爬虫二：有道翻译

import time,random,json
from func_all import post
#md5加密函数
def md5(need_str):
    import hashlib
    # 创建md5对象
    md5_o = hashlib.md5()
    # 需要有bytes, 作为参数
    sign_bytes = need_str.encode('utf-8')
    # print(type(sign_bytes))
    # 更新md5 object的值
    md5_o.update(sign_bytes)
    sign_str = md5_o.hexdigest()
    return sign_str
def translate(kw):
    #url
    url = 'http://fanyi.youdao.com/translate_o?smartresult=dict&smartresult=rule'
    headers = {
         'Accept': 'application/json, text/javascript, */*; q=0.01',
         'Accept-Language': 'zh-CN,zh;q=0.9',
         'Connection': 'keep-alive',
         'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8',
         'Cookie': 'OUTFOX_SEARCH_USER_ID=298855370@10.169.0.83; OUTFOX_SEARCH_USER_ID_NCOO=854769824.938877; fanyi-ad-id=47865; fanyi-ad-closed=1; JSESSIONID=aaakqE9hTCGkigY9vw2uw; ___rl__test__cookies=1534216152192',
         'Host': 'fanyi.youdao.com',
         'Origin': 'http://fanyi.youdao.com',
         'Referer': 'http://fanyi.youdao.com/',
         'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/68.0.3440.84 Safari/537.36',
         'X-Requested-With': 'XMLHttpRequest',
     }
     # form 的生成1. i 需要确定, 2, salt, 3, sign
     key = kw
     # salt : ((new Date).getTime() + parseInt(10 * Math.random(), 10))
     salt = int(time.time()*1000 + random.randint(0,10))
     salt_str = str(salt)
     # sign : o = u.md5(S + n + r + D);
     # S = "fanyideskweb"
     # D = "ebSeFb%=XZ%T[KZ)c(sy!"
     # n = key
     # r = salt_str
     S = "fanyideskweb"
     D = "ebSeFb%=XZ%T[KZ)c(sy!"
     sign_str = S + key + salt_str + D
     # 调用md5加密
     sign_str = md5(sign_str)
     form = {
        'i': key,
        'from': 'AUTO',
        'to': 'AUTO',
        'smartresult': 'dict',
        'client': 'fanyideskweb',
        'salt': salt_str,
        'sign': sign_str,
        'doctype': 'json',
        'version': '2.1',
        'keyfrom': 'fanyi.web',
        'action': 'FY_BY_REALTIME',
        'typoResult': 'false',
    }
    html_bytes = post(url,form,headers=headers)
    #将json类型的字符创转换为字典
    res_dict = json.loads(html_bytes.decode('utf-8'))
    translate_res = res_dict['translateResult'][0][0]['tgt']
    return translate_res

if __name__ == '__main__':
    kw = input('请输入要翻译的内容:')
    ret = translate(kw=kw)
    print(kw + '的翻译是:' + ret)

导入的模块func_all

from urllib import request,parse
from urllib.error import HTTPError,URLError

# get请求函数
def get(url,headers=None):
    return urlrequest(url,headers=headers)

# post请求函数
def post(url,form,headers=None):
    return urlrequest(url,form,headers=headers)

def urlrequest(url,form=None,headers=None):
    user_agent = 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/68.0.3440.84 Safari/537.36'
    if headers == None:
        headers = {
            "User-Agent": user_agent
        }
    html_byte = b''
    # 异常处理
    try:
        if form:
            # POST请求
            # 转换成str
            form_str = parse.urlencode(form)
            # 转换成bytes
            form_bytes = form_str.encode('utf-8')
            req = request.Request(url, data=form_bytes, headers=headers)
        else:
            # get请求
            req = request.Request(url, headers=headers)
        # 发送请求
        response = request.urlopen(req)
        html_byte = response.read()
    except HTTPError as e:
        print(e)
    except URLError as e:
        print(e)
    return html_byte
if __name__ == "__main__":
    url = "http://fanyi.baidu.com/sug"
    data = {
            'kw': '呵呵'
        }
    html_byte = post(url,form=data)
    print(html_byte)
    # url = "http://www.baidu.com"
    # html_byte = get(url)
    # print(html_byte.decode('utf-8'))