爬取百度（有道）翻译

爬取百度（有道）翻译

难点是分析动态网页（抓包），找出url。

#coding=utf-8import requests
import jsonclass BaiDuTranslatePhone:def __init__(self):self.query=input("请输入要翻译的内容：")self.url = ""self.data={"query": self.query,"from": "zh","to": "en"}self.headers={"Host": "fanyi.baidu","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": "/?aldtype=16047"}def run(self):post_response = requests.post(url=self.url, data=self.data, headers=self.headers)self.strs = t.decode()#print(self.strs)#print("self.strs type:"+str(type(self.strs)))def get_result(self):result_dict = json.loads(self.strs)#print("result_dict type:"+str(type(result_dict)))result=result_dict['trans'][0]['dst'] if len(result_dict['trans']) > 0 else Noneprint("翻译结果为：")print(result)if __name__ == '__main__':while True:translate=BaiDuTranslatePhone()translate.run()_result()

百度翻译

import requests
import jsonurl = ""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",
}data = {'from':'zh','to':'en','query':'我是大叔',
}response = requests.post(url,data = data,headers = headers)r = #print(r)h = json.loads(r)#str转dic类型#print(h)result = h['trans'][0]['dst']print(result)

有道翻译

import requests
import jsonurl = '=dict&smartresult=rule'headers = {'User-Agent':'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36(KHTML, like Gecko) Chrome/63.0.3239.26 Safari/537.36 Core/1.63.6776.400 QQBrowser/10.3.2577.400'
}def translate():content = input('输入要翻译的内容：')data = {'i':content ,  'from':'AUTO','to':'AUTO','doctype':'json'}response = requests.post(url,data = data, headers = headers)r = h = json.loads(r)print('翻译结果是：',h['translateResult'][0][0]['tgt'])if __name__ == '__main__':while 1:translate()op = input('是否要继续翻译，Y/继续， N/停止：')if op == 'Y':continueelse:break