数据采集与融合技术第四次作业

作业内容

作业①:

要求：
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https://gitee.com/xu-xuan2568177992/crawl_project/tree/master/4

from selenium import webdriver
from selenium.webdriver.common.by import By
from selenium.webdriver.chrome.service import Service
from selenium.webdriver.chrome.options import Options
from selenium.webdriver.support.wait import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
import time
import pymysql
chrome_driver_path = r"C:\Users\xxy\AppData\Local\Programs\Python\Python310\Scripts\chromedriver.exe"
service = Service(executable_path=chrome_driver_path)
options = Options()
options.add_argument('--disable-gpu')
options.add_argument('--disable-blink-features=AutomationControlled')
driver = webdriver.Chrome(service=service, options=options)
driver.maximize_window()

# 连接scrapy数据库，创建表
try:
    db = pymysql.connect(host='127.0.0.1',user='root',password='xxy4113216923',port=3306,database='scrapy')
    cursor = db.cursor()
    cursor.execute('DROP TABLE IF EXISTS stockT')
    sql = '''CREATE TABLE stockT(num varchar(32),id varchar(12),name varchar(32),Latest_quotation varchar(32),Chg varchar(12),up_down_amount varchar(12),
            turnover varchar(16),transaction_volume varchar(16),amplitude varchar(16),highest varchar(32), lowest varchar(32),today varchar(32),yesterday varchar(32))'''
    cursor.execute(sql)
except Exception as e:
    print(e)

def spider(page_num):
    cnt = 0
    while cnt < page_num:
        spiderOnePage()
        driver.find_element(By.XPATH,'//a[@class="next paginate_button"]').click()
        cnt +=1
    time.sleep(2)

# 爬取一个页面的数据
def spiderOnePage():
    time.sleep(3)
    trs = driver.find_elements(By.XPATH,'//table[@id="table_wrapper-table"]//tr[@class]')
    for tr in trs:
        tds = tr.find_elements(By.XPATH,'.//td')
        num = tds[0].text
        id = tds[1].text
        name = tds[2].text
        Latest_quotation = tds[6].text
        Chg = tds[7].text
        up_down_amount = tds[8].text
        turnover = tds[9].text
        transaction_volume = tds[10].text
        amplitude = tds[11].text
        highest = tds[12].text
        lowest = tds[13].text
        today = tds[14].text
        yesterday = tds[15].text
        cursor.execute('INSERT INTO stockT VALUES ("%s","%s","%s","%s","%s","%s","%s","%s","%s","%s","%s","%s","%s")' % (num,id,name,Latest_quotation,
                                                Chg,up_down_amount,turnover,transaction_volume,amplitude,highest,lowest,today,yesterday))
        db.commit()

# 访问东方财富网
driver.get('https://quote.eastmoney.com/center/gridlist.html#hs_a_board')
# 访问沪深京A股
driver.get(WebDriverWait(driver,10,0.48).until(EC.presence_of_element_located((By.ID,'menu_hs_a_board'))).get_attribute('href'))
# 爬取两页的数据
spider(2)
driver.back()

# 访问上证A股
driver.get(WebDriverWait(driver,10,0.48).until(EC.presence_of_element_located((By.ID,'menu_sh_a_board'))).get_attribute('href'))
spider(2)
driver.back()

# 访问深证A股
driver.get(WebDriverWait(driver,10,0.48).until(EC.presence_of_element_located((By.ID,'menu_sz_a_board'))).get_attribute('href'))
spider(2)

try:
    cursor.close()
    db.close()
except:
    pass
time.sleep(3)
driver.quit()

实验结果：

实验心得：
通过本次作业，我深入掌握了 Selenium 相关操作，包括查找元素、处理 Ajax 数据和等待元素。设计 MySQL 表头让我明白数据存储结构的重要性。过程有挑战，如东方财富网页结构变化和数据存储问题，但提升了编程和处理数据能力，对类似任务有很大帮助。

作业②:

要求：
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文件夹链接https://gitee.com/xu-xuan2568177992/crawl_project/tree/master/4

from selenium import webdriver
from selenium.webdriver.common.by import By
from selenium.webdriver.chrome.service import Service
from selenium.webdriver.chrome.options import Options
from selenium.webdriver.support.wait import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
import time
import pymysql

chrome_driver_path = r"C:\Users\xxy\AppData\Local\Programs\Python\Python310\Scripts\chromedriver.exe"
service = Service(executable_path=chrome_driver_path)
options = Options()
options.add_argument('--disable-gpu')
options.add_argument('--disable-blink-features=AutomationControlled')
driver = webdriver.Chrome(service=service, options=options)
driver.maximize_window()
# 连接MySql
try:
    db = pymysql.connect(host='127.0.0.1', user='root', password='xxy4113216923', port=3306, database='scrapy')
    cursor = db.cursor()
    cursor.execute('DROP TABLE IF EXISTS courseMessage')
    sql = '''CREATE TABLE courseMessage(cCourse varchar(64),cCollege varchar(64),cTeacher varchar(16),cTeam varchar(256),cCount varchar(16),
    cProcess varchar(32),cBrief varchar(2048))'''
    cursor.execute(sql)
except Exception as e:
    print(e)


# 爬取一个页面的数据
def spiderOnePage():
    time.sleep(5)  # 等待页面加载完成
    courses = driver.find_elements(By.XPATH, '//*[@id="channel-course-list"]/div/div/div[2]/div[1]/div')
    current_window_handle = driver.current_window_handle
    for course in courses:
        cCourse = course.find_element(By.XPATH, './/h3').text  # 课程名
        cCollege = course.find_element(By.XPATH, './/p[@class="_2lZi3"]').text  # 大学名称
        cTeacher = course.find_element(By.XPATH, './/div[@class="_1Zkj9"]').text  # 主讲老师
        cCount = course.find_element(By.XPATH, './/div[@class="jvxcQ"]/span').text  # 参与该课程的人数
        cProcess = course.find_element(By.XPATH, './/div[@class="jvxcQ"]/div').text  # 课程进展

        course.click()  # 点击进入课程详情页，在新标签页中打开
        Handles = driver.window_handles  # 获取当前浏览器的所有页面的句柄
        driver.switch_to.window(Handles[1])  # 跳转到新标签页
        time.sleep(5)  # 等待页面加载完成

        # 爬取课程详情数据
        # cBrief = WebDriverWait(driver,10,0.48).until(EC.presence_of_element_located((By.ID,'j-rectxt2'))).text
        cBrief = driver.find_element(By.XPATH, '//*[@id="j-rectxt2"]').text
        if len(cBrief) == 0:
            cBriefs = driver.find_elements(By.XPATH, '//*[@id="content-section"]/div[4]/div//*')
            cBrief = ""
            for c in cBriefs:
                cBrief += c.text

        # 将文本中的引号进行转义处理，防止插入表格时报错
        cBrief = cBrief.replace('"', r'\"').replace("'", r"\'")
        cBrief = cBrief.strip()

        # 爬取老师团队信息
        nameList = []
        cTeachers = driver.find_elements(By.XPATH, '//div[@class="um-list-slider_con_item"]')
        for Teacher in cTeachers:
            name = Teacher.find_element(By.XPATH, './/h3[@class="f-fc3"]').text.strip()
            nameList.append(name)
        # 如果有下一页的标签，就点击它，然后继续爬取
        nextButton = driver.find_elements(By.XPATH, '//div[@class="um-list-slider_next f-pa"]')
        while len(nextButton) != 0:
            nextButton[0].click()
            time.sleep(3)
            cTeachers = driver.find_elements(By.XPATH, '//div[@class="um-list-slider_con_item"]')
            for Teacher in cTeachers:
                name = Teacher.find_element(By.XPATH, './/h3[@class="f-fc3"]').text.strip()
                nameList.append(name)
            nextButton = driver.find_elements(By.XPATH, '//div[@class="um-list-slider_next f-pa"]')
        cTeam = ','.join(nameList)

        driver.close()  # 关闭新标签页
        driver.switch_to.window(current_window_handle)  # 跳转回原始页面
        try:
            cursor.execute('INSERT INTO courseMessage VALUES ("%s","%s","%s","%s","%s","%s","%s")' % (
            cCourse, cCollege, cTeacher, cTeam, cCount, cProcess, cBrief))
            db.commit()
        except Exception as e:
            print(e)


# 访问中国大学慕课
driver.get('https://www.icourse163.org/')


# 访问国家精品课程
driver.get(WebDriverWait(driver, 10, 0.48).until(
    EC.presence_of_element_located((By.XPATH, '//*[@id="app"]/div/div/div[1]/div[1]/div[1]/span[1]/a'))).get_attribute(
    'href'))
spiderOnePage()  # 爬取第一页的内容

count = 1
'''翻页操作'''
# 下一页的按钮
next_page = driver.find_element(By.XPATH, '//*[@id="channel-course-list"]/div/div/div[2]/div[2]/div/a[10]')
# 如果还有下一页，那么该标签的class属性为_3YiUU
while next_page.get_attribute('class') == '_3YiUU ':
    if count == 3:
        break
    count += 1
    next_page.click()  # 点击按钮实现翻页
    spiderOnePage()  # 爬取一页的内容
    next_page = driver.find_element(By.XPATH, '//*[@id="channel-course-list"]/div/div/div[2]/div[2]/div/a[10]')

try:
    cursor.close()
    db.close()
except:
    pass

time.sleep(3)
driver.quit()

实验结果：

实验心得：
此次作业让我对 Selenium 有了新认识，模拟登录很关键。爬取 mooc 网课程信息使我在数据提取和存储上有了更多实践经验，也提高了应对复杂网页结构的能力，有助于今后的爬虫工作。