乐趣区

关于python3.x:python分析全国各城市景点并可视化显示

jiezi

此次爬取波及到的库：

request+json– 网页数据爬取
openpyxl– 保留数据至 Excel
pandas– 表格数据处理
pyechars– 数据可视化

一、剖析网页

关上去哪儿旅行网页：https://piao.qunar.com/

二、爬取每个行政区数据取出 url 和 headers 须要用到

def get_city_scenic(city, page):
    ua = UserAgent(verify_ssl=False)
    # headers = {'User-Agent': ua.random}
    headers = {'user-agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/96.0.4664.45 Safari/537.36'}
    # url = f'https://piao.qunar.com/ticket/list.json?keyword={city}&region=&from=mpl_search_suggest&sort=pp&page={page}'
    url = f'https://piao.qunar.com/ticket/list.json?keyword={city}&region=&from=mpl_search_suggest&page={page}'
    result = requests.get(url, headers=headers, timeout=10)
    result.raise_for_status()
    return  get_scenic_info(city, result.text)

三、爬取每一页数据

def get_scenic_info(city, response):
    response_info = json.loads(response)
    sight_list = response_info['data']['sightList']
    one_city_scenic = []
    for sight in sight_list:
        scenic = []
        name = sight['sightName'] # 景点名称
        star = sight.get('star', None) # 星级
        score = sight.get('score', 0) # 评分
        price = sight.get('qunarPrice', 0) # 价格
        sale = sight.get('saleCount', 0) # 销量
        districts = sight.get('districts', None) # 省，市，区
        point = sight.get('point', None) # 坐标
        intro = sight.get('intro', None) # 简介
        free = sight.get('free', True) # 是否收费
        address = sight.get('address', None) # 具体地址
        scenic.append(city)
        scenic.append(name)
        scenic.append(star)
        scenic.append(score)
        scenic.append(price)
        scenic.append(sale)
        scenic.append(districts)
        scenic.append(point)
        scenic.append(intro)
        scenic.append(free)
        scenic.append(address)
        one_city_scenic.append(scenic)
    return one_city_scenic

四、循环爬取每个行政区每页数据

def get_city_info(city, pages):
    # for city in cities:
        one_city_info = []
        for page in range(1, pages+1):
            try:
                print(f'正在爬取 -{city}(省 / 市), 第 {page} 页景点数据...')
                time.sleep(random.uniform(0.8,1.5))
                one_page_info = get_city_scenic(city, page)
            except:
                continue
            if one_page_info:
                one_city_info += one_page_info
        # print(one_city_info)
        return one_city_info

五、输入到 excel 表中保留

def insert2excel(filepath,allinfo):
    try:
        if not os.path.exists(filepath):
            tableTitle = ['城市','名称','星级','评分','价格','销量','省 / 市 / 区','坐标','简介','是否收费','具体地址']
            wb = Workbook()
            ws = wb.active
            ws.title = 'sheet1'
            ws.append(tableTitle)
            wb.save(filepath)
            time.sleep(3)
        wb = load_workbook(filepath)
        ws = wb.active
        ws.title = 'sheet1'
        for info in allinfo:
            ws.append(info)
        wb.save(filepath)
        return True
    except:
        return False

爬取的过程展现：


六、数据可视化展现

通过剖析上次 python 爬获得到的表格数据，再用 pandas 模块遍历文件夹读取数据

def get_datas():
    """
    遍历 task 文件夹里的文件
    :return:
    """
    df_allinfo = pd.DataFrame()
    for root, dirs, files in os.walk('D:/work/loginn/task'):
        print(files)
        for filename in files:
            try:
                df = pd.read_excel(f'D:/work/loginn/task/{filename}')
                df_allinfo = df_allinfo.append(df, ignore_index=True)
            except:
                continue
    # 去重
    df_allinfo.drop_duplicates(subset=['名称'], keep='first', inplace=True)
    return df_allinfo
    # print(df_allinfo)

6.1 热门景点数据图

以门票销量前 20 为例：

def get_sales_bar(data):
    sort_info = data.sort_values(by='销量', ascending=True)
    c = (Bar()
        .add_xaxis(list(sort_info['名称'])[-20:])
        .add_yaxis('热门景点销量', sort_info['销量'].values.tolist()[-20:])
        .reversal_axis()
        .set_global_opts(title_opts=opts.TitleOpts(title='热门景点销量数据'),
            yaxis_opts=opts.AxisOpts(name='景点名称'),
            xaxis_opts=opts.AxisOpts(name='销量'),
            )
        .set_series_opts(label_opts=opts.LabelOpts(position="right"))
        .render('1- 热门景点数据.html')
        )

成果：

6.2 假期出行数据地图分布图

def get_sales_geo(data):
    df = data[['城市','销量']]
    # print(df)
    df_counts = df.groupby('城市').sum()
    df_counts = df.groupby('城市').count()['销量']

    print(df_counts)
    c = (Map()
        .add('假期出行分布', [list(z) for z in zip(df_counts.index.values.tolist(), df_counts.values.tolist())], 'china')
        .set_global_opts(title_opts=opts.TitleOpts(title='假期出行数据地图散布'),
        visualmap_opts=opts.VisualMapOpts(max_=100, is_piecewise=True),
        )
        .render('2- 假期出行数据地图散布.html')
    )

成果：

6.3 各省市 4A-5A 景区数量图

def get_level_counts(data):
    df = data[data['星级'].isin(['4A', '5A'])]
    df_counts = df.groupby('城市').count()['星级']
    c = (Bar()
            .add_xaxis(df_counts.index.values.tolist())
            .add_yaxis('4A-5A 景区数量', df_counts.values.tolist())
            .set_global_opts(title_opts=opts.TitleOpts(title='各省市 4A-5A 景区数量'),
            datazoom_opts=[opts.DataZoomOpts(), opts.DataZoomOpts(type_='inside')],
        )
        .render('3- 各省市 4A-5A 景区数量.html')
    )

成果：

6.4 4-4A-5A 景区数据地图散布

def get_level_geo(data):
    df = data[data['星级'].isin(['4A', '5A'])]
    df_counts = df.groupby('城市').count()['星级']
 c = (Map()
        .add('4A-5A 景区散布', [list(z) for z in zip(df_counts.index.values.tolist(), df_counts.values.tolist())], 'china')
        .set_global_opts(title_opts=opts.TitleOpts(title='地图数据分布'),
        visualmap_opts=opts.VisualMapOpts(max_=50, is_piecewise=True),
        )
        .render('4-4A-5A 景区数据地图散布.html')
    )

成果：

退出移动版