selenium学习

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

def func():
    browser = webdriver.Chrome(chrome)  # 实例化浏览器对象
    url = 'https://www.baidu.com'
    browser.get(url)  # 发送get请求
    browser.save_screenshot('baidu.png')  # 截图页面
    browser.close()  # 关闭当前页面
    browser.quit()  # 退出


def func2():
    browser = webdriver.Chrome(chrome)
    url = 'https://movie.douban.com'
    browser.get(url)
    browser.maximize_window()  # 最大化窗口

    # 输入文本
    browser.find_element_by_xpath('//*[@id="inp-query"]').send_keys('周星驰')
    # 点击搜索
    browser.find_element_by_xpath('//*[@id="db-nav-movie"]/div[1]/div/div[2]/form/fieldset/div[2]/input').click()
    # 获取当前网页源码
    print(browser.page_source)
    # 在网页源码中查找
    print(browser.page_source.find('keywords'))
    # 查看cookie
    browser.get_cookies()
    # 获取当前url
    print(browser.current_url)
    # 切换frame
    browser.switch_to_frame('id name')
    # 页面进度条下拉操作
    browser.execute_script('window.scrollTo(0,document.body.scrollHeight)')


def func3():
    url = 'http://www.pyttip.com/user/login'
    browser = webdriver.Chrome(chrome)
    browser.maximize_window()
    # 请求网页
    browser.get(url)
    # 输入账号
    browser.find_element_by_xpath('//*[@id="editor_name"]').send_keys('lianggege')
    # 输入密码
    browser.find_element_by_xpath('//*[@id="editor_pwd"]').send_keys('123')
    # 点击登录
    browser.find_element_by_xpath('//*[@id="apLogin"]/fieldset/div[3]/input').click()


class JdSpider():
    def __init__(self):
        self.url = 'https://www.jd.com'
        self.browser = webdriver.Chrome(chrome)
        self.browser.implicitly_wait(10)  # 隐式等待

    def get_page(self):
        self.browser.get(self.url)
        self.browser.find_element_by_xpath('//*[@id="key"]').send_keys('爬虫')
        self.browser.find_element_by_xpath('//*[@id="search"]/div/div[2]/button').click()
        self.browser.find_element_by_class_name('pn-next').click()
        self.browser.close()
        self.browser.quit()
    def main(self):
        self.get_page()

def func4():
    # 防止被反爬
    option = ChromeOptions()
    # option.add_argument('--headless')  # 变成无头浏览器
    option.add_experimental_option('excludeSwitches', ['enable-automation'])
    # 关闭自动化扩展信息
    option.add_experimental_option('useAutomationExtension', False)
    browser = webdriver.Chrome(chrome, options=option)
    browser.execute_cdp_cmd("Page.addScriptToEvaluateOnNewDocument", {
        "source": """
        Object.defineProperty(navigator, 'webdriver', {
          get: () => undefined
        })
      """
    })
    url = 'https://www.zhipin.com'
    browser.get(url)
    browser.find_element_by_xpath('//*[@id="wrap"]/div[4]/div/div/div[1]/form/div[2]/p/input').send_keys('python')
    time.sleep(3)
    browser.execute_cdp_cmd('Page.addScriptToEvaluateOnNewDocument', {'source': 'Object.defineProperty(navigator, "webdriver", {get:()=>undefined})'})
    browser.find_element_by_xpath('//*[@id="wrap"]/div[4]/div/div/div[1]/form/button').send_keys(Keys.ENTER)


def func5():
    # 访问首页
    url = 'https://www.jd.com'
    browser = webdriver.Chrome(chrome)
    browser.execute_cdp_cmd("Page.addScriptToEvaluateOnNewDocument", {
        "source": """
            Object.defineProperty(navigator, 'webdriver', {
              get: () => undefined
            })
          """
    })
    browser.get(url)
    browser.maximize_window()
    # 文本输入点击搜索
    browser.find_element_by_xpath('//*[@id="key"]').send_keys('python')
    browser.find_element_by_xpath('//*[@id="search"]/div/div[2]/button').click()
    time.sleep(5)
    # 模拟下拉
    browser.execute_script('window.scrollTo(0,document.body.scrollHeight)')
    # 获取网页源码
    html = browser.page_source
    # 解析网页
    li_list = browser.find_elements_by_xpath('//*[@id="J_goodsList"]/ul')
    for li in li_list:
        print(li)
    browser.quit()


def func6():
    # 访问首页
    url = 'https://www.zhipin.com'
    # 防止被反爬
    option = ChromeOptions()
    # option.add_argument('--headless')  # 变成无头浏览器
    option.add_experimental_option('excludeSwitches', ['enable-automation'])
    # 关闭自动化扩展信息
    option.add_experimental_option('useAutomationExtension', False)
    browser = webdriver.Chrome(chrome, options=option)
    browser.get(url)
    browser.maximize_window()
    # 文本输入点击搜索
    browser.find_element_by_xpath('//*[@id="wrap"]/div[4]/div/div/div[1]/form/div[2]/p/input').send_keys('python')
    browser.find_element_by_xpath('//*[@id="wrap"]/div[4]/div/div/div[1]/form/button').click()
    time.sleep(5)
    # 获取网页源码
    html = browser.page_source
    # 解析网页
    li_list = browser.find_elements_by_xpath('//*[@id="main"]/div/div[2]/ul/li')
    for li in li_list:
        print(li.text)
    browser.quit()


def func7():
    api_url = 'http://music.163.com/song/media/outer/url?id=152428'
    header = {}
    resp = requests.get(api_url, headers=header)
    with open('朋友.mps', 'wb') as f:
        f.write(resp.content)


def func8():
    headers = {
        'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.9',
        'Accept-Encoding': 'gzip, deflate',
        'Accept-Language': 'zh-CN,zh;q=0.9',
        'Cache-Control': 'max-age=0',
        'Connection': 'keep-alive',
        'Host': 'image.baidu.com',
        'Upgrade-Insecure-Requests': '1',
        'Cookie': 'BDqhfp=python3%E7%BD%91%E7%BB%9C%E7%88%AC%E8%99%AB%E5%BC%80%E5%8F%91%E5%AE%9E%E8%B7%B5%26%26NaN-1undefined%26%260%26%261; PSTM=1585531752; BAIDUID=CA59CB70CF87EDC55E83B1B18AC659EE:FG=1; BIDUPSID=A7FD529C72D6849145DB5CEB87BF005D; BDUSS=NWd2RHcHRrMXFRMHczMmNaSWxHa1NZUncyZGdNS1NpRUFla2RuWUw2ZmZEczVlRVFBQUFBJCQAAAAAAAAAAAEAAAC~o9uvbGlhbmdnZWdlaGNsAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAN-Bpl7fgaZeel; MCITY=-131%3A; BDORZ=B490B5EBF6F3CD402E515D22BCDA1598; BDRCVFR[feWj1Vr5u3D]=I67x6TjHwwYf0; delPer=0; PSINO=5; BDRCVFR[dG2JNJb_ajR]=mk3SLVN4HKm; BDRCVFR[-pGxjrCMryR]=mk3SLVN4HKm; H_PS_PSSID=; userFrom=www.baidu.com',
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/79.0.3945.117 Safari/537.36'
    }
    response = requests.get('http://www.baidu.com', headers=headers)
    print(response.text)
    # # print(response.request.headers)  # 获取请求头
    # html = response.text
    # with open('123.jpg', 'wb') as f:
    #     f.write(response.content)
func8()