大数据毕业设计hadoop+spark+hive知识图谱新能源汽车数据分析可视化大屏 汽车推荐系统 新能源汽车推荐系统 汽车爬虫 汽车大数据 机器学习 大数据 计算机毕业设计 深度学习 人工智能

本科毕业论文（设计）开题报告

核心算法代码分享如下：

def init_data():
    print("==========开始采集车辆信息================")
 
    # 定义一个相对路径
    folder_path = 'photo'  # 注释8
    if os.path.exists(folder_path) == False:  # 注释9
        os.makedirs(folder_path)  # 注释10
 
    db = DBHelper()
    for pageNumber in range(1, 20):
        _jsonStr = __get_car_list_data(pageNumber, '北京')
        print(_jsonStr)
        _jsonObject = json.loads(_jsonStr)
        print(_jsonObject["data"]['series'])
        cars = _jsonObject["data"]['series'];
        for car in cars:
            print("id:" + str(car['id']))
            print("concern_id:" + str(car['concern_id']))
            print("outter_name:" + car['outter_name'])
            print("dealer_max_price:" + car['dealer_max_price'])
            print("dealer_min_price:" + car['dealer_min_price'])
            print("max_price:" + str(car['max_price']))
            print("min_price:" + str(car['min_price']))
            print("dealer_price:" + car['dealer_price'])
            print("cover_url:" + car['cover_url'])
 
            concern_id = car['concern_id']
            car_name = car['outter_name']
            dealer_max_price = car['dealer_max_price']
            dealer_min_price = car['dealer_min_price']
            max_price = car['max_price']
            min_price = car['min_price']
            dealer_price = car['dealer_price']
            cover_img = car['cover_url']
 
            # 遍历车辆详细信息
            print("==========获取车辆详细信息=============")
            _car_detail = __get_car_detail_data(car['concern_id'])
            # 转为json对象
            _json_car_detail = json.loads(_car_detail)
            print("评价人数:" + str(_json_car_detail["data"]['review_count_info']['total']))
            print("评价结果:" + _json_car_detail["data"]['review_count_info']['total_review'])
            score_infos = _json_car_detail["data"]['score_info']
            for score_info in score_infos:
                print(score_info['name'] + ":" + score_info['value'])
            print("rank_tips:" + _json_car_detail["data"]['series_info']['rank_tips'])
            print("score:" + _json_car_detail["data"]['series_info']['score'])
 
            comment_num = _json_car_detail["data"]['review_count_info']['total']
            comment_result = _json_car_detail["data"]['review_count_info']['total_review']
            # 综合得分
            score = _json_car_detail["data"]['series_info']['score']
            # 排名提醒
            rank_tips = _json_car_detail["data"]['series_info']['rank_tips']
            wg_score = score_infos[0]['value']
            ns_score = score_infos[1]['value']
            pz_score = score_infos[2]['value']
            kj_score = score_infos[3]['value']
            ck_score = score_infos[4]['value']
            dl_score = score_infos[5]['value']
 
            # 开始存储车辆信息
            car_list = []  # 空列表
            car_list.extend([concern_id, car_name.strip(), dealer_max_price,
                                dealer_min_price, max_price,
                                min_price, dealer_price.strip(), cover_img.strip(),comment_num,
                             comment_result.strip(),score,rank_tips.strip(),wg_score,ns_score,
                             pz_score,kj_score,ck_score,dl_score])
            db.add_car(car_list)
        else:
            print("没有循环数据!")
        print("==================第-%d-页采集完毕=====================" % pageNumber)
    print("==========数据全部采集完成完成================")
    db.close_db()
 
class DBHelper(object):
    # 数据库地址
    url = "localhost"
    # 数据库用户名
    username = "root"
    # 数据库密码
    password = "123456"
    # 数据库名称
    database = "car"
 
    connect = None
 
    def __init__(self):
        # 打开数据库连接
        if (self.connect == None):
            # self.connect = pymysql.connect(self.url, self.username, self.password, self.database)
            # host="localhost", user="root", password="xxx", database="xxxx"
            self.connect = pymysql.connect(host=self.url,port=3396, user=self.username,
                                           password=self.password, database=self.database)
 
    '''
    # 添加档案信息
    '''
 
    def add_car(self, data):
 
        # 使用 cursor() 方法创建一个游标对象 cursor
        cursor = self.connect.cursor()
 
        # SQL 语句
        _sql = """insert into t_car (concern_id,car_name,dealer_max_price,dealer_min_price,
                                        max_price,min_price,dealer_price,cover_img,comment_num,
                                        comment_result,score,rank_tips,wg_score,ns_score,pz_score,kj_score,
                                        ck_score,dl_score) 
                    values (%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s)"""
        try:
            # 执行SQL语句
            # print(match_sql)
            cursor.execute(_sql, data)
            # 提交事务
            self.connect.commit()
 
        except Exception as e:
            self.connect.rollback()  # 事务回滚
            print("Error: 添加信息失败", e)
 
    '''
    #关闭数据库
    '''
 
    def close_db(self):
        if (self.connect.close == False):
            self.connect.close()
            self.connect = None
 
'''
执行采集数据的方法，并存储到数据
'''
 
if __name__ == '__main__':
    init_data()