使用Selenium抓取网页动态内容

from selenium import webdriver

# 创建Chrome浏览器对象
browser = webdriver.Chrome()
# 加载指定的页面
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/')
# 通过元素ID获取元素
kw_input = browser.find_element(By.ID, 'kw')
# 模拟用户输入行为
kw_input.send_keys('Python')
# 通过CSS选择器获取元素
su_button = browser.find_element(By.CSS_SELECTOR, '#su')
# 模拟用户点击行为
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()
# 设置浏览器窗口大小
browser.set_window_size(1200, 800)
browser.get('https://www.baidu.com/')
# 设置隐式等待时间为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()
# 创建显示等待对象
wait_obj = WebDriverWait(browser, 10)
# 设置等待条件（等搜索结果的div出现）
wait_obj.until(
    expected_conditions.presence_of_element_located(
        (By.CSS_SELECTOR, '#content_left')
    )
)
# 截屏
browser.get_screenshot_as_file('python_result.png')

# 执行JavaScript代码
browser.execute_script('document.documentElement.scrollTop = document.documentElement.scrollHeight')

# 创建Chrome参数对象
options = webdriver.ChromeOptions()
# 添加试验性参数
options.add_experimental_option('excludeSwitches', ['enable-automation'])
options.add_experimental_option('useAutomationExtension', False)
# 创建Chrome浏览器对象并传入参数
browser = webdriver.Chrome(options=options)
# 执行Chrome开发者协议命令（在加载页面时执行指定的JavaScript代码）
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):
    """
    下载保存图片
    :param picture_url: 图片的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('苍老师')
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)