準備

首先安裝爬蟲urllib庫

pip install urllib

獲取有道翻譯的連結url

需要傳送的引數在form data裡

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)

執行會出現50的錯誤，這裡需要將url連結的_o刪除掉

刪除後執行成功

但是這個結果看起來還是太複雜，需要在進行優化

匯入json，然後轉換成字典進行過濾

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)

但是這個程式只能翻譯一個單詞，用完就廢了。於是我在進行優化

import urllib.request
import urllib.parse
import json

def translate():
  centens = input('輸入要翻譯的語句:')
  url = 'http://fanyi.youdao.com/translate?smartresult=dict&smartresult=rule'
  head = {}#增加請求頭，防反爬蟲
  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 = {}#帶上from data的資料進行請求
  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'中英互譯的結果：{result}')
  return result
t = translate()
print(f'中英互譯的結果：{t}')

優化完成，效果還行。

以上就是本文的全部內容，希望對大家的學習有所幫助，也希望大家多多支援我們。