python有道-Python爬去有道翻译

注：传入的类型为POST类型，所以需要使用urllib.parse.urlencode()，将字典转换成URL可用参数；

使用json.loads()，将输出的json格式，转换为字典类型

import urllib.request

import urllib.parse

import json

content = input("请输入要翻译的内容：")

url = "http://fanyi.youdao.com/translate?smartresult=dict&smartresult=rule"

data = {}

data["i"] = content

data["from"] = "AUTO"

data["to"] = "AUTO"

data["smartresult"] = "dict"

data["client"] = "fanyideskweb"

data["salt"] = "1537624423057"

data["sign"] = "0c1989ed937485dd570fc4b5907cf567"

data["doctype"] = "json"

data["version"] = "2.1"

data["keyfrom"] = "fanyi.web"

data["action"] = "FY_BY_REALTIME"

data["typoResult"] = "false"

#因传入的类型为POST类型，所以需要将字典转换为url需要使用的参数

data = urllib.parse.urlencode(data).encode("utf-8")

response = urllib.request.urlopen(url, data)

html = response.read().decode("utf-8")

#将JSON格式转换成字典类型

translate = json.loads(html)

translate_src = translate["translateResult"][0][0]["src"]

translate_Result = translate["translateResult"][0][0]["tgt"]

print("翻译内容：%s" % translate_src)

print("翻译结果：%s" % translate_Result)

==============================使用代理访问======================================

import urllib.request

import urllib.parse

import json

while True:

content = input("请输入要翻译的内容(输入!退出)：")

if content == "!":

break

url = "http://fanyi.youdao.com/translate?smartresult=dict&smartresult=rule"

data = {}

data["i"] = content

data["from"] = "AUTO"

data["to"] = "AUTO"

data["smartresult"] = "dict"

data["client"] = "fanyideskweb"

data["salt"] = "1537624423057"

data["sign"] = "0c1989ed937485dd570fc4b5907cf567"

data["doctype"] = "json"

data["version"] = "2.1"

data["keyfrom"] = "fanyi.web"

data["action"] = "FY_BY_REALTIME"

data["typoResult"] = "false"

#因传入的类型为POST类型，所以需要将字典转换为url需要使用的参数

data = urllib.parse.urlencode(data).encode("utf-8")

#---------------------------------代理---------------------------------------------------

#urllib.request.ProxyHandler的参数师一个数组

proxy_support = urllib.request.ProxyHandler({"https": "27.17.45.90:43411"})

#创建一个opener

opener = urllib.request.build_opener(proxy_support)

#添加user-agent

opener.addheaders = [("User-Agent", "Mozilla/5.0 (Windows NT 10.0; Win64; x64) "

"AppleWebKit/537.36 (KHTML, like Gecko) "

"Chrome/69.0.3497.81 Safari/537.36")]

#全局加载代理IP

urllib.request.install_opener(opener)

#----------------------------------代理结束--------------------------------------------------

req = urllib.request.Request(url, data)

req.add_header("User-Agent", "Mozilla/5.0 (Windows NT 10.0; Win64; x64) "

"AppleWebKit/537.36 (KHTML, like Gecko) "

"Chrome/69.0.3497.81 Safari/537.36")

response = urllib.request.urlopen(req)

html = response.read().decode("utf-8")

#将JSON格式转换成字典类型

translate = json.loads(html)

translate_src = translate["translateResult"][0][0]["src"]

translate_Result = translate["translateResult"][0][0]["tgt"]

print("翻译内容：%s" % translate_src)

print("翻译结果：%s" % translate_Result)

==============================分割线===========================================

1、在运行中报{"errorCode":50}，将审查元素中获取的URL里面，将translate_o的_o去掉就不会报错。

2、data["salt"] = "1537624423057" ：时间戳

3、data["sign"] = "0c1989ed937485dd570fc4b5907cf567" ：时间戳 + 翻译内容加密生成的字符串

4、urllib.error.URLError: ，没有连接到服务器，需要更换代理IP

5、urllib.error.HTTPError: HTTP Error 403: Forbidden：需要添加user-agent