2024 数据采集与融合技术实践 - 作业2

作业①

题目描述

  1. 中国气象网 给定城市集的 7 日天气预报,并将结果保存到数据库。

代码:

import requests
import sqlite3
from bs4 import BeautifulSoup

# 创建数据库并创建表
def create_database():
    conn = sqlite3.connect('weather_forecast.db')
    c = conn.cursor()
    # 创建包含序号、地区、日期、天气信息和温度的表
    c.execute('''
        CREATE TABLE IF NOT EXISTS weather_forecast (
            id INTEGER PRIMARY KEY AUTOINCREMENT,
            city TEXT,
            date TEXT,
            weather TEXT,
            temperature TEXT
        )
    ''')
    conn.commit()
    return conn

# 获取7天的天气数据
def get_weather_data(city_code):
    url = f'http://www.weather.com.cn/weather/{city_code}.shtml'
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/129.0.0.0 Safari/537.36 Edg/129.0.0.0'
    }
    response = requests.get(url, headers=headers)
    response.encoding = 'utf-8'
    soup = BeautifulSoup(response.text, 'html.parser')

    weather_data = []
    forecast = soup.find('ul', class_='t clearfix')
    days = forecast.find_all('li')

    for day in days:
        date = day.find('h1').text  # 获取日期
        weather = day.find('p', class_='wea').text  # 获取天气描述
        temperature_high = day.find('span').text if day.find('span') else ''  # 最高温度
        temperature_low = day.find('i').text  # 最低温度
        temperature = f"{temperature_high}/{temperature_low}"  # 拼接温度信息
        weather_data.append((date, weather, temperature))

    return weather_data

# 保存数据到数据库
def save_to_database(city, weather_data, conn):
    c = conn.cursor()
    for date, weather, temperature in weather_data:
        # 插入每行数据
        c.execute("INSERT INTO weather_forecast (city, date, weather, temperature) VALUES (?, ?, ?, ?)",
                  (city, date, weather, temperature))
    conn.commit()

# 显示表格形式的数据
def display_table(conn):
    c = conn.cursor()
    c.execute("SELECT * FROM weather_forecast")
    rows = c.fetchall()

    print(f"{'序号':<5} {'地区':<10} {'日期':<15} {'天气信息':<20} {'温度':<15}")
    for row in rows:
        print(f"{row[0]:<5} {row[1]:<10} {row[2]:<15} {row[3]:<20} {row[4]:<15}")

# 主函数
def main():
    # 给定的城市集 (使用中国气象网的城市代码)
    cities = {
        '北京': '101010100',
        '上海': '101020100',
        '广州': '101280101',
        '深圳': '101280601',
        '杭州': '101210101',
        '成都': '101270101',
        '武汉': '101200101',
        '南京': '101190101',
        '重庆': '101040100',
        '天津': '101030100',
        '西安': '101110101',
        '沈阳': '101070101',
        '长沙': '101250101',
        '郑州': '101180101',
        '青岛': '101120201',
    }

    # 创建数据库连接
    conn = create_database()

    # 爬取并保存每个城市的天气数据
    for city, city_code in cities.items():
        weather_data = get_weather_data(city_code)
        save_to_database(city, weather_data, conn)

    # 显示表格数据
    display_table(conn)

    conn.close()

if __name__ == '__main__':
    main()

输出结果

Gitee 文件夹链接

https://gitee.com/wang-hengjie-100/crawl_project/blob/master/2.1.py

心得体会

通过该题目,我复习了数据库的相关操作,在完成的过程中,我对数据库的使用更加熟练了,同时也复习了如何编写类和使用类,最主要的是能够规范地编写爬虫程序爬取想要的数据并存储,受益良多。


作业②

题目描述

  1. 使用 requestsBeautifulSoup 库方法定向爬取股票相关信息,并存储在数据库中。

代码:

import requests
import sqlite3
import json


# 创建数据库并创建表
def create_database():
    conn = sqlite3.connect('eastmoney_stock.db')
    c = conn.cursor()
    # 创建表格存储股票信息
    c.execute('''
        CREATE TABLE IF NOT EXISTS stock_info (
            id INTEGER PRIMARY KEY AUTOINCREMENT,
            stock_code TEXT,
            stock_name TEXT,
            latest_price REAL,
            change_percent REAL,
            change_amount REAL,
            volume TEXT,
            turnover TEXT,
            amplitude REAL,
            high REAL,
            low REAL,
            open_price REAL,
            yesterday_close REAL
        )
    ''')
    conn.commit()
    return conn


# 获取股票数据
def get_stock_data():
    url = 'https://push2.eastmoney.com/api/qt/clist/get?cb=jQuery112409840494931556277_1633338445629&pn=1&pz=10&po=1&np=1&fltt=2&invt=2&fid=f3&fs=b:MK0021&fields=f12,f14,f2,f3,f4,f5,f6,f7,f8,f9,f10,f11,f18,f15,f16,f17,f23'
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/129.0.0.0 Safari/537.36 Edg/129.0.0.0'
    }
    response = requests.get(url, headers=headers)

    # 去除不必要的字符,提取有效的JSON部分
    response_text = response.text.split('(', 1)[1].rsplit(')', 1)[0]

    stock_data = json.loads(response_text)['data']['diff']  # 解析JSON并提取有用的字段
    return stock_data


# 保存数据到数据库
def save_to_database(stock_data, conn):
    c = conn.cursor()
    for stock in stock_data:
        stock_code = stock['f12']  # 股票代码
        stock_name = stock['f14']  # 股票名称
        latest_price = stock['f2']  # 最新报价
        change_percent = stock['f3']  # 涨跌幅
        change_amount = stock['f4']  # 涨跌额
        volume = stock['f5']  # 成交量
        turnover = stock['f6']  # 成交额
        amplitude = stock['f7']  # 振幅
        high = stock['f15']  # 最高价
        low = stock['f16']  # 最低价
        open_price = stock['f17']  # 今开
        yesterday_close = stock['f18']  # 昨收

        # 插入每行数据
        c.execute('''
            INSERT INTO stock_info 
            (stock_code, stock_name, latest_price, change_percent, change_amount, volume, turnover, amplitude, high, low, open_price, yesterday_close)
            VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?)
        ''', (
        stock_code, stock_name, latest_price, change_percent, change_amount, volume, turnover, amplitude, high, low,
        open_price, yesterday_close))

    conn.commit()


# 显示表格形式的数据
def display_table(conn):
    c = conn.cursor()
    c.execute("SELECT * FROM stock_info")
    rows = c.fetchall()

    # 打印表头
    print(
        f"{'序号':<5} {'股票代码':<10} {'股票名称':<10} {'最新报价':<10} {'涨跌幅':<10} {'涨跌额':<10} {'成交量':<10} {'成交额':<15} {'振幅':<10} {'最高':<10} {'最低':<10} {'今开':<10} {'昨收':<10}")

    # 打印每行数据
    for row in rows:
        # 尝试将字段转换为浮点数,如果失败则使用0.0
        latest_price = float(row[3]) if row[3] not in ('-', None) else 0.0
        change_percent = float(row[4]) if row[4] not in ('-', None) else 0.0
        change_amount = float(row[5]) if row[5] not in ('-', None) else 0.0
        amplitude = float(row[8]) if row[8] not in ('-', None) else 0.0
        high = float(row[9]) if row[9] not in ('-', None) else 0.0
        low = float(row[10]) if row[10] not in ('-', None) else 0.0
        open_price = float(row[11]) if row[11] not in ('-', None) else 0.0
        yesterday_close = float(row[12]) if row[12] not in ('-', None) else 0.0

        print(f"{row[0]:<5} {row[1]:<10} {row[2]:<10} "
              f"{latest_price:<10.2f} {change_percent:<10.2f} {change_amount:<10.2f} "
              f"{row[6]:<10} {row[7]:<15} {amplitude:<10.2f} {high:<10.2f} "
              f"{low:<10.2f} {open_price:<10.2f} {yesterday_close:<10.2f}")


# 主函数
def main():
    # 创建数据库连接
    conn = create_database()

    # 获取股票数据
    stock_data = get_stock_data()

    # 保存数据到数据库
    save_to_database(stock_data, conn)

    # 显示表格数据
    display_table(conn)

    conn.close()


if __name__ == '__main__':
    main()

输出结果

Gitee 文件夹链接

https://gitee.com/wang-hengjie-100/crawl_project/blob/master/2.2.py

心得体会

通过老师提供的股票爬取教程,我学到了如何从网页中抓包获取所需信息字段,在完成作业的过程中,我慢慢地能够精准地从网页中提取数据,同时对数据量较大的网站能够较为准确快速地获取所需数据。


作业③

题目描述

  1. 爬取中国大学 2021 主榜(链接)所有院校信息,并存储在数据库中。同时将浏览器 F12 调试分析的过程录制为 GIF 并添加至博客。

代码:

import requests
import sqlite3
from bs4 import BeautifulSoup


# 创建数据库并创建表
def create_database():
    conn = sqlite3.connect('university_ranking_2021.db')
    c = conn.cursor()
    # 创建表格存储学校排名信息
    c.execute('''
        CREATE TABLE IF NOT EXISTS university_ranking (
            id INTEGER PRIMARY KEY AUTOINCREMENT,
            rank INTEGER,
            university_name TEXT,
            province TEXT,
            university_type TEXT,
            total_score REAL
        )
    ''')
    conn.commit()
    return conn


# 获取网页内容
def get_html(url):
    try:
        response = requests.get(url, timeout=30)
        response.raise_for_status()
        response.encoding = 'utf-8'
        return response.text
    except requests.RequestException as e:
        print(f"请求错误: {e}")
        return None


# 解析网页并提取大学排名信息
def parse_ranking_table(html):
    soup = BeautifulSoup(html, 'html.parser')
    ranking_table = soup.find('table', class_='rk-table')

    if not ranking_table:
        print("未找到排名表格")
        return []

    rows = ranking_table.find_all('tr')[1:]  # 跳过表头
    university_data = []

    # 打印表头
    print(f"{'排名':<5} {'学校':<20} {'省市':<10} {'类型':<10} {'总分':<10}")

    for row in rows:
        columns = row.find_all('td')
        if len(columns) >= 5:
            rank = int(columns[0].get_text(strip=True))
            university_name = columns[1].get_text(strip=True)
            province = columns[2].get_text(strip=True)
            university_type = columns[3].get_text(strip=True)
            total_score = float(columns[4].get_text(strip=True))

            # 将每个学校信息存入列表
            university_data.append((rank, university_name, province, university_type, total_score))

            # 在控制台打印每所大学的信息
            print(f"{rank:<5} {university_name:<20} {province:<10} {university_type:<10} {total_score:<10.1f}")

    return university_data


# 保存数据到数据库
def save_to_database(university_data, conn):
    c = conn.cursor()
    for university in university_data:
        c.execute('''
            INSERT INTO university_ranking 
            (rank, university_name, province, university_type, total_score)
            VALUES (?, ?, ?, ?, ?)
        ''', university)
    conn.commit()


# 主函数
def main():
    url = 'https://www.shanghairanking.cn/rankings/bcur/2021'
    html_content = get_html(url)

    if html_content:
        university_data = parse_ranking_table(html_content)

        if university_data:
            conn = create_database()
            save_to_database(university_data, conn)
            conn.close()
            print("数据成功保存到数据库")


if __name__ == '__main__':
    main()

输出结果

Gitee 文件夹链接

https://gitee.com/wang-hengjie-100/crawl_project/blob/master/2.3.py

心得体会

该任务完成过了,同样地,通过该题目我复习了数据库的相关操作,我将之前的代码进行了修改,添加了存储到数据库的部分,使数据能够很好地保存到本地。


 posted on 2024-10-27 18:01  whj112  阅读(7)  评论(0编辑  收藏  举报