526互联

数据采集实践第四次作业

发布时间 2023-11-06 20:38:09作者: 熏风雪奈

作业①

熟练掌握 Selenium 查找 HTML 元素、爬取 Ajax 网页数据、等待 HTML 元素等内容。
使用 Selenium 框架+ MySQL 数据库存储技术路线爬取“沪深 A 股”、“上证 A 股”、“深证 A 股”3 个板块的股票数据信息。
候选网站：东方财富网：http://quote.eastmoney.com/center/gridlist.html#hs_a_board
输出信息：MYSQL 数据库存储和输出格式如下，表头应是英文命名例如：序号id，股票代码：bStockNo……，由同学们自行定义设计表头：
Gitee文件夹链接：点这里

代码展示

代码

from selenium import webdriver
from lxml import etree
from selenium.webdriver.common.by import By
import time
import mysql.connector

def get_data(url):
    html = driver.page_source
    bs = etree.HTML(html)
    lis = bs.xpath('//*[@id="table_wrapper-table"]/tbody/tr')
    for link in lis:
        a = link.xpath('./td[2]/a/text()')[0]
        b = link.xpath('./td[3]/a/text()')[0]
        c = link.xpath('./td[5]/span/text()')[0]
        d = link.xpath('./td[6]/span/text()')[0]
        e = link.xpath('./td[7]/span/text()')[0]
        f = link.xpath('./td[8]/text()')[0]
        g = link.xpath('./td[9]/text()')[0]
        h = link.xpath('./td[10]/text()')[0]
        i = link.xpath('./td[11]/span/text()')[0]
        j = link.xpath('./td[12]/span/text()')[0]
        k = link.xpath('./td[13]/span/text()')[0]
        l = link.xpath('./td[14]/text()')[0]
        mydb = mysql.connector.connect(
            host="localhost",
            user="root",
            password="wjy514520",
            database="mydb"
        )
        mycursor = mydb.cursor()

        sql = "INSERT INTO shiyan42 (代码, 名称, 最新价, 涨跌幅, 涨跌额, 成交量, 成交额, 振幅, 最高, 最低, 今开, 昨收) VALUES (%s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s)"
        val = (a, b, c, d, e, f, g, h, i, j, k, l)
        mycursor.execute(sql, val)
        mydb.commit()
        print(a,b,c,d,e,f,g,h,i,j,k,l)
    next_button = driver.find_element(By.XPATH, url)
    next_button.click()
    time.sleep(2)




chrome_options = webdriver.ChromeOptions()
chrome_options.add_argument('--headless')
chrome_options.add_argument('--disable-gpu')

driver = webdriver.Chrome(options=chrome_options)

driver.get("https://quote.eastmoney.com/center/gridlist.html#hs_a_board")
get_data('//*[@id="nav_sh_a_board"]/a')
get_data('//*[@id="nav_sz_a_board"]/a')
get_data('//*[@id="nav_bj_a_board"]/a')

运行结果



心得体会

这次实验的作业①对我来说并不难，之前写过多次类似的代码，主要的难点在于对动态页面的爬取和Xpath的运用，总体并没有花费多少时间。

作业②

熟练掌握 Selenium 查找 HTML 元素、实现用户模拟登录、爬取 Ajax 网页数据、
等待 HTML 元素等内容。
使用 Selenium 框架+MySQL 爬取中国 mooc 网课程资源信息（课程号、课程名
称、学校名称、主讲教师、团队成员、参加人数、课程进度、课程简介）
候选网站：中国 mooc 网：https://www.icourse163.org
输出信息：MYSQL 数据库存储和输出格式
Gitee文件夹：点这里

代码展示

代码

from selenium import webdriver
from lxml import etree
from selenium.webdriver.common.by import By
import time
import mysql.connector


chrome_options = webdriver.ChromeOptions()
chrome_options.add_argument('--headless')
chrome_options.add_argument('--disable-gpu')

driver = webdriver.Chrome(options=chrome_options)

#登录
driver.get('https://www.icourse163.org/')
time.sleep(2)
driver.maximize_window()
next_button = driver.find_element(By.XPATH, '//*[@id="app"]/div/div/div[1]/div[3]/div[3]/div')
next_button.click()
time.sleep(2)
frame = driver.find_element(By.XPATH,'/html/body/div[13]/div[2]/div/div/div/div/div/div[1]/div/div[1]/div[2]/div[2]/div[1]/div/iframe')
driver.switch_to.frame(frame)
# 输入账号
account = driver.find_element(By.ID, 'phoneipt').send_keys('17268180769')
# 输入密码
password = driver.find_element(By.XPATH, '/html/body/div[2]/div[2]/div[2]/form/div/div[4]/div[2]/input[2]').send_keys("qwertyuiop123!")
# 获取登录按钮
logbutton = driver.find_element(By.XPATH, '/html/body/div[2]/div[2]/div[2]/form/div/div[6]/a')
# 点击按钮
logbutton.click()
time.sleep(2)




driver.get('https://www.icourse163.org/search.htm?search=%E5%A4%A7%E5%AD%A6#/')
time.sleep(2)
next_button = driver.find_element(By.XPATH, '/html/body/div[4]/div[2]/div[2]/div[2]/div/div[6]/div[1]/div[1]/label/div')
next_button.click()
time.sleep(2)
js = '''
        timer = setInterval(function(){
           var scrollTop=document.documentElement.scrollTop||document.body.scrollTop;
           var ispeed=Math.floor(document.body.scrollHeight / 100);
           if(scrollTop > document.body.scrollHeight * 90 / 100){
               clearInterval(timer);
           }
           console.log('scrollTop:'+scrollTop)
           console.log('scrollHeight:'+document.body.scrollHeight)
           window.scrollTo(0, scrollTop+ispeed)
        }, 20)
        '''
for i in range(1,5):
    driver.execute_script(js)
    time.sleep(4)
    html = driver.page_source
    bs = etree.HTML(html)
    lis = bs.xpath('/html/body/div[4]/div[2]/div[2]/div[2]/div/div[6]/div[2]/div[1]/div/div/div')
    for link in lis:
        a = link.xpath('./div[2]/div/div/div[1]/a[2]/span/text()')
        if len(a) != 0:
            if a[0] == '国家精品':
                b = link.xpath('./div[2]/div/div/div[1]/a[1]/span/text()')[0]
                c = link.xpath('./div[2]/div/div/div[2]/a[1]/text()')[0]
                d = link.xpath('./div[2]/div/div/div[2]/a[2]/text()')[0]
                e = link.xpath('./div[2]/div/div/a/span/text()')[0]
                f = link.xpath('./div[2]/div/div/div[3]/div/span[2]/text()')[0]
                g = link.xpath('./div[2]/div/div/div[2]/span/span/span/span/span/span/a/text()')[0]
                h = link.xpath('./div[2]/div/div/div[3]/span[2]/text()')[0]
                mydb = mysql.connector.connect(
                    host="localhost",
                    user="root",
                    password="wjy514520",
                    database="mydb"
                )
                mycursor = mydb.cursor()

                sql = "INSERT INTO shiyan42 (cCourse,cCollege,cTeacher,cTeam,cCount,cProcess,cBrief) VALUES (%s, %s, %s, %s, %s, %s, %s)"
                val = (b, c, d, e, f, g, h)
                mycursor.execute(sql, val)
                mydb.commit()
    next_button = driver.find_element(By.XPATH, '//*[@id="j-courseCardListBox"]/div[2]/ul/li[10]')
    next_button.click()
    time.sleep(2)

运行结果

心得体会

这次实验的作业二给我带来了很大困难，首先是模拟浏览器登录，虽然有ppt的帮助，还是花费了很多时间调试代码，自动翻页的实现也比较困难，最后通过查询资料解决，Xpath的定位也花费了不少时间，完成这个实验让我学到了很多。

作业③

实验环境搭建



任务一

任务二

任务三




任务四