cx00000/南昌大学专业录取分数线.py

import requests
from lxml import etree
import pymysql
import re
from bs4 import BeautifulSoup

# MySQL数据库配置
db_config = {
    'host': 'localhost',
    'user': 'root',
    'password': '091020',
    'database': 'jdbc',
    'charset': 'utf8mb4',
    'cursorclass': pymysql.cursors.DictCursor #游标类型返回的结果是一个字典列表，其中每个字典都包含一行结果，字典的键是列名
}

# 爬取并保存数据到MySQL的函数
def crawl_and_save(year, url):
    datas = []
    response = requests.get(url)
    response.raise_for_status()  # 检查请求是否成功
    html = etree.HTML(response.text.encode('iso-8859-1').decode('utf-8'))
    htmlTxt = response.text.encode('iso-8859-1').decode('utf-8')

    table = html.xpath('//table')[0]
    # 提取数据
    if year == 2020:
        # 使用XPath提取表格的所有行
        rows = table.xpath('.//tbody/tr')
        # 遍历所有行，并提取每行的数据
        for row in rows:
            data = {
                'year': year,
                'category': row.xpath('.//td[1]/text()')[0] if row.xpath('.//td[1]') else '',
                'ProDirection': row.xpath('.//td[2]/text()')[0] if row.xpath('.//td[2]') else '',
                'FamCategories': row.xpath('.//td[3]/text()')[0] if row.xpath('.//td[3]') else '',
                'EnrollmentPlan': row.xpath('.//td[4]/text()')[0] if row.xpath('.//td[4]') else '',
                'ControlLine': row.xpath('.//td[5]/text()')[0] if row.xpath('.//td[5]') else '',
                'AdmissionLine': row.xpath('.//td[6]/text()')[0] if row.xpath('.//td[6]') else '',
                'ProAdmissionLine': row.xpath('.//td[7]/text()')[0] if row.xpath('.//td[7]') else '',
                'ReferenceRanking': row.xpath('.//td[8]/text()')[0] if row.xpath('.//td[8]') else '',
            }
            if data['category'] == '类别':
                continue
            datas.append(data)

    elif year == 2021:
        # 使用BeautifulSoup解析HTML代码
        soup = BeautifulSoup(htmlTxt, 'html.parser')
        # 找到包含表格的div元素
        div = soup.find('div', class_='blog-content')
        # 找到表格并提取信息
        table = div.find('table')
        rows = table.find_all('tr')
        for row in rows[2:]:  # 跳过表头和标题行
            cells = row.find_all('td')
            if len(cells) == 8:  # 确保行中有8个单元格
                category, category_type, major, recruitment, control_line, file_line, major_line, rank = cells
                data = {
                    'year': year,
                    'category': category.text,
                    'FamCategories': category_type.text,
                    'ProDirection': major.text,
                    'EnrollmentPlan': recruitment.text,
                    'ControlLine': control_line.text,
                    'AdmissionLine': file_line.text,
                    'ProAdmissionLine': major_line.text,
                    'ReferenceRanking': rank.text,
                }
                datas.append(data)

    elif year == 2022:
        # 正则表达式模式
        pattern = re.compile(r'<td.*?>(.*?)</td>')
        # 提取信息
        rows = re.findall(r'<tr.*?>(.*?)</tr>', htmlTxt, flags=re.DOTALL)  # 找到所有行
        for row in rows[2:]:  # 跳过表头和标题行
            cells = pattern.findall(row)
            if len(cells) == 7:
                data = {
                    'year': year,
                    'category': None,
                    'FamCategories': cells[0],
                    'ProDirection': cells[1],
                    'EnrollmentPlan': cells[2],
                    'ControlLine': cells[3],
                    'AdmissionLine': cells[4],
                    'ProAdmissionLine': cells[5],
                    'ReferenceRanking': cells[6],
                }
                datas.append(data)

    elif year == 2023:
        # 使用XPath提取表格的所有行
        rows = table.xpath('.//tbody/tr')
        # 遍历所有行，并提取每行的数据
        for row in rows:
            data = {
                'year': year,
                'category': None,
                'FamCategories': row.xpath('.//td[1]/text()')[0] if row.xpath('.//td[1]') else '',
                'ProDirection': row.xpath('.//td[2]/text()')[0] if row.xpath('.//td[2]') else '',
                'EnrollmentPlan': row.xpath('.//td[3]/text()')[0] if row.xpath('.//td[3]') else '',
                'ControlLine': row.xpath('.//td[4]/text()')[0] if row.xpath('.//td[4]') else '',
                'AdmissionLine': row.xpath('.//td[5]/text()')[0] if row.xpath('.//td[5]') else '',
                'ProAdmissionLine': row.xpath('.//td[6]/text()')[0] if row.xpath('.//td[6]') else '',
                'ReferenceRanking': row.xpath('.//td[7]/text()')[0] if row.xpath('.//td[7]') else '',
            }
            if data['FamCategories'] == '科类':
                continue
            datas.append(data)

    # 保存到MySQL
    save_to_mysql(datas)


# 保存到MySQL函数
def save_to_mysql(data_list):
    connection = pymysql.connect(**db_config)
    try:
        with connection.cursor() as cursor:
            # 插入数据
            insert_sql = """
            INSERT INTO `enroll` (`year`, `category`, `ProDirection`, `FamCategories`, `EnrollmentPlan`, `ControlLine`, `AdmissionLine`, `ProAdmissionLine`, `ReferenceRanking`)  
            VALUES (%s, %s, %s, %s, %s, %s, %s, %s, %s)  
            """
            for data in data_list:
                cursor.execute(insert_sql, (
                    data['year'],
                    data['category'],
                    data['ProDirection'],
                    data['FamCategories'],
                    data['EnrollmentPlan'],
                    data['ControlLine'],
                    data['AdmissionLine'],
                    data['ProAdmissionLine'],
                    data['ReferenceRanking']
                ))

                # 提交事务
        connection.commit()
    finally:
        connection.close()

def main():
    years_urls = {
        2020: 'https://zjc.ncu.edu.cn/zszx/lnfs/3e5d5e97e5924d1794fd0eba09b79bf2.htm',
        2021: 'https://zjc.ncu.edu.cn/zszx/lnfs/47c901697a5549e998baf512a0c384f5.htm',
        2022: 'https://zjc.ncu.edu.cn/zszx/lnfs/9ba4f80248874172af2937017620226b.htm',
        2023: 'https://zjc.ncu.edu.cn/zszx/lnfs/5f3d9db4a5304265be3e31725a290b5c.htm'
    }
    # 遍历年份和对应的URL，爬取并保存数据
    for year, url in years_urls.items():
        crawl_and_save(year, url)

if __name__ == '__main__':
    main()