拿python写一个考研英语大纲词汇查询exe

本来想找个资源，找来找去，没找到，只找到一个

https://kaoyan.koolearn.com/20190131/1035624.html

里面是19年的，然后110个网址，，，每个里面大约50个词。

爬虫吧，边查边写，写了俩小时。。

主要是，这鬼东西，里面还有网址嵌套、、想找个现成的方法、、结果没找着，自己写了一个

clear

写文件的时候也出问题了，说txt是gbk编码，utf-8有问题、、就搜了个codecs.open()打开文件

#-*- coding:UTF-8 -*-
import requests
import re

url = "https://kaoyan.koolearn.com/20190131/1035624.html"

res = requests.get(url)

print(res.status_code)
#打印变量res的响应状态码，以检查请求是否成功

#print(res.text)
res = res.content.decode(encoding='utf-8')


#print('')
#print(res)

c = re.findall(r'http://kaoyan.koolearn.com/2019..../.......\.html',res)
#for i in c:
#    print(i)
#print(len(c))

def get_url(url):
    res = res = requests.get(url)
    res = res.content.decode(encoding='utf-8')
    res = re.findall(r'<p style="white-space: normal;">　　(..*?)</p>',res)
    return res
    #for i in res:
    #    print(i)
    #print(res)
def clear_inner(s):
    if '<' not in s:
        return s
    l_l,r_l,r_l,r_r = [-1,-1,-1,-1]
    for i in range(len(s)):
        if s[i] == '<':
            if l_l == -1:
                l_l = i
            else:
                l_r = i
        elif s[i] == '>':
            if r_l == -1:
                r_l = i
            else:
                r_r = i
    if -1 in [l_l,r_l,r_l,r_r]:
        return s
    #print(l_l,l_r,r_l,r_r)
    #print(s[:l_l])
    #print(s[r_l+1:l_r])
    #print(s[r_r+1:])
    return s[:l_l]+s[r_l+1:l_r]+s[r_r+1:]
#print(c[1])
print(c[18])
c.remove(c[0])
#c[0]是本身
#x = get_url(c[18])
#print(x[6])
#print(clear_inner(x[6]))

#for i in get_url(c[31]):
#    print(i)
#    print(clear_inner(i))

#print()
#print(len(c))
import codecs
#with codecs.open(write_fileroute,'a',encoding='utf-8') as f:
#    f.write(u'要写入文件的内容'）


with codecs.open("a.txt",'w',encoding='utf-8') as f:
    cnt = 0
    for j in c:
        for i in get_url(j):
            f.write(clear_inner(i)+'\n')
        cnt = cnt+1
        print(cnt)

 

这样爬完之后，写一个py代码

代码找的现成的gui编程链接、

改了改

就是输入单词或者意思，自动填充另一个，例如输入单词abandon，在下面自动填充 遗弃，或者反过来

考虑到根据意思反过来找单词会有多个，所以加了分号作为间隔，并且通过意思找很不稳定，毕竟，匹配的是通过

找字串来的，而不是真正理解了意思，

 

# -*- coding:utf-8 -*-
import wx
import codecs

class MyFrame(wx.Frame):
    def __init__(self,  parent,  id):
        wx.Frame.__init__(self,  parent,  id,  '单词查找',  size=(400,  300))
        # 创建面板
        panel = wx.Panel(self)

        # 创建 data 变量储存数据
        self.data = []

        # 使用方法读取数据
        self.GetData()
        
        # 创建“确定”和“清除”按钮, 并绑定事件
        self.bt_confirm = wx.Button(panel,  label='确定')
        self.bt_confirm.Bind(wx.EVT_BUTTON, self.OnclickSubmit)
        self.bt_clear = wx.Button(panel,  label='清除')
        self.bt_clear.Bind(wx.EVT_BUTTON, self.OnclickClear)

        # 创建文本，左对齐        
        self.title = wx.StaticText(panel,  label="请输入单词或意思")
        self.label_English = wx.StaticText(panel,  label="单词:")
        self.text_English = wx.TextCtrl(panel,  style=wx.TE_LEFT)
        self.label_Chinese = wx.StaticText(panel,  label="意思:")
        self.text_Chinese = wx.TextCtrl(panel,  style=wx.TE_LEFT)
        # 添加容器，容器中控件按横向并排排列
        hsizer_English = wx.BoxSizer(wx.HORIZONTAL)
        hsizer_English.Add(self.label_English,  proportion=0,  flag=wx.ALL,  border=5)
        hsizer_English.Add(self.text_English,  proportion=1,  flag=wx.ALL,  border=5)
        hsizer_Chinese = wx.BoxSizer(wx.HORIZONTAL)
        hsizer_Chinese.Add(self.label_Chinese,  proportion=0,  flag=wx.ALL,  border=5)
        hsizer_Chinese.Add(self.text_Chinese,  proportion=1,  flag=wx.ALL,  border=5)
        hsizer_button = wx.BoxSizer(wx.HORIZONTAL)
        hsizer_button.Add(self.bt_confirm,  proportion=0,  flag=wx.ALIGN_CENTER,  border=5)
        hsizer_button.Add(self.bt_clear,  proportion=0,  flag=wx.ALIGN_CENTER,  border=5)
        # 添加容器，容器中控件按纵向并排排列
        vsizer_all = wx.BoxSizer(wx.VERTICAL)
        vsizer_all.Add(self.title,  proportion=0,  flag=wx.BOTTOM | wx.TOP | wx.ALIGN_CENTER, 
                        border=15)
        vsizer_all.Add(hsizer_English,  proportion=0,  flag=wx.EXPAND | wx.LEFT | wx.RIGHT,  border=45)
        vsizer_all.Add(hsizer_Chinese,  proportion=0,  flag=wx.EXPAND | wx.LEFT | wx.RIGHT,  border=45)
        vsizer_all.Add(hsizer_button,  proportion=0,  flag=wx.ALIGN_CENTER | wx.TOP,  border=15)
        panel.SetSizer(vsizer_all)

    def OnclickSubmit(self, event):
        """ 点击确定按钮，执行方法 """
        English = self.text_English.GetValue()
        Chinese = self.text_Chinese.GetValue()
        if English == "":
            ans = []
            for line in self.data:
                pos = line.find(Chinese)
                if pos != -1:
                    x = line.split()
                    ans.append(x[1])
            self.text_English.SetValue(";".join(ans))   
        else:
            for line in self.data:
                x = line.split()
                if English in x:
                    self.text_Chinese.SetValue("".join(x[2:]))
    def OnclickClear(self,event):
        """点击清除按钮，执行方法"""
        self.text_English.SetValue("")
        self.text_Chinese.SetValue("")
        

    def GetData(self):
        with codecs.open("a.txt",'r',encoding='utf-8') as f:
            self.data = f.readlines()
        if self.data == []:
            message = "请检查a.txt文件是否为空" #数据文件有问题
            wx.MessageBox(message)


if __name__ == '__main__':
    app = wx.App()                      # 初始化
    frame = MyFrame(parent=None, id=-1)  # 实例MyFrame类，并传递参数    
    frame.Show()                        # 显示窗口
    app.MainLoop()                      # 调用主循环方法

然后看到评论说可以打包成exe，就又搜了下

链接、

就是先

pip install pyinstaller

然后cmd打开进入到py目录下，这里因为使用了第三方库，即wx，所以把wx复制到py文件同一目录下

Pyinstaller -F -w main.py

等待完成，哦，对了记得把a.txt手动拿到exe同一目录下

然后就完成了