利用pyecharts看微博粉丝地区分布

# 粉丝用户ID爬取## 导入相关库import reimport time import randomimport requestsfrom tqdm import tqdm_notebook  ### 该库用于进度条的配置
def get_userid(url):    header_list = [        "Opera/12.0(Windows NT 5.2;U;en)Presto/22.9.168 Version/12.00",        "Opera/12.0(Windows NT 5.1;U;en)Presto/22.9.168 Version/12.00",        "Mozilla/5.0 (Windows NT 5.1) Gecko/20100101 Firefox/14.0 Opera/12.0",        "Opera/9.80 (Windows NT 6.1; WOW64; U; pt) Presto/2.10.229 Version/11.62",        "Opera/9.80 (Windows NT 6.0; U; pl) Presto/2.10.229 Version/11.62",    ]    header = {        'user-agent': random.choice(header_list)    }        pat = 'since_id=(.*)'    with open('D:/python爬虫/李子柒微博粉丝地区分布/user_id.txt', 'w') as f:        for page in tqdm_notebook(range(1, 251), desc='进度条:'):            try:                print(url)                r = requests.get(url, headers=header)                all_user = r.json()['data']['cards'][0]['card_group']                since_id = r.json()['data']['cardlistInfo']['since_id']                for user in all_user:                    f.write(str(user.get('user')['id'])+'\n')                url = re.sub(pat, 'since_id='+str(since_id), url)                time.sleep(random.randint(1, 2))            except Exception as e:                print(e)
if __name__ == '__main__':    start_url = "https://m.weibo.cn/api/container/getIndex?containerid=231051_-_fans_-_2970452952&since_id=21"    get_userid(start_url)

# 根据爬取的粉丝用户ID获取粉丝的基本公开信息import requestsfrom lxml import etreeimport pandas as pdimport numpy as npimport reimport timeimport randomimport osos.chdir("D:\python爬虫\李子柒微博粉丝地区分布")

headers = {    "accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.9",    "cookie": "输入自己的cookie",    "user-agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/89.0.4389.72 Safari/537.36"}

new_url = "https://weibo.cn/u/"data = []count = 0def get_id(ID):    with open(ID, 'r') as f:        user_list = f.readlines()        user_id = np.char.rstrip(user_list, '\n')        return user_iddef gethtml(url, header):    r = requests.get(url, headers = headers)    if r.status_code == 200:        return r.text    else:        print("网络连接异常")for user_id in get_id('user_id.txt'):    try:        url = new_url + user_id        r_text = gethtml(url, headers)        tree = etree.HTML(r_text.encode('utf-8'))        user_name_xpath = "//tr/td[2]/div/span[1]/text()[1]"        user_name = tree.xpath(user_name_xpath)        Inf_xpath = "//tr/td[2]/div/span[1]/text()[2]"        Inf = tree.xpath(Inf_xpath)        focusnumber_xpath = "//div[4]/div/a[1]/text()"        focusnumber = tree.xpath(focusnumber_xpath)        fansnumber_xpath = "//div[4]/div/a[2]/text()"        fansnumber = tree.xpath(fansnumber_xpath)        data.append([user_name, Inf, focusnumber, fansnumber])        count += 1        print("第{}个用户信息录入完毕".format(count))        time.sleep(random.randint(1,2))    except:        print("用户信息录入失败")

file = r"D:\python爬虫\李子柒微博粉丝地区分布\粉丝公开信息.xlsx"df = pd.DataFrame(data, columns = ['user_name', 'Inf', 'focusnumber', 'fansnumber'])df.to_excel(file, index = None)print("程序执行完毕")

## 导入相关库并读入数据import pandas as pdimport numpy as npfrom pyecharts.charts import Mapfrom pyecharts import options as opts
df = pd.read_excel("粉丝信息.xlsx")df

## 绘制粉丝地区分布图address=pd.DataFrame(df['Inf'].value_counts())  ### 汇总每个地区的粉丝数量city=np.char.rstrip(list(address.index))  ### 城市名称Map1 = (    Map(init_opts=opts.InitOpts(width="1200px",height="800px"))    .add("",         [list(z) for z in zip(city,address['Inf'])],         "china",        is_roam = False,        is_map_symbol_show = False    )    .set_global_opts(        title_opts = opts.TitleOpts(title = "李子柒微博粉丝地区分布"),        visualmap_opts = opts.VisualMapOpts(max_ = 1500, is_piecewise = True,            pieces=[        {"max": 1500, "min": 1000, "label": ">1000", "color": "#2F7F50"},        {"max": 999, "min": 600, "label": "600-999", "color": "#FFFFE0"},        {"max": 599, "min": 200, "label": "200-599", "color": "#7FFFD4"},        {"max": 199, "min": 1, "label": "1-199", "color": "#00FFFF"},        {"max": 0, "min": 0, "label": "0", "color": "#EE82EE"},])    ))Map1.render("粉丝分布图.html")

from pyecharts import options as optsfrom pyecharts.charts import Geofrom pyecharts.globals import ChartType
g = (    Geo(init_opts=opts.InitOpts(width="1200px",height="800px"))    .add_schema(        maptype = "china",        itemstyle_opts = opts.ItemStyleOpts(color = "#5F9EA0", border_color = "#2F4F4F"),    )    .add("",        [list(z) for z in zip(city,address['Inf'])],        label_opts = opts.LabelOpts(is_show = False),        type_ = ChartType.EFFECT_SCATTER    )    .set_global_opts(        title_opts = opts.TitleOpts(title = "李子柒微博粉丝地区分布"),        visualmap_opts = opts.VisualMapOpts(max_ = 1500, is_piecewise = True,            pieces=[        {"max": 1500, "min": 1000, "label": ">1000", "color": "#2F7F50"},        {"max": 999, "min": 600, "label": "600-999", "color": "#FFFFE0"},        {"max": 599, "min": 200, "label": "200-599", "color": "#FF4500"},        {"max": 199, "min": 1, "label": "1-199", "color": "#6A5ACD"},        {"max": 0, "min": 0, "label": "0", "color": "FF0000"},])    ))g.render("粉丝分布图3.html")