目录
下载驱动器
http://chromedriver.storage.googleapis.com/index.html
下载与谷歌版本相同或最近版本。
chrome版本查看
帮助中查看
导包
from selenium import webdriver
创建浏览器对象(以chrome为例)
driverpath = r\' \'# 驱动器路径(chromedriver.exe) driver = webdriver.Chrome(executable_path=driverpath)
demo
import time from selenium import webdriver url = \'https://www.baidu.com\' driverPath = r\'\' # 驱动器路径 driver = webdriver.Chrome(executable_path=driverPath) driver.get(url) driver.maximize_window() # 最大化页面 time.sleep(3) driver.quit()
基本函数
尺寸,位置
driver.minimize_window() #最大化页面 driver.minimize_window() #最小化页面 driver.set_window_size(200, 100) #设置窗口大小 print(\'窗口尺寸:\' + str(driver.get_window_size())) #窗口大小 driver.set_window_position(200, 300) # 设置窗口位置
关闭
driver.quit() driver.close()
页面基本操作
driver.get(url) # 获取一个页面 driver.back() # 回退 driver.forward() # 前进
demo
import time from selenium import webdriver url1 = \'https://www.baidu.com\' url2 = \'https://www.bilibili.com\' driverPath = r\'C:\\Users\\29273\\AppData\\Local\\Programs\\Python\\Python38-32\\chromedriver.exe\' driver = webdriver.Chrome(executable_path=driverPath) driver.set_window_position(200, 300) driver.get(url1) time.sleep(5) driver.get(url2) time.sleep(5) driver.back() time.sleep(5) driver.close()
元素定位以及数据输入
div标签中的属性来进行定位
id,classname,name,tagname,partial link text,link text,css selector
例如下列a标签中的classname为username
driver.find_element_by_class_name(\"username\")
driver.find_element_by_class_name(\"btn.btn_big.btn_error\")
# 部分函数 driver.find_element_by_xpath(\'/html/body/div[1]/div[2]/div[3]/div[2]/div[1]/dl/dd/div[1]/a\') driver.find_element_by_css_selector(\'body > div.wrap > div.main_wrap > div.main.cc > div.main_sidebar > div.box_wrap.user_info > dl > dd > div.name > a\') driver.find_element_by_id(value) driver.find_element_by_name(value) driver.find_element_by_class_name(value) driver.find_element_by_tag_name(value) driver.find_element_by_link_text(value) driver.find_element_by_partial_link_text(value)
对数据框输入数据
driver.find_element_by_name(\"username\").send_keys(\"giao\")
点击事件
driver.find_element_by_xpath(\'//*[@id=\"J_register_form\"]/div/dl[5]/dd/button\').click()
练习一(简单网页注册)
http://47.107.178.45/phpwind/
import time from selenium import webdriver url = r\'http://47.107.178.45/phpwind/\' driverPath = r\'C:\\Users\\29273\\AppData\\Local\\Programs\\Python\\Python38-32\\chromedriver.exe\' driver = webdriver.Chrome(executable_path=driverPath) driver.get(url) registerBtn = driver.find_element_by_xpath(\'//*[@id=\"J_login_form\"]/dl/dd[2]/a\') registerBtn.click() time.sleep(5) driver.find_element_by_name(\"username\").send_keys(\"giao\") driver.find_element_by_name(\"password\").send_keys(\"giaogiao\") driver.find_element_by_name(\"repassword\").send_keys(\'giaogiao\') driver.find_element_by_name(\"email\").send_keys(\'giao@qq.com\') driver.find_element_by_xpath(\'//*[@id=\"J_register_form\"]/div/dl[5]/dd/button\').click() time.sleep(10) driver.quit()
练习二
打开某民宿网站->输入城市->选择人数->点击查看详情
import time from selenium import webdriver city = input(\'请输入你想查询的城市:\') adult = input(\'请输入大人人数:\') teen = input(\'请输入孩子人人数:\') baby = input(\'请输入婴儿人数:\') url = \"https://www.airbnb.cn/?logo=1\" driverPath = r\'C:\\Users\\29273\\AppData\\Local\\Programs\\Python\\Python38-32\\chromedriver.exe\' driver = webdriver.Chrome(executable_path=driverPath) driver.get(url) city_input = driver.find_element_by_id(\"Koan-via-HeaderController__input\") city_input.send_keys(city + \"\\n\") time.sleep(5) driver.find_element_by_name(\"query\").click() time.sleep(3) for i in range(int(adult)): driver.find_element_by_xpath( \'//*[@id=\"menuItemComponent-guest_picker\"]/div/div/div/div[1]/div/div/div[1]/div/div/div/div/div/div[2]/div/div[3]/button\').click() time.sleep(4) for i in range(int(teen)): driver.find_element_by_xpath( \'//*[@id=\"menuItemComponent-guest_picker\"]/div/div/div/div[1]/div/div/div[2]/div/div/div/div/div/div[2]/div/div[3]/button\').click() time.sleep(3) for i in range(int(baby)): driver.find_element_by_xpath( \'//*[@id=\"menuItemComponent-guest_picker\"]/div/div/div/div[1]/div/div/div[3]/div/div/div/div/div/div[2]/div/div[3]/button\').click() time.sleep(5) driver.find_element_by_class_name(\"_fhph4u\")[0].click() time.sleep(20)
练习三
爬取某站入站必看视频信息
import time from selenium import webdriver url = \'https://www.baidu.com\' driverPath = r\'C:\\Users\\29273\\AppData\\Local\\Programs\\Python\\Python38-32\\chromedriver.exe\' driver = webdriver.Chrome(executable_path=driverPath) res = driver.find_elements_by_class_name(\"video-card\") for i in range(len(res)): print(\'第\' + str(i) + \'个视频\') print(\'up主:\' + str(res[i].find_element_by_class_name(\"up-name__text\").text)) print(\'视频名称:\' + str(res[i].find_element_by_class_name(\"video-name\").text)) print(\'视频播放量:\' + str(res[i].find_element_by_class_name(\"play-text\").text)) print(\'评论数:\' + str(res[i].find_element_by_class_name(\"like-text\").text)) print(\'note:\' + str(res[i].find_element_by_class_name(\"history-hint\").text))
© 版权声明
THE END
暂无评论内容