通过Python爬虫获取【小说网站GUI】数据，保姆级教学

import requests
import parsel
import uuid
import time
import random
import os
from tkinter import *
import threading
import tkinter.messagebox as messagebox
import tkinter as tk
from tkinter import ttk

root = Tk()

# 进度条count
barCount = []

screenwidth = root.winfo_screenwidth()
screenheight = root.winfo_screenheight()
dialog_width = 800
dialog_height = 220
# 前两个参数是窗口的大小，后面两个参数是窗口的位置
root.geometry(
    "%dx%d+%d+%d" % (dialog_width, dialog_height, (screenwidth - dialog_width) / 2, (screenheight - dialog_height) / 2))

root.title("(红目香薰提供)主页地址：【https://laoshifu.blog.csdn.net/】")
Label(root, text='例如：https://book.zongheng.com/book/1228049.html中的【1228049】一组数字').grid(row=0, column=0)

Label(root, text='url：输入文章id即可').grid(row=1, column=0)
e = Entry(root, width=100)
e.grid(row=3, column=0, padx=15, pady=5)

root.resizable(height=False, width=False)

headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/78.0.3904.108 Safari/537.36'
}

listChild = []
listDate = []
mTitle = []
# 文章链接与标题独立列表
a_href_list = ["", ""]
# 存放文章链接与标题数组列表
a_href_arr = []
# 存放文章全文
infoDate = []


def GetUrl(url):
    try:
        html = requests.get(url, headers=headers)
        sel = parsel.Selector(html.text)
        # 获取主Title
        mTitle.append(sel.css(".book-meta h1::text").getall()[0])
        href = sel.css(".volume-list ul a::attr(href)").getall()
        # 获取标题
        text = sel.css(".volume-list ul a::text").getall()
        for item1, item2 in zip(href, text):
            a_href_list = ["", ""]
            a_href_list[0] = item1
            a_href_list[1] = item2
            a_href_arr.append(a_href_list)
        print("列表获取完毕")
    except:
        print("解析异常")


def GetTxt(url, title):
    html = requests.get(url, headers=headers)
    sel = parsel.Selector(html.text)
    # 文章
    info = sel.css(".content p::text").getall()
    infoDate.append(title + "\r\n")
    for item in info:
        infoDate.append(item + "\r\n")


def show():
    """
    开启线程1,2
    :return:
    """
    t1 = threading.Thread(target=showFun, name="T1")
    t2 = threading.Thread(target=startThread, name="T2")
    t1.start()
    t2.start()


def showFun():
    try:
        # 获取的文本
        oldUrl = e.get()
        # 1159606
        bookIdDir = "https://book.zongheng.com/showchapter/{0}.html".format(oldUrl)
        GetUrl(bookIdDir)

        for item in a_href_arr:
            barCount.append("1")
            GetTxt(item[0], item[1])
            print(item[1], "获取文章完毕")
            time.sleep(random.uniform(0.5, 1.5))

        with open(str.format("{0}.txt", mTitle[0]), "w+", encoding="utf-8") as f:
            f.write("".join(infoDate))
            f.close()
        os.system("explorer .")
        messagebox.showinfo("提示", str.format("{0}.txt", mTitle[0]), "保存完毕")
    except:
        print("列表获取结束")


def find():
    """打开默认页面"""
    os.system(
        '"C:/Program Files/Internet Explorer/iexplore.exe" https://book.zongheng.com/store/c0/c0/b0/u21/p1/v0/s1/t0/u0/i1/ALL.html')


def startThread():
    """进度条读条"""
    time.sleep(2)
    bar["value"] = 0
    while True:
        if len(a_href_arr) > 1:
            go = (float(len(barCount)) / len(a_href_arr)) * 100
            bar["value"] = go
            bar.Progress = "{0}%".format(go)
            root.update()
            time.sleep(5)
            if go > 99:
                break


Button(root, text='小说下载', width=10, command=show).grid(row=4, column=0, padx=10, pady=5)
Button(root, text='查找小说', width=10, command=find).grid(row=5, column=0, padx=10, pady=5)
Label(root, text='程序进度条').grid(row=6, column=0)

bar = ttk.Progressbar(root, length=600, cursor='spider', mode="determinate", maximum=100, orient=tk.HORIZONTAL)
bar.grid(row=7, column=0)
mainloop()