【Python】ヤフオクの自動延長なし商品を抽出してみた！

import csv
import logging
import os
import random
import time
import tkinter as tk
from functools import wraps
from selenium import webdriver
from selenium.webdriver.chrome.options import Options
from selenium.webdriver.common.by import By

options = Options()
# options.add_argument("--headless")
driver = webdriver.Chrome(options=options)
driver.implicitly_wait(10)

logging.basicConfig(
    level=logging.INFO,
    format="%(asctime)s %(levelname)s %(message)s",
    datefmt="%Y/%m/%d %H:%M:%S"
)
logger = logging.getLogger(__name__)

def sleep():
    time.sleep(random.uniform(2, 5))

def sleep_after_execution():
    def decorator(func):
        @wraps(func)
        def wrapper(*args, **kwargs):
            result = func(*args, **kwargs)
            sleep()
            return result
        return wrapper
    return decorator

def delete_csv_file():
    if(os.path.isfile("disappointing.csv")):
        os.remove("disappointing.csv")

    if(os.path.isfile("automatic_extension.csv")):
        os.remove("automatic_extension.csv")

@sleep_after_execution()
def open_site():
    driver.get("https://auctions.yahoo.co.jp/")

@sleep_after_execution()
def delete_ad():
    try:
        driver.find_element(By.CSS_SELECTOR, "div > a.Close-sc-uncojt.UslsY").click()
    except:
        pass

@sleep_after_execution()
def search(keyword):
    driver.find_element(By.CSS_SELECTOR, "div > input").send_keys(keyword)
    driver.find_element(By.ID, "acHdSchBtn").click()

@sleep_after_execution()
def filter_price(min, max):
    if min is not None:
        driver.find_element(By.XPATH, "//input[@name='min']").send_keys(min)
    
    if max is not None:
        driver.find_element(By.XPATH, "//input[@name='max']").send_keys(max)

    driver.find_element(By.CSS_SELECTOR, "form > input.Button.u-marginT10").click()

@sleep_after_execution()
def select_auction_mode():
    driver.find_element(By.CSS_SELECTOR, "div.Tab > ul > li:nth-child(2) > a").click()

@sleep_after_execution()
def sort():
    driver.find_element(By.CSS_SELECTOR, "li:nth-child(1) > div > button").click()
    driver.find_element(By.CSS_SELECTOR, "li:nth-child(1) > ul > li:nth-child(2) > a").click()

@sleep_after_execution()
def select_item_number():
    driver.find_element(By.CSS_SELECTOR, "li:nth-child(2) > div > button").click()
    driver.find_element(By.CSS_SELECTOR, "li:nth-child(2) > div > ul > li:nth-child(2) > a").click()

def get_hrefs_per_page():
    hrefs = []

    hrefs_elem = driver.find_elements(By.CSS_SELECTOR, "div.Product__detail > h3 > a")
    for elem in hrefs_elem:
        href = elem.get_attribute("href")
        hrefs.append(href)

    return hrefs

def get_hrefs():
    hrefs = []

    while True:
        try:
            hrefs.extend(get_hrefs_per_page())
            driver.find_element(By.CSS_SELECTOR, "li.Pager__list.Pager__list--next > a").click()
            sleep()
        except:
            break

    return hrefs

def write_csv(file_name, href):
    with open(file_name, mode="a", newline="", encoding="utf-8") as file:
        writer = csv.writer(file)
        writer.writerow([href])

def create_csv_file(hrefs):
    for href in hrefs:
        driver.get(href)

        try:
            remaining_time_unit = driver.find_element(By.CSS_SELECTOR, "span.Count__detail > span").text
        except:
            continue
            
        if remaining_time_unit == "日":
            break
        
        title = driver.find_element(By.CSS_SELECTOR, "h1").text
        if len(title) < 30:
            write_csv("disappointing.csv", href)

        automatic_extension = driver.find_element(By.CSS_SELECTOR, "tr:nth-child(5) > td").text
        if automatic_extension == "なし":
            write_csv("automatic_extension.csv", href)

        sleep()

def open_url(file_name):
    with open(file_name, newline='') as csv_file:
        urls = csv.reader(csv_file)

        for url in urls:
            driver.execute_script("window.open('');")
            driver.switch_to.window(driver.window_handles[-1])
            driver.get(url[0])

def main(keywords, min_price, max_price):
    try:
        logger.info("処理開始")

        delete_csv_file()

        open_site()
        delete_ad()

        for keyword in keywords:
            logger.info(f"キーワード「{keyword}」を処理中...")

            search(keyword)
            filter_price(min_price, max_price)
            select_auction_mode()
            sort()
            select_item_number()

            hrefs = get_hrefs()
            create_csv_file(hrefs)
        
        open_url("disappointing.csv")
        open_url("automatic_extension.csv")

        logger.info("処理終了")
    except Exception as e:
        logger.error(f"予期せぬエラーが発生しました: {e}")

if __name__ == "__main__":
    root = tk.Tk()
    root.geometry(f"{root.winfo_screenwidth()}x{root.winfo_screenheight()}")
    root.title("自動延長なし商品抽出ツール")

    tk.Label(root, text="検索ワード").grid(row=0, column=0, padx=10, pady=5)
    keyword_input = tk.Text(root)
    keyword_input.grid(row=0, column=1, padx=10, pady=5)

    tk.Label(root, text="最小金額").grid(row=1, column=0, padx=10, pady=5)
    min_price_input = tk.Entry(root)
    min_price_input.grid(row=1, column=1, padx=10, pady=5)

    tk.Label(root, text="最大金額").grid(row=2, column=0, padx=10, pady=5)
    max_price_input = tk.Entry(root)
    max_price_input.grid(row=2, column=1, padx=10, pady=5)

    button = tk.Button(root, text="実行", command=lambda: main(keyword_input.get("1.0", tk.END).strip().split("\n"), min_price_input.get(), max_price_input.get()))
    button.grid(row=3, columnspan=2, pady=10)

    root.mainloop()

$ python3 yahoo_auction.py