一 . 认识PhantomJS

# 导入 webdriver
from selenium import webdriver
# 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()
# 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被完全加载，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 wrapper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
# 打印页面标题 "百度一下，你就知道
"print driver.title
# 生成当前页面快照并保存
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("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("atguigu")
# 模拟Enter回车键
driver.find_element_by_id("su").send_keys(Keys.RETURN)
# 清除输入框内容
driver.find_element_by_id("kw").clear()
# 生成新的页面快照
driver.save_screenshot("atguigu.png")
# 获取当前url
print driver.current_url
# 关闭当前页面，如果只有一个页面，会关闭浏览器# driver.close()
# 关闭浏览器
driver.quit()

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

# 定位UI元素 (WebElements)
 
find_element_by_id
find_elements_by_name
find_elements_by_xpath
find_elements_by_link_text
find_elements_by_partial_link_text
find_elements_by_tag_name
find_elements_by_class_name
find_elements_by_css_selector

# 导入 webdriver
 
#导入 ActionChains 类
from selenium.webdriver import ActionChains
# 鼠标移动到 ac 位置
ac = driver.find_element_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()

# 导入 Select 类
from selenium import webdriver
from selenium.webdriver.support.ui import Select
driver = webdriver.Chrome()
driver.get("http://127.0.0.1:8080")
# 找到 name 的选项卡
select = Select(driver.find_element_by_name('status'))
#根据位置下标
# select.select_by_index(1)
#根据值找到对应的选择
# select.select_by_value("3")
#根据显示值找到对应的选择
select.select_by_visible_text("审核不通过")

driver.switch_to.window("window name")

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

from selenium import webdriver
driver = webdriver.Chrome()
driver.implicitly_wait(10) # seconds
driver.get("http://www.xxxxx.com/loading")

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，负责条件出发
from selenium.webdriver.support import expected_conditions as EC
driver = webdriver.Chrome()
driver.get("http://www.xxxxx.com/loading")
try:
    # 页面一直循环，直到 id="myElement" 出现
    element = WebDriverWait(driver, 10).until(EC.presence_of_element_located((By.ID, "myElement")))
finally:
    driver.quit()

二、网站模拟登录豆瓣网

from selenium import webdriver
import time
 
# 创建一个浏览器客户端,并且指定配置
# 如果是PhantomJS做浏览器客户端还要设置路径
# driver = webdriver.PhantomJS(executable_path="/usr/local/bin/phantomjs")
driver = webdriver.Chrome()
 
driver.get("https://www.douban.com/")
time.sleep(1)
driver.save_screenshot("豆瓣首页.png")
 
#输入账号
driver.find_element_by_id("form_email").send_keys("username")
#输入密码
driver.find_element_by_name("form_password").send_keys("password")
#保存验证码的图片
driver.save_screenshot("验证码.png")
#输入验证码
check_code = input("请输入验证码:")
print(r"验证码是多少:%s" % check_code)
 
driver.find_element_by_id("captcha_field").send_keys(check_code)
 
#点击登录按钮
driver.find_element_by_xpath("//input[@class='bn-submit']").click()
 
#休眠一下等待登录成功
time.sleep(3)
#保存登录成功的快照
driver.save_screenshot("登录成功.png")
 
 
#保存成功登录好的html到本地
with open("douban.html","w",encoding="utf-8") as f:
   f.write(driver.page_source)
 
#退出成功
driver.quit()

三、动态页面模拟点击（unittest -python测试模块）

import time
#导入python测试模块
import unittest
 
#类名任意,但必须继承unittest.TestCase
class DouyuTest(unittest.TestCase):
   #固定写法,通常做初始化
   def setUp(self):
      print("setUp()....")
      self.num1 = 1
      self.num2 = 1
 
   def testTest(self):
      for i in range(1,3):
         print("testTest()==",i)
         self.num1 += 1
         time.sleep(1)
 
   def testTest2(self):
      for i in range(1,3):
         print("testTest2()==",i)
         self.num2 += 1
         time.sleep(1)
   #固定写法,但每个自定义方法接收后都会调用一次该方法
   def tearDown(self):
      print("tearDown()...")
      print("num1==",self.num1)
      print("num2==", self.num2)
 
if __name__ == "__main__":
   #调用的时候只需要写上main,固定的调用方式
   unittest.main()

四、执行JavaScript代码from selenium import webdriver

import time
 
driver = webdriver.PhantomJS()
 
driver.get("https://movie.douban.com/typerank?type_name=剧情&type=11&interval_id=100:90&action=")
# 向下滚动10000像素
js = "document.body.scrollTop=10000"
time.sleep(5)
#查看页面快照
driver.save_screenshot("douban.png")
# 执行JS语句
driver.execute_script(js)
 
time.sleep(5)
#查看页面快照
driver.save_screenshot("newdouban.png")
#退出浏览器
driver.quit()

五、模拟最新无界面浏览器（绝招在这，缺陷性能太慢）

from selenium import webdriver
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver.common.by import By
from bs4 import BeautifulSoup
from selenium.webdriver.chrome.options import Options
 
#不加载图片,不缓存在硬盘(内存)
SERVICE_ARGS = ['--load-images=false', '--disk-cache=false']
chrome_options = Options()
chrome_options.add_argument("--headless")
# 创建浏览器, 添加参数设置为无界面浏览器
driver = webdriver.Chrome(service_args=SERVICE_ARGS, chrome_options=chrome_options)
#设置等待时间
waite = WebDriverWait(driver, 5)
driver.get('https://taobao.com/')
 
def get_page_num():
	# 等待搜索框出现
	input = waite.until(EC.presence_of_element_located((By.CSS_SELECTOR, '#q')))
	# 输入美食
	input.send_keys('美食')
	# 点击搜索
	driver.find_element_by_css_selector("#J_TSearchForm > div > button").click()
	# 共计多少页
	text = driver.find_element_by_css_selector('#mainsrp-pager > div > div > div > div[class="total"]').text
	data = text[2:6]
	get_product_info()
	return data
 
#得到某一个宝贝,商品的大体信息
def get_product_info():
	waite.until(EC.presence_of_element_located((By.CSS_SELECTOR, '#mainsrp-itemlist .items .item')))
	# 通过BeautifulSoup取数据
	soup = BeautifulSoup(driver.page_source, 'lxml')
	#取所有的列表数据
	item_lists = soup.select("#mainsrp-itemlist .items .item")
	for item_list in item_lists:
		item_dict = {}
		image = item_list.select('.J_ItemPic.img')[0].attrs["data-src"]
		if not image:
			image = item_list.select('.J_ItemPic.img')[0].attrs["data-ks-lazyload"]
		# 销售地
		location = item_list.select(".location")[0].text
		# 价格
		price = item_list.select(".price")[0].text
		# 商店名称
		shopname = item_list.select(".shopname")[0].text.strip()
		# 宝贝名称
		title = item_list.select('a[class="J_ClickStat"]')[0].text.strip()
		# 链接
		data_link = item_list.select('a[class="J_ClickStat"]')[0].attrs["href"]
 
		item_dict["image"] = "https:" + image
		item_dict["location"] = location
		item_dict["shopname"] = shopname
		item_dict["title"] = title
		item_dict["data_link"] = "https:" + data_link
		item_dict["price"] = price
		print(item_dict)
 
# 切换下一页
def next_page(page):
	print("当前正在加载第%s页的数据--------" % page)
	try:
		input = waite.until(EC.presence_of_element_located((By.CSS_SELECTOR, '#mainsrp-pager > div > div > div > div > input')))
		input.clear()   # 清空输入框
		# 页面框添加页码
		input.send_keys(page)
		#找到确定按钮,点击确定
		driver.find_element_by_css_selector("#mainsrp-pager > div > div > div > div > span.btn.J_Submit").click()
		waite.until(EC.text_to_be_present_in_element(
			(By.CSS_SELECTOR, "#mainsrp-pager > div > div > div > ul.items > li.item.active"), str(page)))
	except Exception as e:
		print(e)
		next_page(page)
	# 当前切换后的页面的数据
	get_product_info()
 
def main():
	data = get_page_num()
	print('总页数是=', data)
	for page in range(2, int(data) + 1):
		next_page(page)
 
	# 退出浏览器
	driver.quit()
 
if __name__ == '__main__':
	main()