Python爬虫实现翻译功能

前言

学了这么久的python理论知识，需要开始实战来练手巩固了。

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。

巴特西

Python爬虫实现翻译功能

前言

准备

示例

最新文章

热门文章