有道翻译和百度翻译在线爬取

import requests
import time
import random
from hashlib import md5


def get_salt_sign_ts(word):
    ts = str(int(time.time() * 1000))
    salt = ts + str(random.randint(0, 9))
    string = "fanyideskweb" + word + salt + "n%A-rKaT5fb[Gy?;N5@Tj"
    s = md5()
    s.update(string.encode())
    sign = s.hexdigest()

    return salt, ts, sign


def attack_yd(word):
    salt, ts, sign = get_salt_sign_ts(word)
    url = \'http://fanyi.youdao.com/translate_o?smartresult=dict&smartresult=rule\'
    headers = {
        \'Accept\': \'image/webp,image/apng,image/*,*/*;q=0.8\',
        \'Accept-Encoding\': \'gzip, deflate\',
        \'Accept-Language\': \'zh-CN,zh;q=0.9,en;q=0.8\',
        \'Connection\': \'keep-alive\',
        \'Cookie\': \'OUTFOX_SEARCH_USER_ID=1966607151@10.169.0.83; OUTFOX_SEARCH_USER_ID_NCOO=250069037.7227244; JSESSIONID=aaakkyCArmplF4qJhJHWw; DICT_UGC=be3af0da19b5c5e6aa4e17bd8d90b28a|; JSESSIONID=abc9CfcjVp7bS6v1XUIWw; ___rl__test__cookies=1563952124524\',
        \'Host\': \'fanyi.youdao.com\',
        \'Referer\': \'http://fanyi.youdao.com/\',
        \'User-Agent\': \'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.142 Safari/537.36\',
    }
    data = {
        \'i\': word,
        \'from\': \'AUTO\',
        \'to\': \'AUTO\',
        \'smartresult\': \'dict\',
        \'client\': \'fanyideskweb\',
        \'salt\': salt,
        \'sign\': sign,
        \'ts\': ts,
        # \'bv\': \'6cf12640614e68ba598ee58ceccb0605\',
        # \'doctype\': \'json\',
        # \'version\': \'2.1\',
        \'keyfrom\': \'fanyi.web\',
        \'action\': \'FY_BY_REALTlME\',
    }
    html_json = requests.post(url, data=data, headers=headers).json()
    return html_json[\'translateResult\'][0][0]


if __name__ == \'__main__\':
    word = input(\'请输入要翻译的单词：\')
    result = attack_yd(word)
    print(result)

请输入要翻译的单词：你好
{\'tgt\': \'hello\', \'src\': \'你好\'}

 

import requests
import re
import execjs


class BaiduTranslateSpider:
    def __init__(self):
        self.get_url = \'https://fanyi.baidu.com/?aldtype=16047\'
        self.headers = {
            \'accept\': \'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3\',
            \'accept-encoding\': \'gzip, deflate, br\',
            \'accept-language\': \'zh-CN,zh;q=0.9,en;q=0.8\',
            \'cookie\': \'BAIDUID=68E904D92F2C8ACC62C7542C397FBD0B:FG=1; PSTM=1561529234; BIDUPSID=2633580F87BCDFE102C31514DA3EACA6; BDUSS=HdWTDhTajh0ZTd3QmFIbzZjeDdhTTE5Wkd0R1FGcFFSaDFJVVRRSHN3ZjNnbGRkSVFBQUFBJCQAAAAAAAAAAAEAAADE7I5C06LTwrDUxvjLq9fTAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAPf1L1339S9dM; BDORZ=B490B5EBF6F3CD402E515D22BCDA1598; locale=zh; REALTIME_TRANS_SWITCH=1; FANYI_WORD_SWITCH=1; HISTORY_SWITCH=1; SOUND_SPD_SWITCH=1; SOUND_PREFER_SWITCH=1; BDRCVFR[feWj1Vr5u3D]=I67x6TjHwwYf0; delPer=0; PSINO=3; H_PS_PSSID=29546_1466_21083_29578_29519_28518_29099_29568_28835_29221_29460_22157; Hm_lvt_64ecd82404c51e03dc91cb9e8c025574=1563869496,1563869600,1563953532,1564019873; to_lang_often=%5B%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; from_lang_often=%5B%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; yjs_js_security_passport=47e142eebb082b8c92ef506657211ad704b97215_1564026801_js; Hm_lpvt_64ecd82404c51e03dc91cb9e8c025574=1564026808\',
            \'upgrade-insecure-requests\': \'1\',
            \'user-agent\': \'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.142 Safari/537.36\',
        }

    # 获取token
    def get_token(self):
        html = requests.get(url=self.get_url, headers=self.headers).text
        # 用正则解析
        pattern = re.compile(r"token: \'(.*?)\'", re.S)
        token = pattern.findall(html)
        print(token)

    # 获取sign
    def get_sign(self, word):
        with open(\'./node.js\', \'r\') as f:
            js_data = f.read()
        execjs_obj = execjs.compile(js_data)
        sign = execjs_obj.eval(\'e("{}")\'.format(word))

        return sign

    # 获取翻译结果
    def get_result(self, word, fro, to):
        token = self.get_token()
        sign = self.get_sign(word)
        # 把formdata定义成字典
        formdata = {
            \'from\': fro,
            \'to\': to,
            \'query\': word,
            \'transtype\': \'realtime\',
            \'simple_means_flag\': \'3\',
            \'sign\': sign,
            \'token\': token
        }
        html_json = requests.post(url=\'https://fanyi.baidu.com/v2transapi\', data=formdata, headers=self.headers).json()
        return html_json[\'trans_result\'][\'data\'][0][\'dst\']


if __name__ == \'__main__\':
    spider = BaiduTranslateSpider()
    num = input(\'1.翻译英语，2.翻译汉语，请选择（1/2）：\')
    if num == \'1\':
        fro = \'zh\'
        to = \'en\'
    else:
        fro = \'en\'
        to = \'zh\'
    word = input(\'请输入要翻译的单词:\')
    result = spider.get_result(word, \'zh\', \'en\')
    print(result)