爬虫-有道翻译

 
  
# !/usr/bin/python
# -*- encoding: UTF-8 -*-
import urllib
import urllib2
headers={"X-Requested-With":"XMLHttpRequest",
"User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/60.0.3112.113 Safari/537.36",
"Content-Type":"application/x-www-form-urlencoded; charset=UTF-8"}#也可以使用代理headers={"User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/60.0.3112.113 Safari/537.36"}

url="http://fanyi.youdao.com/translate?smartresult=dict&smartresult=rule"
print u"请输入需要翻译的文字:",
key=raw_input()#外部输入的key是简体中文格式(gb2312的编码)
fromdata={"from":"AUTO",
"to":"AUTO",
"i":key.decode("gb2312"),#把gb2312编码格式的key解码成这个程序可以识别的unicode格式(包含utf-8格式)
"doctype":"json",
"version":"2.1",
"keyfrom":"fanyi.web",
"action":"FY_BY_CLICKBUTTION",
"typoResult":"true"}
data = urllib.urlencode(fromdata)
request=urllib2.Request(url,data)
response = urllib2.urlopen(request)
html = response.read()

print html.encode("gb2312")#把这个程序跑出来的程序(unicode格式)打印到终端上,终端是cmd是识别简体中文(gb2312编码),所以把结果编码成gb2312格式的,这样中文的结果才能显示出来

结果打印的是json格式的
结果是:
{"type":"FR2ZH_CN","errorCode":0,"elapsedTime":34,"translateResult":[[{"src":"??python","tgt":"? ?巨蟒"}]]}
在json在线解析器http://www.json.cn/中显示出来的是:
{
    "type":"FR2ZH_CN",
    "errorCode":0,
    "elapsedTime":34,
    "translateResult":[
        [
            {
                "src":"??python",
                "tgt":"? ?巨蟒"
            }
        ]
    ]
}
如果是出现{"errorCode":50}这是因为访问的链接需要密码
只要把07.url = 'http://fanyi.youdao.com/translate_o?smartresult=dict&smartresult=rule&sessionFrom=null'中translate_o?后面的“_o”去掉就好了,其他比如时间戳什么的都不用改。其他的URL也是一样,去掉“_o”就好

 
  
 
 

你可能感兴趣的:(python学习)