Python爬蟲基礎(chǔ)之selenium庫的用法總結(jié)

from selenium import webdriver

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

# 將webdriver實例化
path = 'C:\Program Files (x86)\Python38-32\chromedriver.exe'
browser = webdriver.Chrome(executable_path = path)

# 用谷歌瀏覽器訪問百度
 
r = browser.get(url)
with open ('test.txt','wb+') as f:
    f.write(r.content)

'''
代碼功能：selenium是的常用用法
時間：@Date: 2021-05-22 21:37:05
'''

from selenium import webdriver

# 導(dǎo)入Options類
from selenium.webdriver.chrome.options import Options

url = "https://movie.douban.com/"

# Options的實例化
chrome_options = Options()

# 設(shè)置瀏覽器參數(shù)

# --headless 是不顯示瀏覽器啟動以及執(zhí)行過程
chrome_options.add_argument('--headless')

# 設(shè)置lang和User-Agent信息，防止反爬檢測
chrome_options.add_argument('lang=zh_CN.utf-8')

UserAgent = 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/90.0.4430.93 Safari/537.36'

chrome_options.add_argument('User-Agent='+UserAgent)

# 啟動瀏覽器并設(shè)置chrome_options參數(shù)
driver = webdriver.Chrome(chrome_options=chrome_options)

# 設(shè)置瀏覽器窗口最大化
# driver.maximize_window()

# # 設(shè)置瀏覽器窗口最小化
# driver.minimize_window()

driver.get(url)

# 獲取網(wǎng)頁的標(biāo)題
print(driver.title)

# page_source是獲取網(wǎng)頁的HTML代碼
print(driver.page_source)

from selenium import webdriver
import time

# 啟動瀏覽器
driver = webdriver.Chrome()
driver.get('https://www.youdao.com')
time.sleep(5)

# 添加cookie
driver.add_cookie({'name':'login','value':'登錄'})

# 獲取全部cookie
allCookies = driver.get_cookies()

print('全部cookies',allCookies)

# 獲取name為login的cookie
cookie = driver.get_cookie('login')
print('name為login的cookie',cookie)

# 刪除單個cookie
driver.delete_cookie('login')
print("\n--------------剩余的cookies\n",driver.get_cookies())

# 刪除全部cookies
driver.delete_all_cookies()

print("-------------剩余的cookies------------\n",driver.get_cookies())

time.sleep(60)

!DOCTYPE html>
html lang="en">
head>
    meta charset="UTF-8">
    meta http-equiv="X-UA-Compatible" content="IE=edge">
    meta name="viewport" content="width=device-width, initial-scale=1.0">
    title>Document/title>
/head>
body>
    h1>配合selenium模擬上傳文件/h1>
    input type='file' name='file' />
/body>
/html>

'''
代碼功能：selenium上傳文件 --配合upload.html使用
時間：@Date: 2021-05-23 09:56:53
'''


from selenium import webdriver
import time

driver = webdriver.Chrome()

url = 'http://localhost:52330/selenium/upload.html'

driver.get(url)

ele = driver.find_element_by_name('file')
print("獲取到的元素",ele)

# 注意路徑不能有中文字符
ele.send_keys('D:\dcsdk_eventv3.db')
time.sleep(10)

'''
代碼功能：模擬文件下載
時間：@Date: 2021-05-23 10:21:28
'''

from selenium import webdriver
import time

# 設(shè)置文件保存路徑，如果不設(shè)置，會默認(rèn)保存到Downloads文件夾

options = webdriver.ChromeOptions()

prefs = {'download.default_directory':'D:\\'}
options.add_experimental_option('prefs',prefs)

# 啟動瀏覽器
driver = webdriver.Chrome()

# 下載PC版微信
driver.get('https://pc.weixin.qq.com')

# 瀏覽器窗口最大化
driver.maximize_window()
time.sleep(5)
# 點擊下載按鈕
driver.find_element_by_class_name('download-button').click()

time.sleep(30)

from selenium import webdriver
import time

url = 'https://www.baidu.com/'
driver = webdriver.Chrome()

# 隱式等待，一次設(shè)置對整個driver的周期都起作用
driver.implicitly_wait(30)

driver.get(url)

# 使用js開啟新的窗口
js = 'window.open("https://www.sogou.com/")'
driver.execute_script(js)


# 獲取當(dāng)前顯示的窗口信息
current_window = driver.current_window_handle

print(driver)
# 獲取瀏覽器的全部窗口信息
handles = driver.window_handles
print('獲取到的窗口全部信息\n------------------\n',handles)


'''
獲取到的窗口全部信息
------------------
 ['CDwindow-7FB808B4F24EF5385A9AFBDC21FA13B9', 'CDwindow-E879C0A64E734C3F88468A4388F48E3B']
'''

# 設(shè)置延時看切換的效果
time.sleep(3)


# 根據(jù)窗口信息進(jìn)行窗口切換
# 切換到百度搜索的窗口
driver.switch_to_window(handles[0])
time.sleep(3)


# 切換到搜狗窗口
driver.switch_to_window(handles[1])

'''
代碼功能：熟悉selenium的自動化操作
時間：2020/5/22
'''


from selenium import webdriver
from selenium.webdriver.common.keys import Keys
import time

# Keys 類中定義了很多快捷鍵


url = 'https://wwww.baidu.com'

path = 'C:\Program Files (x86)\Python38-32\chromedriver.exe'
driver = webdriver.Chrome(executable_path=path)
driver.get(url)

# 獲取輸入框標(biāo)簽對象
element = driver.find_element_by_id('kw')

# 輸入框輸入內(nèi)容
element.send_keys('python你')
time.sleep(2)

# 刪除最后一個文字
element.send_keys(Keys.BACK_SPACE)
time.sleep(2)

# 添加空格加教程
element.send_keys(Keys.SPACE)
element.send_keys("教程")
time.sleep(2)


# ctrl+a 全選輸入框內(nèi)容
element.send_keys(Keys.CONTROL, 'a')
time.sleep(2)

# ctrl+x 剪切輸入框內(nèi)容
element.send_keys(Keys.CONTROL, 'x')
time.sleep(2)
# ctrl+v 復(fù)制
element.send_keys(Keys.CONTROL, 'v')
time.sleep(2)

# 回車鍵
driver.find_element_by_id('su').send_keys(Keys.ENTER)
time.sleep(10)