python+selenium+PhantomJS抓取网页动态加载内容

from selenium import webdriver
 
 
driver = webdriver.PhantomJS()
driver.get('http://www.baidu.com')  #加载网页
data = driver.page_source  #获取网页文本
driver.save_screenshot('1.png')  #截图保存
print(data)
driver.quit()

from selenium import webdriver
from selenium.webdriver.common.desired_capabilities import DesiredCapabilities
 
 
dcap = dict(DesiredCapabilities.PHANTOMJS) #设置useragent
dcap['phantomjs.page.settings.userAgent'] = ('Mozilla/5.0 (Macintosh; Intel Mac OS X 10.9; rv:25.0) Gecko/20100101 Firefox/25.0 ') #根据需要设置具体的浏览器信息
driver = webdriver.PhantomJS(desired_capabilities=dcap) #封装浏览器信息
driver.get('http://www.baidu.com')  #加载网页
data = driver.page_source  #获取网页文本
driver.save_screenshot('1.png')  #截图保存
print(data)
driver.quit()

from selenium import webdriver
 
driver = webdriver.PhantomJS()
driver.set_page_load_timeout(5) #设置超时时间
driver.get('http://www.baidu.com')
print(driver.title)
driver.quit()

from selenium import webdriver
 
driver = webdriver.PhantomJS()
driver.set_page_load_timeout(5)
driver.get('http://www.baidu.com')
try:
  driver.get('http://www.baidu.com')
  driver.find_element_by_id('kw') # 通过ID定位
  driver.find_element_by_class_name('s_ipt') # 通过class属性定位
  driver.find_element_by_name('wd') # 通过标签name属性定位
  driver.find_element_by_tag_name('input') # 通过标签属性定位
  driver.find_element_by_css_selector('#kw') # 通过css方式定位
  driver.find_element_by_xpath("//input[@id='kw']") # 通过xpath方式定位
  driver.find_element_by_link_text("贴吧") # 通过xpath方式定位
  print(driver.find_element_by_id('kw').tag_name ) # 获取标签的类型
except Exception as e:
  print(e)
driver.quit()

from selenium import webdriver
driver = webdriver.PhantomJS()
try:
  driver.get('http://www.baidu.com')  #访问百度首页
  driver.save_screenshot('1.png')
  driver.get('http://www.sina.com.cn') #访问新浪首页
  driver.save_screenshot('2.png')
  driver.back()              #回退到百度首页
  driver.save_screenshot('3.png')
  driver.forward()            #前进到新浪首页
  driver.save_screenshot('4.png')
except Exception as e:
  print(e)
driver.quit()