百度翻译网址 : https://fanyi.baidu.com
第一步分析网页
打开页面之后，摁F12，打开开发者工具，在文本框中输入想要翻译的词汇
这时，就能看到network中的请求响应：
https://fanyi.baidu.com/v2transapi?from=zh&to=en，请求方式为post,
鼠标往下移动，能看到请求自带Form Data的参数：
再重复一次操作：
就能得出两次请求所带的参数的不同之处。
想要得到动态sign的数据，需要点击下图选项，在参数中选择一个参数放到search中，然后点击处于蓝色方框的simple_means_flag
把鼠标移到sign: L(e)的这行的行数8392中点击，打上断点，在页面再点击一次翻译，就会显示出前端的数据，把鼠标移到L，他会显示出一个函数的调用，点击进入函数
点击f(e)
可以看得出来传入函数的型参r就是我们在页面输入的需要翻译字符, 点击下图红框选项，让它执行下一行，就会把参数显示出来了
把2703-2734行代码复制下来，放到本地保存fanyi_baidu_com.js文件
第二步 开始写爬虫程序
在pycharm的终端中下载第三方库 PyExecJS，jsonpath, requests
先写一个用户代理随机分配的函数
建立自定义的爬虫函数
在请求头(request headers)中找到User-Agent, Cookie, Referer, 复制里面的值下来到文件中，用来应对反爬策略
运行代码查看结果
跳出报错信息，知道了 i 未定义，主函数中并没有 i 这个变量， 于是把目标转移到网页当中选中watch点击+直接输入 i 点击+旁边的刷新，就能得到数据
在js文件中添加上这个参数
再试试打印结果
在watch这种输入n，得出的结果是 n ( r , o )
把鼠标移到 p = (D , F), 点击进去直接黄色黄色高亮会跳到n ( r , o )的函数
把这段代码复制下来，放到js文件中
最后再运行下代码
得到sign的参数, 使用变量接收，并把它放到字典中保存
使用requests的方法post开始爬取数据
使用jsonpath的方法解析json数据, 运行结果得出翻译结果
完整爬虫代码
def User_Agent(): import random User_Agent_list = [ "Mozilla/5.0 (Windows NT 6.1; WOW64) appleWebKit/537.1 (KHTML, like Gecko) Chrome/22.0.1207.1 Safari/537.1" "Mozilla/5.0 (X11; CrOS i686 2268.111.0) appleWebKit/536.11 (KHTML, like Gecko) Chrome/20.0.1132.57 Safari/536.11", "Mozilla/5.0 (Windows NT 6.1; WOW64) appleWebKit/536.6 (KHTML, like Gecko) Chrome/20.0.1092.0 Safari/536.6", "Mozilla/5.0 (Windows NT 6.2) appleWebKit/536.6 (KHTML, like Gecko) Chrome/20.0.1090.0 Safari/536.6", "Mozilla/5.0 (Windows NT 6.2; WOW64) appleWebKit/537.1 (KHTML, like Gecko) Chrome/19.77.34.5 Safari/537.1", "Mozilla/5.0 (X11; Linux x86_64) appleWebKit/536.5 (KHTML, like Gecko) Chrome/19.0.1084.9 Safari/536.5", "Mozilla/5.0 (Windows NT 6.0) appleWebKit/536.5 (KHTML, like Gecko) Chrome/19.0.1084.36 Safari/536.5", "Mozilla/5.0 (Windows NT 6.1; WOW64) appleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1063.0 Safari/536.3", "Mozilla/5.0 (Windows NT 5.1) appleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1063.0 Safari/536.3", "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_8_0) appleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1063.0 Safari/536.3", "Mozilla/5.0 (Windows NT 6.2) appleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1062.0 Safari/536.3", "Mozilla/5.0 (Windows NT 6.1; WOW64) appleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1062.0 Safari/536.3", "Mozilla/5.0 (Windows NT 6.2) appleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1061.1 Safari/536.3", "Mozilla/5.0 (Windows NT 6.1; WOW64) appleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1061.1 Safari/536.3", "Mozilla/5.0 (Windows NT 6.1) appleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1061.1 Safari/536.3", "Mozilla/5.0 (Windows NT 6.2) appleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1061.0 Safari/536.3", "Mozilla/5.0 (X11; Linux x86_64) appleWebKit/535.24 (KHTML, like Gecko) Chrome/19.0.1055.1 Safari/535.24", "Mozilla/5.0 (Windows NT 6.2; WOW64) appleWebKit/535.24 (KHTML, like Gecko) Chrome/19.0.1055.1 Safari/535.24" ] return random.choices(User_Agent_list)[-1]
def baidu_fanyi(): from jsonpath import jsonpath import execjs # 导入执行js文件的第三方库 # 百度翻译 url = "https://fanyi.baidu.com/v2transapi?from=zh&to=en" # 请求头 header = { # 用户代理 'user-agent': User_Agent(), # 跳转网址 'referer': "https://fanyi.baidu.com/", # 会话记录 'cookie': "PSTM=1624889671; BDRCVFR[IZdXtXdDRBm]=EBD6F1bEM2tXZKdrHn8mvqV; BA" "IDUID=A40ADC4C6BA4061C4246C9BE890ADBCA:FG=1; H_PS_PSSID=; BIDUPSID" "=DF100614A15524BC80AF12360E70B2FE; Hm_lvt_64ecd82404c51e03dc91cb9e8" "c025574=1625065330; __yjs_duid=1_a8b2eaa3041ec1e82854c53f970c651c162" "5065329951; REALTIME_TRANS_SWITCH=1; FANYI_WORD_SWITCH=1; HISTORY_SW" "ITCH=1; SOUND_SPD_SWITCH=1; SOUND_PREFER_SWITCH=1; Hm_lpvt_64ecd82404" "c51e03dc91cb9e8c025574=1625838257; ab_sr=1.0.1_NzM2MDM1OTRkNmFkN2RlYz" "kwNzYwMzYxYmQ4ZjFhZTNlOGI5ZDliMjRhZTRiODUzMzY5MDIxODcxM2YxZWQwNWY0ZmY" "0NTU4ODRjN2M3MjkwYWIyZWU2ZTcxODE3OWQ5MDM0M2IzZWZhNjkyNDgwN2RkNTU1YTI" "zN2RhYzM1NzMyZTU4OGFkOWNlMjNhYWEwMzc4MzcyNWIxNzM1NTg5ZA==; __yjs_st=" "_Nzc4MmU3Mzk2NDRiYjA4ZTQ4YzY3NjQ3MGZlZmY5OWQ2OThjOTJhZjg2MGUzNjc2NTd" "mN2Y2OTMwYTlhZWJlOGUxOTAwY2E1OTY3MDY3YTg2ZDMwMDYxNTc2OTI4ZjRlNzlmODU" "5NDIzMjdkYzJjYzQ3YWRkOTY3ODJiZDc4NTVjYmQxZWE5ZmRjNjYyOGQ5OWNkZTRmZmY" "5OTk0YWE1OTk1MmEzYWZiN2Y0ZWFjYzI5YTFmMTAzY2Q2OWMyMWJmNzY1YWFmM2ZjYjJ" "mMDg2OTYyNTMzNDRlZjE4YzY2MmFmNDU4ZTdhMWRhODIzY2U1OWM4MWIwYzMzY2E2ZW" "RjYl83XzUxM2E1Yzhk", } query = str(input("请输入要翻译的关键词: ")) # 读取js文件 with open('fanyi_baidu_com.js', 'r') as r: read = r.read() # 使用变量接收js第三方库的方法,并接收读取到的js文件 exe = execjs.compile(read) sign = exe.call("e", query) # 执行js文件 print(sign) # 参数 data = { 'from': 'zh', 'to': 'en', 'query': query, 'transtype': 'realtime', 'simple_means_flag': '3', 'sign': sign, 'token': 'a8e3ac80bd327c34add38ea58ffbcef1', 'domain': 'common', } # print(data) res = requests.post(url, data=data, headers=header).json() print(jsonpath(res, "$..dst")[0]) 完整js文件
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 i = "320305.131321201"; 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) };
