pip install selenium==4.5.0

from selenium import webdriver
?
url = 'https://www.baidu.com'
?
# 創(chuàng)建瀏覽器操作對(duì)象
browser = webdriver.Chrome()
?
# 打開網(wǎng)頁
browser.get(url)
# 獲取源碼(同requests.text)
print(browser.page_source)
input('用戶按下回車鍵退出')
# 退出
browser.quit()

from selenium import webdriver
# 定位元素，必須要導(dǎo)入By
from selenium.webdriver.common.by import By
?
url = 'https://www.baidu.com'
?
# 創(chuàng)建瀏覽器操作對(duì)象
browser = webdriver.Chrome()
?
# 打開網(wǎng)頁
browser.get(url)
?
# 通過id獲取輸入框
res1 = browser.find_element(By.ID,'kw')
print(res1)
?
# 通過name獲取輸入框
res2 = browser.find_element(By.NAME,'wd')
print(res2)
?
# 通過XPath獲取輸入框
res3 = browser.find_element(By.XPATH,"http://*/input[@id='kw']")
print(res3)
print(res1==res2 and res2==res3)# True
?
# 通過類名獲取輸入框
res4 = browser.find_element(By.CLASS_NAME,"s_ipt")
?
# 通過css選擇器來獲取輸入框
res5 = browser.find_element(By.CSS_SELECTOR,"#kw")
print(res3==res4 and res4==res5)# True
?
# 通過通過鏈接文本獲取標(biāo)簽
res6 = browser.find_element(By.LINK_TEXT,"新聞")
?
# 通過部分鏈接文本獲取標(biāo)簽
res7 = browser.find_element(By.PARTIAL_LINK_TEXT,"聞")
print(res6==res7)# True
?
# 通過標(biāo)簽名，并且由復(fù)數(shù)的形式獲取a標(biāo)簽
res8 = browser.find_elements(By.TAG_NAME,"a")
print(res8)
?
input('用戶按下回車鍵退出~')
# 退出
browser.quit()

from selenium import webdriver
from selenium.webdriver.common.by import By
?
# 創(chuàng)建瀏覽器操作對(duì)象
browser = webdriver.Chrome()
?
url = "https://www.baidu.com"
# 打開網(wǎng)頁
browser.get(url)
?
# 獲取到新聞文本的a鏈接(通過鏈接文本內(nèi)容)
a = browser.find_element(By.LINK_TEXT,"新聞")
?
# 獲取href
a_href = a.get_attribute('href')
print(f"href:{a_href}")
# 結(jié)果：href:http://news.baidu.com/
?
# 獲取class
a_class = a.get_attribute('class')
print(f"class:{a_class}")
# 結(jié)果：class:mnav c-font-normal c-color-t
?
# 獲取文本內(nèi)容
a_text = a.text
print(a_text)
# 結(jié)果：新聞
?
# 獲取標(biāo)簽名稱
a_tag_name = a.tag_name
print(a_tag_name)
# 結(jié)果：a

from selenium import webdriver
from selenium.webdriver.common.by import By
import time
?
# 創(chuàng)建瀏覽器操作對(duì)象
browser = webdriver.Chrome()
# 將窗口最大化
# browser.maximize_window()
?
url = 'https://www.baidu.com'
# 打開瀏覽器
browser.get(url)
?
# 獲取輸入框
get_input = browser.find_element(By.ID,"kw")
# 輸入周杰倫
get_input.send_keys('周杰倫')
?
# 獲取點(diǎn)擊按鈕
get_button = browser.find_element(By.CSS_SELECTOR,"input[type='submit']")
# 執(zhí)行點(diǎn)擊操作
get_button.click()
?
def scoll():
    # 這里要進(jìn)行等待，否則后面的滑動(dòng)頁面沒有反應(yīng)，目的是等待頁面加載
    time.sleep(2)
    # 執(zhí)行滑動(dòng)
    js = 'document.documentElement.scrollTop=100000'
    browser.execute_script(js)
def next_page():
    scoll()
    time.sleep(2)
    # 獲取下一頁按鈕
    next_button = browser.find_element(By.PARTIAL_LINK_TEXT,"下一頁")
    # 執(zhí)行點(diǎn)擊操作
    next_button.click()
for i in range(3):
    next_page()
# 導(dǎo)航操作
browser.back()  # 回退
time.sleep(2)
browser.forward() # 前進(jìn)
input('回車鍵退出程序~')
browser.quit()

# 導(dǎo)入模塊
import time
from selenium import webdriver
from selenium.webdriver.common.by import By
from selenium.webdriver.support.ui import Select  # 專門處理下拉框
?
# 目標(biāo)網(wǎng)站
url = 'https://kyfw.12306.cn/otn/regist/init'
?
# 創(chuàng)建瀏覽器操作對(duì)象
browser = webdriver.Chrome()
?
# 打開網(wǎng)頁
browser.get(url)
?
# 獲取下拉框?qū)ο?
get_selector = browser.find_element(By.ID,'cardType')
# 實(shí)例化Selectors對(duì)象
selector = Select(get_selector)
time.sleep(2)
# 使用value來選定
# selector.select_by_value('B')
# 使用索引來選擇
selector.select_by_index(5)
input('回車鍵退出程序~')
browser.quit()

# 導(dǎo)入模塊
import time
from selenium import webdriver
from selenium.webdriver.common.by import By
import csv

# 目標(biāo)網(wǎng)站
url = 'https://www.suning.com/'

# 創(chuàng)建瀏覽器操作對(duì)象
browser = webdriver.Chrome()

browser.maximize_window()
# 打開網(wǎng)頁
browser.get(url)

# 獲取輸入框?qū)ο?
input_element = browser.find_element(By.ID,"searchKeywords")
# 執(zhí)行輸入
input_element.send_keys('口紅')
time.sleep(1)

# 獲取點(diǎn)擊按鈕
button_element = browser.find_element(By.ID,"searchSubmit")
# 執(zhí)行點(diǎn)擊
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)
# 獲取數(shù)據(jù)
def get_info():
    # 先執(zhí)行下拉
    drop_down()
    # 構(gòu)建字典
    info_dict = {
        '商品名稱':"",
        '商品價(jià)格':"",
        '評(píng)論數(shù)':"",
        '店鋪名稱':"",
        '詳情鏈接':"",
        '圖片url':""
    }
    # 獲取每一個(gè)盒子
    list_box = browser.find_elements(By.CLASS_NAME,"product-box ")
    if list_box:
        for box in list_box:
            # 獲取商品名稱
            title = box.find_element(By.CSS_SELECTOR,".title-selling-point > a").text
            info_dict['商品名稱'] = title
            # 獲取商品價(jià)格
            price = box.find_element(By.CSS_SELECTOR,".def-price").text
            info_dict['商品價(jià)格'] = price
            # 獲取評(píng)論數(shù)
            comment = box.find_element(By.CSS_SELECTOR,".info-evaluate > a").text
            info_dict['評(píng)論數(shù)'] = comment
            # 獲取店鋪名稱
            dianpu = box.find_element(By.CSS_SELECTOR,".store-stock > a").text
            info_dict['店鋪名稱'] = dianpu
            # 獲取詳情鏈接
            detail_url = box.find_element(By.CSS_SELECTOR,".title-selling-point > a").get_attribute('href')
            info_dict['詳情鏈接'] = detail_url
            # 獲取圖片url
            photo_url = box.find_element(By.CSS_SELECTOR,".sellPoint > img").get_attribute('src')
            info_dict['圖片url'] = photo_url
            csv_writer.writerow(info_dict)
            print(info_dict)
    else:
        print('沒有獲取到所有盒子')
flag = True
i = 1
with open('蘇寧易購_口紅.csv','w',newline='',encoding='utf-8') as f:
    field_list = ['商品名稱','商品價(jià)格','評(píng)論數(shù)','店鋪名稱','詳情鏈接','圖片url']
    csv_writer = csv.DictWriter(f,fieldnames=field_list)
    csv_writer.writeheader()
    while flag:
        try:
            print(f'正在獲取第{i}頁內(nèi)容')
            # 調(diào)用獲取內(nèi)容函數(shù)
            get_info()
            # # 獲取下一頁按鈕
            # next_page_btn = browser.find_element(By.ID,"nextPage")
            # # 執(zhí)行點(diǎn)擊下一頁
            # next_page_btn.click()
            # 翻頁
            browser.execute_script('document.querySelector("#nextPage").click()')
            time.sleep(2)  # 等待頁面加載
            i += 1
        except Exception as e:
            flag = False
            print('已經(jīng)是最后一頁了')
            input('回車鍵結(jié)束')
            browser.quit()