import hashlib
import random
import time
import requests
from lxml import etree
def get_random_agent():
agent_list = [
"Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; AcooBrowser; .NET CLR 1.1.4322; .NET CLR 2.0.50727)",
"Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.0; Acoo Browser; SLCC1; .NET CLR 2.0.50727; Media Center PC 5.0; .NET CLR 3.0.04506)",
"Mozilla/4.0 (compatible; MSIE 7.0; AOL 9.5; AOLBuild 4337.35; Windows NT 5.1; .NET CLR 1.1.4322; .NET CLR 2.0.50727)",
"Mozilla/5.0 (Windows; U; MSIE 9.0; Windows NT 9.0; en-US)",
"Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Win64; x64; Trident/5.0; .NET CLR 3.5.30729; .NET CLR 3.0.30729; .NET CLR 2.0.50727; Media Center PC 6.0)",
"Mozilla/5.0 (compatible; MSIE 8.0; Windows NT 6.0; Trident/4.0; WOW64; Trident/4.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; .NET CLR 1.0.3705; .NET CLR 1.1.4322)",
"Mozilla/4.0 (compatible; MSIE 7.0b; Windows NT 5.2; .NET CLR 1.1.4322; .NET CLR 2.0.50727; InfoPath.2; .NET CLR 3.0.04506.30)",
"Mozilla/5.0 (Windows; U; Windows NT 5.1; zh-CN) AppleWebKit/523.15 (KHTML, like Gecko, Safari/419.3) Arora/0.3 (Change: 287 c9dfb30)",
"Mozilla/5.0 (X11; U; Linux; en-US) AppleWebKit/527+ (KHTML, like Gecko, Safari/419.3) Arora/0.6",
"Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.8.1.2pre) Gecko/20070215 K-Ninja/2.1.1",
"Mozilla/5.0 (Windows; U; Windows NT 5.1; zh-CN; rv:1.9) Gecko/20080705 Firefox/3.0 Kapiko/3.0",
"Mozilla/5.0 (X11; Linux i686; U;) Gecko/20070322 Kazehakase/0.4.5",
"Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.9.0.8) Gecko Fedora/1.9.0.8-1.fc10 Kazehakase/0.5.6",
"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.56 Safari/535.11",
"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7_3) AppleWebKit/535.20 (KHTML, like Gecko) Chrome/19.0.1036.7 Safari/535.20",
"Opera/9.80 (Macintosh; Intel Mac OS X 10.6.8; U; fr) Presto/2.9.168 Version/11.52",
"Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36"
]
agent = random.choice(agent_list)
return agent
class YouDao():
def get_dom(self):
"""
获取主页的dom信息
:return:
"""
_ = self
url = 'https://fanyi.youdao.com/'
res = requests.get(url).content.decode('utf-8')
html = etree.HTML(res)
languages = html.xpath('//*[@id="langSelect"]//li/@data-value')
languages = [i.split('2') for i in languages]
languages_text = html.xpath('//*[@id="langSelect"]//li//text()')
languages_text = [i.split('\xa0 ? \xa0') for i in languages_text]
langs_en = {}
langs_zh = {}
for i in range(len(languages)):
for j in range(len(languages[i])):
langs_en.update({languages[i][j]: languages_text[i][j]})
langs_zh.update({languages_text[i][j]: languages[i][j]})
print(langs_en)
print(langs_zh)
return langs_en, langs_zh
def get_js(self):
"""
通过这个js文件生成翻译所需的参数, 可以查看都有哪些参数加密
:return:
"""
url = 'https://shared.ydstatic.com/fanyi/newweb/v1.1.8/scripts/newweb/fanyi.min.js'
res = requests.get(url).content.decode('utf-8')
with open('111.js', 'w', encoding='utf-8') as w:
w.write(res)
print(res)
def md_encrypt(self, query):
"""
有道 md 加密
:param query: 需要加密的字符串
:return: 加密后的结果
"""
_ = self
md = hashlib.md5()
md.update(query.encode('utf-8'))
encrypt = md.hexdigest()
return encrypt
def get_data(self, keyword):
"""
获取加密参数
:param keyword:
:return: 返回接口携带的参数 user-agent
"""
t = str(int(time.time() * 1000))
salt = t + str(random.randrange(10))
# s = 'fanyideskweb{}{}Tbh5E8=q6U3EXe+&L[4c@'.format(keyword, salt).encode('utf8')
s = 'fanyideskweb{}{}Y2FYu%TNSbMCxc3t2u^XT'.format(keyword, salt)
sign = self.md_encrypt(s)
# version = '5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/93.0.4577.82 Safari/537.36'
# bv = 'navigator.appVersion 结果为 版本信息'
user_agent = get_random_agent()
bv = self.md_encrypt(user_agent)
data = {
'i': keyword,
'from': 'en',
# 'from': 'AUTO',
'to': 'zh-CHS',
# 'to': 'AUTO',
'smartresult': 'dict',
'client': 'fanyideskweb',
'salt': salt,
'sign': sign,
'lts': str(int(time.time() * 1000)),
'bv': bv,
# 'bv': '3530cfa5c901d5d46408a6c23db771c2',
'doctype': 'json',
'version': '2.1',
'keyfrom': 'fanyi.web',
'action': 'FY_BY_REALTlME'
}
return data, user_agent
def translate(self, keyword):
"""
有道翻译
:param keyword: 要翻译的句子
:return: 翻译的结果
"""
data, user_agent = self.get_data(keyword)
headers = {
'Accept': 'application/json, text/javascript, */*; q=0.01',
'Accept-Encoding': 'gzip, deflate, br',
'Connection': 'keep-alive',
'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8',
'Cookie': 'P_INFO=null; OUTFOX_SEARCH_USER_ID=-2068944752@10.108.160.133; OUTFOX_SEARCH_USER_ID_NCOO=1275392645.9123814; JSESSIONID=aaaztdtL28PLLa_IHe0Xx; ___rl__test__cookies=1634035626358',
'Host': 'fanyi.youdao.com',
'Origin': 'https://fanyi.youdao.com',
'Referer': 'https://fanyi.youdao.com/',
# 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/93.0.4577.82 Safari/537.36',
'User-Agent': user_agent,
'X-Requested-With': 'XMLHttpRequest',
}
url = 'https://fanyi.youdao.com/translate_o?smartresult=dict&smartresult=rule'
res = requests.post(url, headers=headers, data=data).json()
translateResult = res.get('translateResult')[0][0]
tgt = translateResult.get('tgt')
src = translateResult.get('src')
print(' tgt:{} \n src:{}'.format(tgt, src))
return tgt, src
if __name__ == '__main__':
keyword = 'NOMINATIONS SENT TO THE SENATE'
YouDao().get_dom()
YouDao().translate(keyword)