动态渲染页面爬取---selenium的使用

import time

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
from selenium.webdriver import ActionChains

'''基本使用'''
#声明浏览器对象
browser=webdriver.Chrome()
try:
    '''访问页面'''
    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('='*50)
    print(browser.current_url)
    print('=' * 50)
    print(browser.get_cookies())
    print('=' * 50)
    # print(browser.page_source)
    browser.quit()
except:
    browser.close()

'''节点交互'''
driver=webdriver.Chrome()
try:
    driver.get('https://www.taobao.com')
    input=driver.find_element(By.ID,'q')
    input.send_keys('手机')
    # input.clear()   #清除
    button=driver.find_element(By.CLASS_NAME,'btn-search')
    button.click()
    driver.close()
except:
    driver.close()


'''动作链'''
driver=webdriver.Chrome()
try:
    driver.get('https://www.runoob.com/try/try.php?filename=jqueryui-api-droppable')
    driver.switch_to.frame('iframeResult')     #切换frame
    source=driver.find_element(By.ID,'draggable')
    target=driver.find_element(By.ID,'droppable')
    actions=ActionChains(driver)
    actions.drag_and_drop(source,target)
    actions.perform()

except:
    driver.close()

'''执行JavaScript,比如下拉进度条'''
driver=webdriver.Chrome()
try:
    driver.get('https://www.zhihu.com/explore')
    driver.execute_script('window.scrollTo(0,document.body.scrollHeight)')
    driver.execute_script('alert("To Bottom")')
except:
    print('error')
    driver.close()

'''获取属性'''
driver=webdriver.Chrome()
try:
    driver.get('https://www.zhihu.com/explore')
    logo=driver.find_element(By.ID,'special')
    print(logo)
    print(logo.get_attribute('class'))
    driver.close()
except:
    print('error')
    driver.close()

'''获取文本'''
driver=webdriver.Chrome()
try:
    driver.get('https://www.zhihu.com/explore')
    res=driver.find_element(By.CLASS_NAME,'ExploreSpecialCard-contentTitle')
    print(res.text)
    driver.close()
except:
    print('error')
    driver.close()

'''获取id、位置、标签吗和大小'''
driver=webdriver.Chrome()
try:
    driver.get('https://www.zhihu.com/explore')
    res=driver.find_element(By.CLASS_NAME,'ExploreSpecialCard-contentTitle')
    print('id',res.id)
    print('位置',res.location)
    print('标签',res.tag_name)
    print('大小',res.size)
    driver.close()
except:
    print('error')
    driver.close()

'''延时显式等待'''
driver=webdriver.Chrome()
try:
    driver.get('https://www.taobao.com')
#引入WebDriverWait对象，设置最长等待时间
    wait=WebDriverWait(driver,10)
#调用until方法，传入等待条件;EC.presence_of_element_located代表节点出现
    input=wait.until(EC.presence_of_element_located((By.ID,'q')))
    button=wait.until(EC.element_to_be_clickable((By.CSS_SELECTOR,'.btn-search')))
    print(input,button)
    driver.close()
except:
    print('error')
    driver.close()

'''前进和后退'''
driver=webdriver.Chrome()
try:
    driver.get('https://www.taobao.com/')
    driver.get('https://www.baidu.com/')
    driver.get('https://www.python.org/')
    driver.back()   #后退
    time.sleep(1)
    driver.forward()  #前进
    driver.close()
except:
    print('error')
    driver.close()