Python爬虫(二十一)_Selenium与PhantomJS

#-*-  coding:utf-8 -*-
#主要用来测试selenium使用phantomJs

#导入webdriver
from selenium import webdriver
import time

#要想调用键盘按键操作需要引入keys包
from selenium.webdriver.common.keys import Keys

#调用环境变量指定的PhantomJS浏览器创建浏览器对象
driver = webdriver.PhantomJS()
driver.set_window_size(1366, 768)
#如果没有在环境变量指定PhantomJS位置
#driver = webdriver.PhantomJS(executable_path = "./phantomjs")

#get方法会一直等到页面加载，然后才会继续程序，通常测试会在这里选择time.sleep(2)

driver.get("http://www.baidu.com/")

#获取页面名为wraper的id标签的文本内容
data = driver.find_element_by_id('wrapper').text

#打印数据内容
print(data)

print driver.title

#生成页面快照并保存
driver.save_screenshot("baidu.png")

# id="kw"是百度搜索输入框，输入字符串"长城"
driver.find_element_by_id('kw').send_keys(u'长城')

# id="su"是百度搜索按钮，click()是模拟点击
driver.find_element_by_id('su').click()

#获取新的页面快照
driver.save_screenshot("长城.png")

#打印网页渲染后的源代码
print(driver.page_source)

#获取当前页面Cookie
print(driver.get_cookies())

#ctrl+a全选输入框内容
driver.find_element_by_id('kw').send_keys(Keys.CONTROL, 'a')
#ctrl+x剪切输入框内容
driver.find_element_by_id('kw').send_keys(Keys.CONTROL, 'x')

#输入框重新输入内容
driver.find_element_by_id('kw').send_keys('itcast')

#模拟Enter回车键
driver.find_element_by_id('su').send_keys(Keys.RETURN)
time.sleep(5)

#清空输入框内容
driver.find_element_by_id('kw').clear()

#生成新的页面快照
driver.save_screenshot('itcast.png')

#获取当前url
print(driver.current_url)

driver.quit()

<input type="text" name="user-name" id="passwd-id" />

#获取id标签值
element = driver.find_element_by_id("passwd-id")
#获取name值
element = driver.find_element_by_name("user-name")
#获取标签名
element = driver.find_element_by_tag("input")
#也可以通过XPath来匹配
element = driver.find_element_by_xpath(//input[@id="passwd-id"])

<div id="coolesWidgeEvah">...</div>

element = driver.find_element_by_id("coolesWidgetEvah")

---------or-------
from selenium.webdriver.common.by import By
element = driver.find_element(by=By.ID, value="coolesWidgetEvah")

<div class="cheese"><span>Cheddar</span></div><div class="cheese"><span>Gouda</span></div>

<iframe src="..."></iframe>

<imput name="cheese" type="text" />

cheese = driver.find_element_by_name("cheese")

-------------or-------------------------
from selenium.webdrier.common.by import By
cheese = driver.find_element(By.NAME, "cheese")

<a href="http://www.google.com/search?q=cheese">cheese</a>

<a href="http://www.google.com/search?q=cheese">search for cheese</a>

<div id="food"><span class="dairy">milk</span><span class="dairy">cheese</span></div>

<input type="text" name="example" / >
<input type="text" name="other" / >

#导入ActionChains类
from selenium.webdrive import ActionChains

#鼠标移动到ac位置
ac = driver.find_elenemt_by_xpath('element')
ActionChains(driver).move_to_element(ac).perform()

#在ac位置单击
ac = driver.find_element_by_xpath('elementA')
ActionChains(driver).move_to_element(ac).click(ac).perform()

#在ac位置双击
ac = driver.find_element_by_xpath("elementB")
ActionChains(driver).move_to_element(ac).double_click(ac).perform()

#在ac位置右击
ac = driver.find_element_by_xpath('elementC')
ActionChains(driver).move_to_element(ac).context_click(ac).perform()

#在ac位置左键单击hold住
ac = driver.find_element_by_xpath('elementF')
ActionChains(driver).move_to_element(ac).click_and_hold(ac).perform()

#将ac1拖拽到ac2位置
ac1 = driver.find_element_by_xpath('elementD')
ac2 = driver.find_element_by_xpath('elementE')
ActionChains(driver).drag_and_drop(ac1, ac2).perform()

<select id="status" class="form-control valid" onchange="" name = 'status'>
    <option value=""></option>
    <option value="0">未审核</option>
    <option value="1">初审通过</option>
    <option value="2">复审通过</option>
    <option value="3">审核不通过</option>
</select>

#导入Select类
from selenium.webdriver.support.ui import Select

#找到name的选项卡
select = Select(driver.find_element_by_name('status'))

#s
select.select_by_index(1)
select.select_by_value("0")
select.select_by_visible_text(u'未审核')

select.deselect_all()

alert = driver.switch_to_alert()

for handle in driver.window_handles:
    driver.switch_to_window(handle)

driver.forward()  #前进
driver.back()    #后退

for cookie in driver.get_cookies():
    print("%s -> %s"%(cookie['name'], cookie['value']))

#By name
driver.delete_cookie('CookieName')

#all
driver.delete_all_cookies()

from selenium import webdriver
from selenium.webdriver.common.by import By

#WebDriverWait库，负责循环等待
from selenium.webdriver.support.ui import WebDriverWait
#expected_conditions类，负责条件触发
from selenium.webdriver.support import expected_conditions as EC

driver = webdriver.Chrome()

driver.get("http://www.xxxx.com/loading")

try:
    #页面一直循环，知道id="myDynamicElement"出现
    element = WebDriverWait(driver, 10).until(
            EC.presence_of_element_located((By.ID, "myDynamicElement"))
        )
finally:
    driver.quit()    

    title_is
    title_contains
    presence_of_element_located
    visibility_of_element_located
    visibility_of
    presence_of_all_elements_located
    text_to_be_present_in_element
    text_to_be_present_in_element_value
    frame_to_be_available_and_switch_to_it
    invisibility_of_element_located
    element_to_be_clickable - it is Displayed and Enabled
    staleness_of
    element_to_be_selected
    element_located_to_be_selected
    element_selection_state_to_be
    element_located_selection_state_to_be
    aert_is_present

from selenium import webdriver

driver = webdriver.Chrome()
driver.implicitly_wait(10)  #seconds

driver.get("http://www.xxxxx.com/loading")

myDynamicElement = driver.find_element_by_id("myDynamicElement")