Selenium 的基本使用【模拟浏览器爬取】

from typing_extensions import Final
from selenium import webdriver
from selenium.webdriver.common.by import By
from selenium.webdriver.common.keys import Keys
from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver.support.wait import WebDriverWait
browser = webdriver.Chrome()

try:
  browser.get('https://www.baidu.com')
  input = browser.find_element_by_id('kw')
  input.send_keys('Python')
  input.send_keys(Keys.ENTER)
  wait = WebDriverWait(browser, 10)
  wait.until(EC.presence_of_element_located((By.ID, 'content_left')))

  print(browser.current_url)
  print(browser.get_cookies())
  print(browser.page_source)
finally:
  browser.close()

模拟浏览器爬取

有些靠JavaScript渲染的网站，直接requests.get()是获取不到内容的