百度翻譯爬蟲要滿足以下幾點:
1 登錄自己的百度賬號,需要cookie 信息
2 使用chrome手機瀏覽模式
# 第一版本的百度翻譯爬蟲,非面向對象
import requests
import execjs # 執行js代碼
import json
import sys
# headers 全部使用網頁中的cookie
headers = {
"accept": "*/*",
"accept-encoding": "gzip, deflate, br",
"accept-language": "zh-CN,zh;q=0.9",
"content-length": "122",
"content-type": "application/x-www-form-urlencoded; charset=UTF-8",
"cookie": "填入自己的cookie信息", # 可以先將cookie信息複製sublime 避免 pycharm 出現亂序
"origin": "https://fanyi.baidu.com",
"referer": "https://fanyi.baidu.com/",
"user-agent": "Mozilla/5.0 (Linux; Android 5.0; SM-G900P Build/LRX21T) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/65.0.3325.181 Mobile Safari/537.36",
"x-requested-with": "XMLHttpRequest"
}
# query = sys.argv[1]
query = "good morning"
# 'baidufanyi_sign.js' 在下面
with open('baidufanyi_sign.js', 'r', encoding='utf-8') as f: # 運行百度翻譯的js代碼,生成 sign 值
ctx = execjs.compile(f.read())
sign = ctx.call('e', query)
# print(sign)
p = sign
# print(p)
post_data = { # post 請求 攜帶的數據
"query": query,
"from": "en",
"to": "zh",
"token": "a5f643c1c49ffcfd86b9638e358a3376",
"sign": p,
"simple_means_flag": "3",
}
post_url = "https://fanyi.baidu.com/v2transapi" # 百度翻譯的接口
r = requests.post(post_url, data=post_data, headers=headers)
print(r.content)
print(type(r.content.decode())) # str
dict_ret = json.loads(r.content.decode(), strict=False) # json.loads 把json 數據格式轉換成 python 字典形式 dict
print(type(dict_ret)) # dict
ret = dict_ret["trans_result"]['data'][0]['dst']
print(ret)
這是百度翻譯的sign 生成js。
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
}
var i = "320305.131321201"
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)
}
聲明:代碼僅用爲技術研究使用,禁止作爲商業使用哦。
感謝百度翻譯,感謝
https://blog.csdn.net/qq_38534107/article/details/90440403,js代碼的分析可以在此文查看。
https://blog.csdn.net/qq_38534107/article/details/90440403