Python 100 Days Day64 Introduction to Selenium

from selenium import webdriver

# 創建Chrome瀏覽器對象
browser = webdriver.Chrome()
# 加載指定的頁面
browser.get('https://www.baidu.com/')

from selenium import webdriver
from selenium.webdriver.common.by import By

browser = webdriver.Chrome()
browser.get('https://www.baidu.com/')
# 通過元素ID獲取元素
kw_input = browser.find_element(By.ID, 'kw')
# 模擬用戶輸入行為
kw_input.send_keys('Python')
# 通過CSS選擇器獲取元素
su_button = browser.find_element(By.CSS_SELECTOR, '#su')
# 模擬用戶點擊行為
su_button.click()

from selenium import webdriver
from selenium.webdriver.common.by import By
from selenium.webdriver.support import expected_conditions
from selenium.webdriver.support.wait import WebDriverWait

browser = webdriver.Chrome()
# 設置瀏覽器窗口大小
browser.set_window_size(1200, 800)
browser.get('https://www.baidu.com/')
# 設置隱式等待時間為10秒
browser.implicitly_wait(10)
kw_input = browser.find_element(By.ID, 'kw')
kw_input.send_keys('Python')
su_button = browser.find_element(By.CSS_SELECTOR, '#su')
su_button.click()
# 創建顯示等待對象
wait_obj = WebDriverWait(browser, 10)
# 設置等待條件（等搜索結果的div出現）
wait_obj.until(
    expected_conditions.presence_of_element_located(
        (By.CSS_SELECTOR, '#content_left')
    )
)
# 截屏
browser.get_screenshot_as_file('python_result.png')

# 執行JavaScript代碼
browser.execute_script('document.documentElement.scrollTop = document.documentElement.scrollHeight')

# 創建Chrome參數對象
options = webdriver.ChromeOptions()
# 添加試驗性參數
options.add_experimental_option('excludeSwitches', ['enable-automation'])
options.add_experimental_option('useAutomationExtension', False)
# 創建Chrome瀏覽器對象並傳入參數
browser = webdriver.Chrome(options=options)
# 執行Chrome開發者協議命令（在加載頁面時執行指定的JavaScript代碼）
browser.execute_cdp_cmd(
    'Page.addScriptToEvaluateOnNewDocument',
    {'source': 'Object.defineProperty(navigator, "webdriver", {get: () => undefined})'}
)
browser.set_window_size(1200, 800)
browser.get('https://www.baidu.com/')

options = webdriver.ChromeOptions()
options.add_argument('--headless')
browser = webdriver.Chrome(options=options)

import os
import time
from concurrent.futures import ThreadPoolExecutor

import requests
from selenium import webdriver
from selenium.webdriver.common.by import By
from selenium.webdriver.common.keys import Keys

DOWNLOAD_PATH = 'images/'


def download_picture(picture_url: str):
    """
    下載保存圖片
    :param picture_url: 圖片的URL
    """
    filename = picture_url[picture_url.rfind('/') + 1:]
    resp = requests.get(picture_url)
    with open(os.path.join(DOWNLOAD_PATH, filename), 'wb') as file:
        file.write(resp.content)


if not os.path.exists(DOWNLOAD_PATH):
    os.makedirs(DOWNLOAD_PATH)
browser = webdriver.Chrome()
browser.get('https://image.so.com/z?ch=beauty')
browser.implicitly_wait(10)
kw_input = browser.find_element(By.CSS_SELECTOR, 'input[name=q]')
kw_input.send_keys('蒼老師')
kw_input.send_keys(Keys.ENTER)
for _ in range(10):
    browser.execute_script(
        'document.documentElement.scrollTop = document.documentElement.scrollHeight'
    )
    time.sleep(1)
imgs = browser.find_elements(By.CSS_SELECTOR, 'div.waterfall img')
with ThreadPoolExecutor(max_workers=32) as pool:
    for img in imgs:
        pic_url = img.get_attribute('src')
        pool.submit(download_picture, pic_url)