Python爬虫实现多语言翻译词典

【推荐】2019 Java 开发者跳槽指南.pdf(吐血整理) >>>

代码如下：

import urllib.request
from lxml.html import etree
import os
from urllib.parse import urlencode

def InputWord(step, type = 0):
_type = type
if step == 1:
_type = input("\n1.中 => 英\n2.英 => 中\n3.中 => 日\n4.日 => 中\n(1/2/3/4)请选择：")
if _type != '1' and _type != '2' and _type != '3' and _type != '4':
InputWord(step, 0)

step = 2
tips = '\n请输入要查询的中文(输入*返回上一级)：'
tmp_url = 'https://dict.youdao.com/w/{a}/'
data_xpath = '//*[@id="phrsListTab"]/div/ul/p/span/a/text()'

if _type == '2':
tips = '\n请输入要查询的英文(输入*返回上一级)：'
data_xpath = '//*[@id="phrsListTab"]/div/ul/li/text()'
if _type == '3':
tmp_url = 'https://dict.youdao.com/w/jap/{a}/'
data_xpath = '//div/ul/li/p[@class="sense-title"]/text()'
if _type == '4':
tips = '\n请输入要查询的日文(输入*返回上一级)：'
tmp_url = 'https://dict.youdao.com/w/jap/{a}/'
data_xpath = '//div/ul/li/span[@class="field"]/text()'

word = input(tips)

if str(word) == '*':
InputWord(1, 0)

params = {
"value": word.replace(' ', '-')
}
url = tmp_url.format(a=urlencode(params)[6:urlencode(params).__len__()])

req = urllib.request.Request(url)
req.add_header('User-Agent', 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/79.0.3945.88 Safari/537.36')
response = urllib.request.urlopen(req)
html = response.read().decode('utf-8')

data = etree.HTML(html).xpath(data_xpath)

if not data:
print("未能查询到结果")

else:
print('===================================\n查询结果:')
for d in data:
print(d)

print('===================================')

InputWord(step, _type)

InputWord(1, 0)

os.system('pause')

实现结果：