爬虫 selenium

开启浏览器的前端的爬虫

from selenium import webdriver
from time import sleep
bro
= webdriver.Chrome(executable_path=r'D:\爬虫存储\chromedriver.exe')
bro.
get(url='https://www.baidu.com/')
sleep(
2) bro.find_element_by_id('kw').send_keys('python') sleep(1) bro.find_element_by_id('su').click() time.sleep(2)
with open(
'baidu.html', 'w', encoding='utf8') as f: f.write(bro.page_source)
bro.quit()

不开启浏览器的前端的爬虫

from selenium.webdriver.chrome.options import Options
chrome_options
= Options() chrome_options.add_argument('--headless') chrome_options.add_argument('--disable-gpu')
url
= 'https://movie.douban.com/typerank?type_name=%E6%83%8A%E6%82%9A&type=19&interval_id=100:90&action=' bro = webdriver.Chrome(executable_path=r'D:\爬虫存储\chromedriver.exe', chrome_options=chrome_options)
bro.
get(url)
bro.execute_script(
'window.scrollTo(0,document.body.scrollHeight)') for i in range(2): sleep(1) bro.execute_script('window.scrollTo(0,document.body.scrollHeight)') sleep(5)
with open(
'douban.html', 'w', encoding='utf8') as f: f.write(bro.page_source)
bro.quit()

获取浏览器的实时图片和设置浏览器的大小

from selenium.webdriver.chrome.options import Options

chrome_options = Options()
chrome_options.add_argument('--headless')
chrome_options.add_argument('--disable-gpu')

url = r'www.baidu.com'

bro = webdriver.Chrome(executable_path=r'D:\爬虫存储\chromedriver.exe', chrome_options=chrome_options)

bro.set_window_size(7680, 4320)
bro.get(url)
sleep(30)
data = bro.get_screenshot_as_png()

with open('1.png', 'wb') as f:
    f.write(data)

bro.quit()

在碰到iframe的情况下, 使用选择id等都会找不到, 解决方法

bro.switch_to_frame('login_frame')
bro.find_element_by_id('switcher_plogin').click()
bro.find_element_by_id('u').send_keys('1132300949')
bro.find_element_by_id('login_button').click()
page_text = bro.page_source

猜你喜欢

转载自www.cnblogs.com/NachoLau/p/10453871.html