Python爬虫爬取有道实现翻译功能_Python

Python爬虫爬取有道实现翻译功能

准备

首先安装爬虫urllib库

pip install urllib

获取有道翻译的链接url

需要发送的参数在form data里

示例

import urllib.request
import urllib.parse

url = 'http://fanyi.youdao.com/translate_o?smartresult=dict&smartresult=rule'
data = {}
data['i'] = 'i love python'
data['from'] = 'auto'
data['to'] = 'auto'
data['smartresult'] = 'dict'
data['client'] = 'fanyideskweb'
data['salt'] = '16057996372935'
data['sign'] = '0965172abb459f8c7a791df4184bf51c'
data['lts'] = '1605799637293'
data['bv'] = 'f7d97c24a497388db1420108e6c3537b'
data['doctype'] = 'json'
data['version'] = '2.1'
data['keyfrom'] = 'fanyi.web'
data['action'] = 'fy_by_realtlme'
data = urllib.parse.urlencode(data).encode('utf-8')
response = urllib.request.urlopen(url,data)
html = response.read().decode('utf-8')
print(html)

运行会出现50的错误，这里需要将url链接的_o删除掉

删除后运行成功

但是这个结果看起来还是太复杂，需要在进行优化

导入json，然后转换成字典进行过滤

import urllib.request
import urllib.parse
import json

url = 'http://fanyi.youdao.com/translate?smartresult=dict&smartresult=rule'
data = {}
data['i'] = 'i love python'
data['from'] = 'auto'
data['to'] = 'auto'
data['smartresult'] = 'dict'
data['client'] = 'fanyideskweb'
data['salt'] = '16057996372935'
data['sign'] = '0965172abb459f8c7a791df4184bf51c'
data['lts'] = '1605799637293'
data['bv'] = 'f7d97c24a497388db1420108e6c3537b'
data['doctype'] = 'json'
data['version'] = '2.1'
data['keyfrom'] = 'fanyi.web'
data['action'] = 'fy_by_realtlme'
data = urllib.parse.urlencode(data).encode('utf-8')
response = urllib.request.urlopen(url,data)
html = response.read().decode('utf-8')

req = json.loads(html)
result = req['translateresult'][0][0]['tgt']
print(result)

但是这个程序只能翻译一个单词，用完就废了。于是我在进行优化

import urllib.request
import urllib.parse
import json

def translate():
  centens = input('输入要翻译的语句:')
  url = 'http://fanyi.youdao.com/translate?smartresult=dict&smartresult=rule'
  head = {}#增加请求头，防反爬虫
  head['user-agent'] = 'mozilla/5.0 (windows nt 10.0; win64; x64) applewebkit/537.36 (khtml, like gecko) chrome/86.0.4240.198 safari/537.36'
  data = {}#带上from data的数据进行请求
  data['i'] = centens
  data['from'] = 'auto'
  data['to'] = 'auto'
  data['smartresult'] = 'dict'
  data['client'] = 'fanyideskweb'
  data['salt'] = '16057996372935'
  data['sign'] = '0965172abb459f8c7a791df4184bf51c'
  data['lts'] = '1605799637293'
  data['bv'] = 'f7d97c24a497388db1420108e6c3537b'
  data['doctype'] = 'json'
  data['version'] = '2.1'
  data['keyfrom'] = 'fanyi.web'
  data['action'] = 'fy_by_realtlme'
  data = urllib.parse.urlencode(data).encode('utf-8')
  req = urllib.request.request(url,data,head)
  response = urllib.request.urlopen(req)
  html = response.read().decode('utf-8')
  req = json.loads(html)
  result = req['translateresult'][0][0]['tgt']
  # print(f'中英互译的结果：{result}')
  return result
t = translate()
print(f'中英互译的结果：{t}')

优化完成，效果还行。