取sign的值 + sign = self.make_sign() + # 构建参数 + data = self.make_data(sign) + # 获取翻译内容 + content = self.get_content(data) + print(content) + + +if __name__ == '__main__': + query = input("请输入您要翻译的内容:") + translater = BaiDuTranslater(query) + translater.run() diff --git a/baidu_translate/translate.js b/baidu_translate/translate.js new file mode 100644 index 0000000..fda17d0 --- /dev/null +++ b/baidu_translate/translate.js @@ -0,0 +1,45 @@ +var i = "320305.131321201" + + +function n(r, o) { + for (var t = 0; t < o.length - 2; t += 3) { + var e = o.charAt(t + 2); + e = e >= "a" ? e.charCodeAt(0) - 87 : Number(e), + e = "+" === o.charAt(t + 1) ? r >>> e : r << e, + r = "+" === o.charAt(t) ? r + e & 4294967295 : r ^ e + } + return r +} + +function a(r) { + var t = r.match(/[\uD800-\uDBFF][\uDC00-\uDFFF]/g); + if (null === t) { + var a = r.length; + a > 30 && (r = "" + r.substr(0, 10) + r.substr(Math.floor(a / 2) - 5, 10) + r.substr(-10, 10)) + } else { + for (var C = r.split(/[\uD800-\uDBFF][\uDC00-\uDFFF]/), h = 0, f = C.length, u = []; f > h; h++) + "" !== C[h] && u.push.apply(u, e(C[h].split(""))), + h !== f - 1 && u.push(t[h]); + var g = u.length; + g > 30 && (r = u.slice(0, 10).join("") + u.slice(Math.floor(g / 2) - 5, Math.floor(g / 2) + 5).join("") + u.slice(-10).join("")) + } + var l = void 0 + , d = "" + String.fromCharCode(103) + String.fromCharCode(116) + String.fromCharCode(107); + l = null !== i ? i : (i = o.common[d] || "") || ""; + for (var m = l.split("."), S = Number(m[0]) || 0, s = Number(m[1]) || 0, c = [], v = 0, F = 0; F < r.length; F++) { + var p = r.charCodeAt(F); + 128 > p ? c[v++] = p : (2048 > p ? c[v++] = p >> 6 | 192 : (55296 === (64512 & p) && F + 1 < r.length && 56320 === (64512 & r.charCodeAt(F + 1)) ? (p = 65536 + ((1023 & p) << 10) + (1023 & r.charCodeAt(++F)), + c[v++] = p >> 18 | 240, + c[v++] = p >> 12 & 63 | 128) : c[v++] = p >> 12 | 224, + c[v++] = p >> 6 & 63 | 128), + c[v++] = 63 & p | 128) + } + for (var w = S, A = "" + String.fromCharCode(43) + String.fromCharCode(45) + String.fromCharCode(97) + ("" + String.fromCharCode(94) + String.fromCharCode(43) + String.fromCharCode(54)), b = "" + 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)), D = 0; D < c.length; D++) + w += c[D], + w = n(w, A); + return w = n(w, b), + w ^= s, + 0 > w && (w = (2147483647 & w) + 2147483648), + w %= 1e6, + w.toString() + "." + (w ^ S) +}