主页 / 问题 / 1503062
Accepted
shezyy
Asked:2023-03-08 07:30:04 +0000 UTC2023-03-08 07:30:04 +0000 UTC

程序达到最大1200局，虽然总共有7350局，定时器尝试增加，没有任何变化，但你需要把7350局全部拿走

  • 772
from selenium import webdriver, common
import time
from bs4 import BeautifulSoup
from selenium import webdriver
import time
from selenium.webdriver.chrome.options import Options
from selenium.webdriver.chrome.service import Service
from selenium.webdriver.common.by import By
import json

url = f'https://store.steampowered.com/specials/'
s = Service(executable_path='C:\Пользователи\Олег\PycharmProjects\TelegramBot\chromedriver_win32\chromedriver.exe')
options = webdriver.ChromeOptions()
driver = webdriver.Chrome(service=s, options=options)
driver.get(url)
time.sleep(3)
try:
    for i in range(650):
        driver.execute_script("window.scrollTo(0, document.body.scrollHeight);")
        time.sleep(2)
        driver.find_element(By.XPATH, '//div[@class="saleitembrowser_ShowContentsContainer_3IRkb"]//button[text()="Показать больше"]').click()
except common.exceptions.NoSuchElementException:
    pass
time.sleep(3)
html = driver.page_source
soup = BeautifulSoup(html, "lxml")
games_names = soup.find_all('div', class_='salepreviewwidgets_StoreSaleWidgetRight_1lRFu')
all_sales_dict = {}
for game in games_names:
    try:
        name = game.find('div', 'salepreviewwidgets_TitleCtn_1F4bc').find('a').text
        price_sale = game.find('div', 'salepreviewwidgets_StoreSalePriceBox_Wh0L8').text
        price_orig = game.find('div', 'salepreviewwidgets_StoreOriginalPrice_1EKGZ').text
        sale = game.find('div', 'salepreviewwidgets_StoreSaleDiscountBox_2fpFv').text
        price = (f"Цена без скидки: {price_orig}. Скидка: {sale}. Цена со скидкой: {price_sale}")
        all_sales_dict[name] = price
    except AttributeError:
        pass
with open("all_sales.json", "w", encoding="utf-8") as file:
    json.dump(all_sales_dict, file, indent=4, ensure_ascii=False)
python

1 个回答

  1. Best Answer

    看起来现在的问题是页面没有时间加载，我更改了代码并留下了评论。将数据收集传输到我们将在循环中调用的函数。在该函数中，我们将等到按钮加载完毕或 10 秒超时结束，然后按下它，收集数据并将其写入文件。不要忘记进口。重复的次数必须以帝国的方式确定，我认为5-7次就足够了。为方便起见，我还添加了循环输出，以便了解程序现在的位置，在程序完成后，我添加了收集结果数量的输出。请检查它是如何工作的，写下结果。

    ...
from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver.support.wait import WebDriverWait
...

...
    driver.get(url)
    time.sleep(3)
    count=0
    for i in range(7): # Можно увеличить счётчик на столько повторений сколько потребуется, что бы собрать все скидки
        count+=1
        print(f'Итерация N - {count}')
        try:
            f = open("all_sales.json")
            d = json.load(f)
            print('Собрано сейчас -', len(d))
        except FileNotFoundError:
            print('Собрано сейчас - 0')
            pass
        driver = try_sales(driver)
    f = open("all_sales.json")
    d = json.load(f)
    print('Сбор данных завершен, собрано -', len(d))
    


def try_sales(driver):
    try:
        for i in range(100): # Тут тоже можно увеличить допустим до 100-200
            driver.execute_script("window.scrollTo(0, document.body.scrollHeight);")
            wait = WebDriverWait(driver, 10) # установим таймаут ожидания в 10 секунд, ниже будем ждать до появления элемента на странице или 10 секунд 
            wait.until(EC.element_to_be_clickable((By.XPATH, '//div[@class="saleitembrowser_ShowContentsContainer_3IRkb"]//button[text()="Показать больше"]')))
            driver.find_element(By.XPATH, '//div[@class="saleitembrowser_ShowContentsContainer_3IRkb"]//button[text()="Показать больше"]').click()
    except common.exceptions.NoSuchElementException:
        pass
    html = driver.page_source
    soup = BeautifulSoup(html, "lxml")
    games_names = soup.find_all('div', class_='salepreviewwidgets_StoreSaleWidgetRight_1lRFu')
    all_sales_dict = {}
    for game in games_names:
        try:
            name = game.find('div', 'salepreviewwidgets_TitleCtn_1F4bc').find('a').text
            price_sale = game.find('div', 'salepreviewwidgets_StoreSalePriceBox_Wh0L8').text
            price_orig = game.find('div', 'salepreviewwidgets_StoreOriginalPrice_1EKGZ').text
            sale = game.find('div', 'salepreviewwidgets_StoreSaleDiscountBox_2fpFv').text
            price = (f"Цена без скидки: {price_orig}. Скидка: {sale}. Цена со скидкой: {price_sale}")
            all_sales_dict[name] = price
        except AttributeError:
            pass
    with open("all_sales.json", "w", encoding="utf-8") as file:
        json.dump(all_sales_dict, file, indent=4, ensure_ascii=False)
    return driver
...
    • 1

相关问题