selenium+chromedrive 爬取js載入的動態網頁(下拉才能顯示內容)
阿新 • • 發佈:2018-12-15
from selenium import webdriver from selenium.webdriver.common.keys import Keys #呼叫鍵盤操作 from selenium.webdriver.chrome.options import Options import time from lxml import etree #建立chrome瀏覽器驅動,無頭模式 chrome_options = Options() chrome_options.add_argument('--headless') driver = webdriver.Chrome(chrome_options=chrome_options) #載入介面 driver.get("https://ai.ofweek.com/") time.sleep(3) #逐漸滾動瀏覽器視窗,令ajax逐漸載入 for i in range(0,10): driver.execute_script('window.scrollTo(0, document.body.scrollHeight)') i += 1 time.sleep(4) # 拿到頁面原始碼 html = driver.page_source print(html) driver.quit()