Python Selenium爬取微博并登录163邮箱发送附件

使用selenium爬取微博头条标题数据，将数据写入表格中，再登录163邮箱进行发送---------------仅供参考

selenium的驱动下载地址

1. 先获取微博头条的数据

当打开微博点击头条时页面会自动跳转到一个空白页面，可以使用selenium中的 back() 进行后退

import time
from openpyxl import workbook  # 写入Excel表所用
from selenium import webdriver

class Wb_tt():
    def __init__(self):
        self.wb = webdriver.Chrome()
        self.item = {}
        self.lists = []
    def wb_get(self):
        # 获取微博数据
        self.wb.get('http://weibo.com/login.php')
        time.sleep(3)
        self.wb.find_element_by_xpath("//*[@id='pl_unlogin_home_leftnav']/div/ul/div[2]/li/a").click()
        time.sleep(0.5)
        # 后退
        self.wb.back()
        time.sleep(10)
        # 控制滚轮逐步进行向下滑动
        for y in range(10):
            js = 'window.scrollBy(0,1000)'
            self.wb.execute_script(js)
            time.sleep(0.5)
        time.sleep(1)
        # 获得整个div
        content = self.wb.find_elements_by_xpath('//ul/div[@class="UG_list_b"]')
        # print(content)
        time.sleep(2)
        return content
    def wb_info(self, item):
        # 处理微博数据
        for x in item:
            title = x.find_element_by_xpath('./div[2]/h3/a').text
            source = x.find_element_by_xpath('./div[2]/div/a[2]/span').text
            time = x.find_element_by_xpath('./div[2]/div/span').text
            img = x.find_element_by_xpath('./div[1]/img').get_attribute('src')
            print(title, source, time, img)
            #  存入的数据不能为字符串
            yield [title] + [source] + [time] + [img]
    def wb_save(self, info):
        wb = workbook.Workbook()  # 创建Excel对象
        ws = wb.active  # 获取当前正在操作的表对象
        ws.append(['标题', '来源', '时间', '图片'])
        print(type(info))
        for data in info:
            print('正在写入表格')
            ws.append(data)
        # 保存的名字
        wb.save('wbtt.xlsx')
        print('抓取成功')
        time.sleep(2)
        self.wb.quit()
if __name__ == '__main__':
    result = Wb_tt()
    item = result.wb_get()
    time.sleep(3)
    info = result.wb_info(item)
    time.sleep(3)
    result.wb_save(info)

获取的数据如下：

2. 登录163邮箱发送邮件

想要登录必须要进入iframe

import time
from selenium import webdriver


def Login_163(browser):
    # 登录邮箱
    # browser.save_screenshot("163邮箱.png")
    browser.maximize_window()
    iframe = browser.find_element_by_xpath('//div[@id="loginDiv"]/iframe')
    # 进入iframe
    browser.switch_to.frame(iframe)
    # 输入自己的邮箱账号
    browser.find_element_by_name("email").send_keys('输入自己的账号')
    time.sleep(2)
    # 输入密码
    browser.find_element_by_name("password").send_keys('输入自己的密码')
    time.sleep(2)
    # 点击登录
    browser.find_element_by_id('dologin').click()
    time.sleep(5)


def Wite_email(browser):
    browser.switch_to_default_content()  # 跳出frame，回到主页面
    # 点击写信
    browser.find_element_by_xpath("//*[@id='dvNavTop']/ul/li[2]/span[2]").click()
    # 输入收件人
    browser.find_element_by_class_name('nui-editableAddr-ipt').send_keys('[e-mail]')
    # 输入主题
    browser.find_element_by_xpath("//*[@class='nui-ipt-input'and @type = 'text' and @tabindex = '1']").send_keys('selenium爬虫')
    time.sleep(4)
    # 此时要输入要传送的文件路径如：C:\Users\123\Desktop\Selenium爬虫\wbtt.xlsx
    browser.find_element_by_xpath("//input[@type='file' and @class='O0']").send_keys(r"存放自己要发送的路径")
    time.sleep(2)
    # 进入内容
    browser.switch_to.frame(browser.find_element_by_xpath("//iframe[contains(@class,'APP-editor-iframe')]"))
    browser.find_element_by_class_name("nui-scroll").send_keys('123456789')  # 可以输入要发送内容
    browser.switch_to_default_content()
    #点击发送
    browser.find_element_by_xpath("//*[@class='nui-toolbar-item']/div//span[2]").click()


    time.sleep(10)
    browser.quit()

if __name__ == '__main__':
    # 使用谷歌浏览器
    browser = webdriver.Chrome()
    browser.get('https://mail.163.com/')
    Login_163(browser)
    Wite_email(browser)

3. 完整代码

import time
from openpyxl import workbook  # 写入Excel表所用
from selenium import webdriver

class Wb_tt():
    def __init__(self):
        self.wb = webdriver.Chrome()
        self.item = {}
        self.lists = []

    def wb_get(self):
        # 获取微博数据
        self.wb.get('http://weibo.com/login.php')
        time.sleep(3)
        self.wb.find_element_by_xpath("//*[@id='pl_unlogin_home_leftnav']/div/ul/div[2]/li/a").click()
        time.sleep(2)
        # 后退
        self.wb.back()
        time.sleep(10)
        # 控制滚轮逐步进行向下滑动
        for y in range(10):
            js = 'window.scrollBy(0,700)'
            self.wb.execute_script(js)
            time.sleep(0.5)
        time.sleep(1)
        # 获得源码
        content = self.wb.find_elements_by_xpath('//ul/div[@class="UG_list_b"]')
        time.sleep(3)
        return content

    def wb_info(self, item):
        #  使用xpath处理微博数据
        for x in item:
            # 标题  来源  时间  图片
            title = x.find_element_by_xpath('./div[2]/h3/a').text
            source = x.find_element_by_xpath('./div[2]/div/a[2]/span').text
            time = x.find_element_by_xpath('./div[2]/div/span').text
            img = x.find_element_by_xpath('./div[1]/img').get_attribute('src')
            print(title, source, time, img)
            #  存入的数据不能为字符串
            yield [title] + [source] + [time] + [img]

    def wb_save(self, info):
        wb = workbook.Workbook()  # 创建Excel对象
        ws = wb.active  # 获取当前正在操作的表对象
        ws.append(['标题', '来源', '时间', '图片'])

        for data in info:
            print(type(data))
            ws.append(data)
        wb.save('wbtt.xlsx')
        print('抓取成功')

        time.sleep(5)

    def Login_163(self):
        # 登录163邮箱
        # browser.save_screenshot("163邮箱.png")
        self.wb.get('https://mail.163.com/')
        iframe = self.wb.find_element_by_xpath('//div[@id="loginDiv"]/iframe')
        self.wb.switch_to.frame(iframe)
        self.wb.find_element_by_name("email").send_keys('输入账号')  # 163邮箱的账号
        time.sleep(2)
        self.wb.find_element_by_name("password").send_keys('输入密码')  # 163邮箱的密码
        time.sleep(2)
        self.wb.find_element_by_id('dologin').click()
        time.sleep(5)

    def Wite_email(self):
        self.wb.switch_to_default_content()  # 跳出frame，回到主页面
        # 点击写信
        self.wb.find_element_by_xpath("//*[@id='dvNavTop']/ul/li[2]/span[2]").click()
        # 输入收件人
        self.wb.find_element_by_class_name('nui-editableAddr-ipt').send_keys('[e-mail]')  # 这里输入收件人的名字
        # 输入主题
        self.wb.find_element_by_xpath("//*[@class='nui-ipt-input'and @type = 'text' and @tabindex = '1']").send_keys(
            'selenium爬虫')
        time.sleep(4)
        # 输入自己要发送文件的路径
        self.wb.find_element_by_xpath("//input[@type='file' and @class='O0']").send_keys(
            r"C:\Users\123\Desktop\Flask_New\Selenium爬虫\wbtt.xlsx")  # 这里存放刚刚保存的xlsx表的路径
        time.sleep(2)
        # 进入内容
        self.wb.switch_to.frame(self.wb.find_element_by_xpath("//iframe[contains(@class,'APP-editor-iframe')]"))
        self.wb.find_element_by_class_name("nui-scroll").send_keys('123456789')
        self.wb.switch_to_default_content()
        # 点击发送
        self.wb.find_element_by_xpath("//*[@class='nui-toolbar-item']/div//span[2]").click()

        time.sleep(10)
        self.wb.quit()


if __name__ == '__main__':
    result = Wb_tt()
    item = result.wb_get()
    info = result.wb_info(item)
    result.wb_save(info)
    result.Login_163()
    result.Wite_email()

本文地址：https://blog.csdn.net/weixin_44369251/article/details/107675754