使用爬虫利用有道翻译网站做一个翻译接口
import urllib.request
import http.client
import re
from urllib import request,parse
def getTInfo(key):
# 通过抓包的方式获取的url,并不是浏览器上显示的url
url = "http://fanyi.youdao.com/translate?smartresult=dict&smartresult=rule&smartresult=ugc&sessionFrom=null"
# 完整的headers
headers = {
"Accept" : "application/json, text/javascript, */*; q=0.01",
"X-Requested-With" : "XMLHttpRequest",
# 这里可以导入上次写的User-Agent池
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64; rv:45.0) Gecko/20100101 Firefox/45.0",
"Content-Type" : "application/x-www-form-urlencoded; charset=UTF-8",
}
formdata = {
"i":key,
"from":"auto",
"to":"auto",
"smartresult":"dict",
"client":"fanyideskweb",
"salt":"1511219405946",
"sign":"f8965f67a1d3eee8a69ddf8ccc5f582b",
"doctype":"json",
"version":"2.1",
"keyfrom":"fanyi.web",
"action":"FY_BY_REALTIME",
"typoResult":"false"
}
# 做一次urlencode
data=bytes(parse.urlencode(formdata),encoding='utf-8')
#利用Request将headers,dict,data整合成一个对象传入urlopen
req = request.Request(url,data,headers,method='POST')
response=request.urlopen(req)
info = response.read().decode('utf-8') # 这里需要做一次utf-8的转码
# 因为这里需要对信息做文本的处理
# 使用正则表达式提取翻译出的信息
strRule = re.compile('"tgt":(.*?)}')
info2 = strRule.findall(info)
for i in info2:
i = i.replace('"',"")
return info2[0]
# 执法仪输入的单词
#if __name__ == "__main__":
# info = input("请输入您要翻译的英文单词:")
# print(getTInfo(info))
def info(object, spacing=15, collapse=0):
"""
Print methods and doc strings. Take module, class,
dictionary, or string.
"""
# 遍历一遍object对象,把里面的可以被调用的方法提取出来
methodList = [method for method in dir(object)
if callable(getattr(object, method))]
# 把要提取出来的方法以更好看的,多行变单行
#collapse可以控制打印的信息是否换行
#collapse = 1,并行
#collapse = 0,保持原来的显示
processFunc = collapse and (lambda s:" ".join(s.split())) or (lambda s:s)
print('\n'.join(["%s %s"%(method.ljust(spacing), processFunc(getTInfo(getattr(object, method).__doc__))) for method in methodList]))
# 测试代码
# 运行出来的结果,当然只能作为参考
提供给像我这样英语不好的同学查方法用