Python Selenium自动化实现网页操控

pip install selenium==4.5.0

from selenium import webdriver
​
url = 'https://www.baidu.com'
​
# 创建浏览器操作对象
browser = webdriver.Chrome()
​
# 打开网页
browser.get(url)
# 获取源码(同requests.text)
print(browser.page_source)
input('用户按下回车键退出')
# 退出
browser.quit()

from selenium import webdriver
# 定位元素，必须要导入By
from selenium.webdriver.common.by import By
​
url = 'https://www.baidu.com'
​
# 创建浏览器操作对象
browser = webdriver.Chrome()
​
# 打开网页
browser.get(url)
​
# 通过id获取输入框
res1 = browser.find_element(By.ID,'kw')
print(res1)
​
# 通过name获取输入框
res2 = browser.find_element(By.NAME,'wd')
print(res2)
​
# 通过XPath获取输入框
res3 = browser.find_element(By.XPATH,"//*/input[@id='kw']")
print(res3)
print(res1==res2 and res2==res3)# True
​
# 通过类名获取输入框
res4 = browser.find_element(By.CLASS_NAME,"s_ipt")
​
# 通过css选择器来获取输入框
res5 = browser.find_element(By.CSS_SELECTOR,"#kw")
print(res3==res4 and res4==res5)# True
​
# 通过通过链接文本获取标签
res6 = browser.find_element(By.LINK_TEXT,"新闻")
​
# 通过部分链接文本获取标签
res7 = browser.find_element(By.PARTIAL_LINK_TEXT,"闻")
print(res6==res7)# True
​
# 通过标签名，并且由复数的形式获取a标签
res8 = browser.find_elements(By.TAG_NAME,"a")
print(res8)
​
input('用户按下回车键退出~')
# 退出
browser.quit()

from selenium import webdriver
from selenium.webdriver.common.by import By
​
# 创建浏览器操作对象
browser = webdriver.Chrome()
​
url = "https://www.baidu.com"
# 打开网页
browser.get(url)
​
# 获取到新闻文本的a链接(通过链接文本内容)
a = browser.find_element(By.LINK_TEXT,"新闻")
​
# 获取href
a_href = a.get_attribute('href')
print(f"href:{a_href}")
# 结果：href:http://news.baidu.com/
​
# 获取class
a_class = a.get_attribute('class')
print(f"class:{a_class}")
# 结果：class:mnav c-font-normal c-color-t
​
# 获取文本内容
a_text = a.text
print(a_text)
# 结果：新闻
​
# 获取标签名称
a_tag_name = a.tag_name
print(a_tag_name)
# 结果：a

from selenium import webdriver
from selenium.webdriver.common.by import By
import time
​
# 创建浏览器操作对象
browser = webdriver.Chrome()
# 将窗口最大化
# browser.maximize_window()
​
url = 'https://www.baidu.com'
# 打开浏览器
browser.get(url)
​
# 获取输入框
get_input = browser.find_element(By.ID,"kw")
# 输入周杰伦
get_input.send_keys('周杰伦')
​
# 获取点击按钮
get_button = browser.find_element(By.CSS_SELECTOR,"input[type='submit']")
# 执行点击操作
get_button.click()
​
def scoll():
    # 这里要进行等待，否则后面的滑动页面没有反应，目的是等待页面加载
    time.sleep(2)
    # 执行滑动
    js = 'document.documentElement.scrollTop=100000'
    browser.execute_script(js)
def next_page():
    scoll()
    time.sleep(2)
    # 获取下一页按钮
    next_button = browser.find_element(By.PARTIAL_LINK_TEXT,"下一页")
    # 执行点击操作
    next_button.click()
for i in range(3):
    next_page()
# 导航操作
browser.back()  # 回退
time.sleep(2)
browser.forward() # 前进
input('回车键退出程序~')
browser.quit()

# 导入模块
import time
from selenium import webdriver
from selenium.webdriver.common.by import By
from selenium.webdriver.support.ui import Select  # 专门处理下拉框
​
# 目标网站
url = 'https://kyfw.12306.cn/otn/regist/init'
​
# 创建浏览器操作对象
browser = webdriver.Chrome()
​
# 打开网页
browser.get(url)
​
# 获取下拉框对象
get_selector = browser.find_element(By.ID,'cardType')
# 实例化Selectors对象
selector = Select(get_selector)
time.sleep(2)
# 使用value来选定
# selector.select_by_value('B')
# 使用索引来选择
selector.select_by_index(5)
input('回车键退出程序~')
browser.quit()

# 导入模块
import time
from selenium import webdriver
from selenium.webdriver.common.by import By
import csv

# 目标网站
url = 'https://www.suning.com/'

# 创建浏览器操作对象
browser = webdriver.Chrome()

browser.maximize_window()
# 打开网页
browser.get(url)

# 获取输入框对象
input_element = browser.find_element(By.ID,"searchKeywords")
# 执行输入
input_element.send_keys('口红')
time.sleep(1)

# 获取点击按钮
button_element = browser.find_element(By.ID,"searchSubmit")
# 执行点击
button_element.click()
time.sleep(1)
# 下滑
def drop_down():
    time.sleep(6)
    for x in range(1,12,2):
        time.sleep(1)
        j = x / 9
        js = f'document.documentElement.scrollTop = document.documentElement.scrollHeight * {j}'
        browser.execute_script(js)
# 获取数据
def get_info():
    # 先执行下拉
    drop_down()
    # 构建字典
    info_dict = {
        '商品名称':"",
        '商品价格':"",
        '评论数':"",
        '店铺名称':"",
        '详情链接':"",
        '图片url':""
    }
    # 获取每一个盒子
    list_box = browser.find_elements(By.CLASS_NAME,"product-box ")
    if list_box:
        for box in list_box:
            # 获取商品名称
            title = box.find_element(By.CSS_SELECTOR,".title-selling-point > a").text
            info_dict['商品名称'] = title
            # 获取商品价格
            price = box.find_element(By.CSS_SELECTOR,".def-price").text
            info_dict['商品价格'] = price
            # 获取评论数
            comment = box.find_element(By.CSS_SELECTOR,".info-evaluate > a").text
            info_dict['评论数'] = comment
            # 获取店铺名称
            dianpu = box.find_element(By.CSS_SELECTOR,".store-stock > a").text
            info_dict['店铺名称'] = dianpu
            # 获取详情链接
            detail_url = box.find_element(By.CSS_SELECTOR,".title-selling-point > a").get_attribute('href')
            info_dict['详情链接'] = detail_url
            # 获取图片url
            photo_url = box.find_element(By.CSS_SELECTOR,".sellPoint > img").get_attribute('src')
            info_dict['图片url'] = photo_url
            csv_writer.writerow(info_dict)
            print(info_dict)
    else:
        print('没有获取到所有盒子')
flag = True
i = 1
with open('苏宁易购_口红.csv','w',newline='',encoding='utf-8') as f:
    field_list = ['商品名称','商品价格','评论数','店铺名称','详情链接','图片url']
    csv_writer = csv.DictWriter(f,fieldnames=field_list)
    csv_writer.writeheader()
    while flag:
        try:
            print(f'正在获取第{i}页内容')
            # 调用获取内容函数
            get_info()
            # # 获取下一页按钮
            # next_page_btn = browser.find_element(By.ID,"nextPage")
            # # 执行点击下一页
            # next_page_btn.click()
            # 翻页
            browser.execute_script('document.querySelector("#nextPage").click()')
            time.sleep(2)  # 等待页面加载
            i += 1
        except Exception as e:
            flag = False
            print('已经是最后一页了')
            input('回车键结束')
            browser.quit()