selenium自動化模擬

代碼如下:

pip install selenium

from selenium import webdriver
import time

# 創建一個瀏覽器對象
path = r'E:\360\Google\Chrome\chromedriver.exe'
driver = webdriver.Chrome(executable_path=path)

# 讓瀏覽器打開百度
url = 'http://www.baidu.com/'
driver.get(url)
time.sleep(5)


'''
下面的操作依賴上面的響應，所以每次只要是耗時的操作，都需要停頓
（1）顯示等待
	time.sleep(10)     
	一直等待10s
（2）隱示等待
	driver.implicitly_wait(10)
	最多等待10s
動態加載
1、請求，得到的是空的html內容
2、在發送ajax請求，得到json格式數據
3、執行裏面的js代碼，根據DOM操作添加html內容
'''

# 找到輸入框
my_input = driver.find_element_by_id('kw')
'''
find_element_by_id
find_element_by_xpath
find_elements_by_xpath
find_element_by_class_name
find_element_by_css_selector
find_element_by_link_text
find_elements_by_class_name
find_elements_by_css_selector
find_elements_by_link_text
'''
# 向這個框裏面寫內容
my_input.send_keys('清純美女')
time.sleep(3)

# 查找百度一下按鈕
button = driver.find_element_by_id('su')
button.click()
time.sleep(5)

# 查找指定鏈接
a_href = driver.find_elements_by_link_text('清純美女_海量精選高清圖片_百度圖片')[0]
a_href.click()
time.sleep(10)

# 退出瀏覽器
driver.quit()

自運行無界面谷歌測試:

[注意]文件路徑填寫自己的

代碼如下:

from selenium import webdriver
import time
from selenium.webdriver.chrome.options import Options

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

path = r'E:\360\Google\Chrome\chromedriver.exe'
driver = webdriver.Chrome(executable_path=path, chrome_options=chrome_options)
driver.get('http://www.baidu.com')
time.sleep(3)
driver.save_screenshot('guge.png')
driver.close()

phantomjs:

from selenium import webdriver
import time

path = r'F:\StudyNotes\spider-4\day06\ziliao\phantomjs-2.1.1-windows\bin\phantomjs.exe'
driver = webdriver.PhantomJS(path)

url = 'http://www.baidu.com/'

driver.get(url)
time.sleep(3)
driver.save_screenshot('baidu1.png')
driver.close()