Python爬蟲足彩網(wǎng)站賠率數(shù)據(jù)Excel文件自動(dòng)定時(shí)下載（Tkinter+BeautifulSoup+Selenium隱藏瀏覽器界面，雙線程）

朋友為了分析足彩的實(shí)時(shí)賠率，需要每隔一段時(shí)間自動(dòng)下載網(wǎng)站上的excel數(shù)據(jù)。因此開發(fā)了這款軟件。

總共就3個(gè)代碼塊，以下是完整源代碼。

1.第一步：創(chuàng)建應(yīng)用程序界面

import tkinter as tk
from tkinter import messagebox
import tkinter.scrolledtext as scrolledtext
import auto_download
import threading

# 創(chuàng)建一個(gè)全局變量來存儲(chǔ)線程對(duì)象
thread = None
running = False  # 用于控制線程是否繼續(xù)執(zhí)行的標(biāo)志


def start_selenium(callback,download_callback):
    auto_download.main(time_entry.get(), callback,download_callback)
    update_progress('程序開始運(yùn)行。')

def start_program():
    global thread, running
    try:
        duration = int(time_entry.get())
        if duration <= 0:
            raise ValueError
        start_button.config(state="disabled")
        time_entry.config(state="disabled")
        root.after(duration * 1000, enable_button)

        # 設(shè)置標(biāo)志為True，表示線程可以繼續(xù)執(zhí)行
        running = True
        def download():
            while running:
                #傳遞回調(diào)函數(shù)
                start_selenium(update_progress,download_excel_callback)

        def run_in_thread():
            global thread
            thread = threading.Thread(target=download)
            thread.daemon = True  # 設(shè)置線程為守護(hù)線程，主線程退出后會(huì)自動(dòng)退出子線程
            thread.start()

        run_in_thread()
    except ValueError:
        messagebox.showerror("錯(cuò)誤", "請(qǐng)輸入有效的定時(shí)時(shí)間（大于0的整數(shù)）！")
        time_entry.delete(0, tk.END)
        time_entry.focus()

def enable_button():
    start_button.config(state="normal")
    time_entry.config(state="normal")

def update_progress(info):
    text_widget.insert(tk.END, info + "\n")
    text_widget.see(tk.END)  # 滾動(dòng)至最底部
    text_widget.update()  # 更新文本框
def download_excel_callback(info):  # 定義下載回調(diào)函數(shù)
    text_widget.insert(tk.END, info + "\n")
    text_widget.see(tk.END)  # 滾動(dòng)至最底部
    text_widget.update()  # 更新文本框

def on_closing():
    global running
    # 在窗體關(guān)閉時(shí)修改標(biāo)志為False，停止線程的執(zhí)行
    running = False
    root.quit()  # 使用root.quit()代替root.destroy()

root = tk.Tk()
root.title("Selenium程序執(zhí)行界面")
root.geometry("400x250")

# 定時(shí)時(shí)間標(biāo)簽和文本框
time_label = tk.Label(root, text="執(zhí)行頻率（min）：")
time_label.grid(row=0, column=0, sticky="E", pady=10)

time_entry = tk.Entry(root, justify='right')
time_entry.insert(tk.END, '60')
time_entry.grid(row=0, column=1, padx=0, pady=10)

# 多行文本框
text_widget = scrolledtext.ScrolledText(root, height=10,width=51)
text_widget.grid(row=1, columnspan=2, padx=15, pady=5)

# 開始按鈕
start_button = tk.Button(root, text="開始", command=start_program)
start_button.grid(row=2, columnspan=2, pady=10)

root.protocol("WM_DELETE_WINDOW", on_closing)
root.mainloop()

2第二步：獲所有需要下載的URL并添加到列表。循環(huán)列表。

import requests
from bs4 import BeautifulSoup
import download_excel
import os
import datetime
import time

def main(m,callback,download_callback):
    callback('程序開始...')
    n=0
    while True:
        n=n+1
        callback('開始第%s次嘗試...'%n)
        url = 'https://trade.500.com/jczq/'
        callback(url)
        soup=None
        try:
            response = requests.get(url)
            response.raise_for_status()  # 檢查請(qǐng)求是否成功，如果不是則拋出異常
            soup = BeautifulSoup(response.content, 'html.parser')

            # 進(jìn)一步處理頁面內(nèi)容

        except requests.exceptions.RequestException as e:
            # 請(qǐng)求異常處理
            callback("請(qǐng)求發(fā)生異常:", e)

        except Exception as e:
            # 其他異常處理
            callback("發(fā)生異常:", e)
        table=soup.find_all('table')[2]
        print(table)
        callback('一級(jí)網(wǎng)頁爬取成功。')
        detail_urls=[]
        links = table.find_all("a")
        for link in links:
            if "歐" in link.text and "shtml" in link["href"]:
                detail_urls.append(link["href"])

        callback('發(fā)現(xiàn)目標(biāo)文件%s個(gè)'%len(detail_urls))
        print(detail_urls)
        if len(detail_urls)<1:
            callback('二級(jí)網(wǎng)頁爬取失敗。')
            time.sleep(int(m)*60)
            callback('待機(jī)中,%s分鐘后繼續(xù)掃描。' % m)
            callback('*************************************************')
            continue
        callback('二級(jí)網(wǎng)頁獲取成功。')
        # 獲取當(dāng)前時(shí)間
        current_time = datetime.datetime.now()

        # 將時(shí)間格式化為"20231222"的格式
        formatted_time = current_time.strftime("%Y%m%d%H%M%S")

        download_path = '.\\download\\' + formatted_time
        download_path=os.path.abspath(download_path)
        if not os.path.exists(download_path):
            # 如果文件夾不存在，則創(chuàng)建文件夾
            os.makedirs(download_path)
        i=0
        for d in detail_urls:
            i+=1
            callback('正在下載第%s個(gè)...'%i)
            callback(d)
            download_excel.download(d, download_path,download_callback)
            callback('第%s個(gè)下載完成。'%i)
        callback('待機(jī)中,%s分鐘后繼續(xù)掃描。'%m)
        callback('*************************************************')
        time.sleep(int(m)*60)

3第三步：下載Excel文件。因?yàn)槭菬o頭瀏覽器，所以不能直接用Selenium點(diǎn)擊，要用Javascript。

from selenium import webdriver
from selenium.webdriver.chrome.options import Options
from selenium.webdriver.common.by import By
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
from selenium.common.exceptions import TimeoutException
from selenium.common.exceptions import WebDriverException
import sys
import time
def download(url,download_path,callback):
    # 指定Chrome瀏覽器位置和驅(qū)動(dòng)位置
    chrome_binary_path = '.\\chrome\\Application\\chrome.exe'
    chrome_driver_path = '.\\chrome\\Application\\chromedriver.exe'

    # 創(chuàng)建瀏覽器選項(xiàng)實(shí)例，并啟用下載文件功能
    chrome_options = Options()
    # 切換為無頭模式
    chrome_options.add_argument('--headless')
    chrome_options.add_argument('--no-sandbox')
    chrome_options.add_argument('--disable-gpu')
    chrome_options.add_argument('–-disable-dev-shm-usage')
    chrome_options.add_argument('--disable-extensions')
    chrome_options.add_argument('--ignore-certificate-errors')
    chrome_options.add_argument("--test-type")
    chrome_options.binary_location = chrome_binary_path

    prefs = {'download.default_directory': download_path }  # 設(shè)置默認(rèn)下載文件路徑
    chrome_options.add_experimental_option('prefs', prefs)
    # 在瀏覽器選項(xiàng)中添加下面兩行代碼，指定下載路徑和禁用PDF和Flash插件
    chrome_options.add_argument('--disable-plugins')
    chrome_options.add_argument('--disable-extensions')
    driver=None
    try:
        # 啟動(dòng)瀏覽器并打開目標(biāo)網(wǎng)頁
        driver = webdriver.Chrome(chrome_driver_path, options=chrome_options)
        driver.get(url)
    except WebDriverException as e:
        # 處理WebDriverException異常
        callback("啟動(dòng)瀏覽器或打開目標(biāo)網(wǎng)頁時(shí)發(fā)生異常:")
    callback('瀏覽器啟動(dòng)并成功獲取頁面。')
    btn_xpath = "http://a[contains(text(), '賠率下載')]"
    wait_time = 10  # 最大等待時(shí)間，單位為秒

    wait = WebDriverWait(driver, wait_time)
    btn=None
    while True:
        try:
            btn = wait.until(EC.visibility_of_element_located((By.XPATH, btn_xpath)))
        except TimeoutException:
            callback('等待超時(shí)，未找到按鈕。3秒后再次嘗試...')
            time.sleep(3)
            continue

        callback('獲取按鈕。')
        driver.execute_script("arguments[0].click();", btn)
        callback('點(diǎn)擊按鈕。')
        callback('下載中，等待3秒。')
        time.sleep(3)
        driver.quit()
        callback('瀏覽器已關(guān)閉。')
        break

4.第四部：打包應(yīng)用程序文章來源地址http://www.zghlxwxcb.cn/news/detail-800273.html

pyinstaller --hidden-import=selenium --hidden-import=tkinter --hidden-import=auto_download --hidden-import=requests --hidden-import=bs4 form.py

*本文章僅供學(xué)習(xí)和交流

到了這里，關(guān)于【 Python足彩網(wǎng)站賠率數(shù)據(jù)文件自動(dòng)下載（Tkinter+BeautifulSoup+Selenium隱藏瀏覽器界面，雙線程）】的文章就介紹完了。如果您還想了解更多內(nèi)容，請(qǐng)?jiān)谟疑辖撬阉鱐OY模板網(wǎng)以前的文章或繼續(xù)瀏覽下面的相關(guān)文章，希望大家以后多多支持TOY模板網(wǎng)！