一、抓取数据
1、抓取数据的意义
对电商来说,抓取某些数据,再进行分析,可以有效地反映出数据在某个区间内变化情况。数据受某些因素而发生巨大的影响,也可以借助分析的数据来规划相关项目的后续发展。因此,如果能利用网页爬取数据技术获取数据并对各种数据进行统计分析,对后续淘宝的发展具有指导意义。
2、抓取的内容
包括:商品名称title、商品价格price、付款人数deal,店铺名称shop、店铺地址location、商品的详情页detail_url。
3、实现内容
1、开打淘宝网站,输入搜索内容“word”查找商品
2、再解决登录问题(登录时解决网站对selenium的判别,修改浏览器的内部属性,否则被识别出有selenium,需要进行滑动登陆验证。但是在运行时,你手动地去进行滑动登录也是会判别出存在selenium的,进而登陆不上去)
3、对查找商品在控制台上输出
4、具体实现代码
#include<iostream>
#include<string>
#include<curl/curl.h>
using namespace std;
static size_t Data(void *ptr, size_t size, size_t nmemb, string *stream)
{
std::size_t realSize = size *nmemb;
auto *realPtr = reinterpret_cast<char *>(ptr);
for (std::size_t i=0;i<realSize;++i) {
*(stream) += *(realPtr + i);
}
return realSize;
}
int main(){
CURL *curl;
CURLcode result;
string readBuffer;
curl = curl_easy_init();
if(curl) {
curl_easy_setopt(curl, CURLOPT_URL, "https://api-gw.Taobaoapi2014.cn/taobao/item_get/?key=<您自己的apiKey>&secret=<您自己的apiSecret>&num_iid=652874751412&is_promotion=1");
curl_easy_setopt(curl, CURLOPT_FOLLOWLOCATION, 1L);
curl_easy_setopt(curl, CURLOPT_WRITEFUNCTION, Data);
curl_easy_setopt(curl, CURLOPT_WRITEDATA, &readBuffer);
result = curl_easy_perform(curl);
if(result == CURLE_OK) {
cout<<readBuffer<<endl;
}else{
cerr<<"curl_easy error:"<<curl_easy_strerror(result)<<endl;
}
curl_easy_cleanup(curl);
}
return 0;
}
5.响应示例
{
"item": {
"num_iid": "520813250866",
"title": "三刃木折叠刀过安检创意迷你钥匙扣钥匙刀军刀随身多功能小刀包邮",
"desc_short": "",
"price": 25.8,
"total_price": 0,
"suggestive_price": 0,
"orginal_price": "25.80",
"nick": "欢乐购客栈",
"num": "832",
"min_num": 0,
"detail_url": "http://item.taobao.com/item.htm?id=520813250866",
"pic_url": "//img.alicdn.com/imgextra/i4/2596264565/TB2p30elFXXXXXQXpXXXXXXXXXX_!!2596264565.jpg",
"brand": "三刃木",
"brandId": "4036703",
"rootCatId": "50013886",
"cid": "50014822",
"favcount": "4824",
"fanscount": "1469",
"crumbs": [],
"created_time": "",
"modified_time": "",
"delist_time": "",
"desc": "<p style=\"text-align:center;\"><span style=\"color:#ff0000;\"><span style=\"font-size:24.0px;\"><strong>小店所有产品都支持刻字,如需刻字,拍之前联系客服即可。</strong></span></span></p> <p style=\"text-align:center;\"><span style=\"font-size:18.0px;\"><strong>炎炎夏日来临,一把随身携带便携式的折叠小刀,<span style=\"color:#ff0000;\">带开瓶器功能</span>,喝酒不用愁。(钥匙刀不带开瓶器功能)</strong></span></p> <p style=\"text-align:center;\"><strong style=\"color:#000000;line-height:1.5;\"><span style=\"font-size:18.0px;\"><span style=\"line-height:18.0px;\">可以当吊牌项链装饰,也可当钥匙扣挂饰, 水果刀 开瓶器 户外防身.</span></span></strong></p> <p style=\"text-align:center;\"><strong style=\"line-height:1.5;\"><span style=\"font-size:24.0px;\">部分客户跟我们反映链子质量还不够好,因此小店已重新订购一批质量更好的链子赠送,<span style=\"color:#ff0000;\">加量不加价</span>,只为让你买的更舒心,戴的更放心。</span></strong></p> <p style=\"text-align:center;\"><span style=\"font-size:36.0px;\"><strong>购买就送<span style=\"color:#ff0000;\">工具刀卡和链子</span>一条</strong></span></p> <p style=\"text-align:center;\"><span style=\"font-size:36.0px;\"><strong><img align=\"absmiddle\" src=\"//img.alicdn.com/imgextra/i3/2596264565/TB2Sci2jXXXXXXFXpXXXXXXXXXX_!!2596264565.png\" size=\"611x442\"> </strong></span></p> <p style=\"text-align:center;\"><span style=\"font-size:18.0px;\"><strong>璀璨钻石套餐包含【SK016D钥匙扣+GJ019C折叠刀+GJ017D工具卡】</strong></span><img align=\"absmiddle\" src=\"//img.alicdn.com/imgextra/i3/2596264565/TB2wWohmXXXXXX8XXXXXXXXXXXX_!!2596264565.jpg\" size=\"750x600\" /></p> <p style=\"text-align:center;\"><span style=\"font-size:18.0px;\"><strong>超凡大师套餐包括【304不锈钢钥匙扣+GJ019C折叠刀+GJ017D工具卡】</strong></span><a href=\"//item.taobao.com/item.htm?id=520798805877\" target=\"_blank\"><img align=\"absmiddle\" src=\"//img.alicdn.com/imgextra/i4/2596264565/TB2_uiXnFXXXXXBXXXXXXXXXXXX_!!2596264565.jpg_q90.jpg\" style=\"float:none;margin:0.0px;\" /></a></p> <p style=\"text-align:center;\"> </p> <p style=\"text-align:center;\"><span style=\"font-size:18.0px;\"><strong>最强王者套餐包括【钛钢钥匙扣+GJ019C折叠刀+GJ017D工具卡】<a href=\"//item.taobao.com/item.htm?id=520801586805\" target=\"_blank\"><img align=\"absmiddle\" src=\"//img.alicdn.com/imgextra/i4/2596264565/TB2Gm9xnFXXXXbmXXXXXXXXXXXX_!!2596264565.jpg_q90.jpg\" style=\"float:none;margin:0.0px;\" /></a> </strong></span></p> <p style=\"text-align:center;\"><img align=\"absmiddle\" src=\"//img.alicdn.com/imgextra/i3/2596264565/TB28Ox4b77OyuJjSsplXXXqdpXa_!!2596264565.jpg\" size=\"749x553\"> <img align=\"absmiddle\" src=\"//img.alicdn.com/imgextra/i1/2596264565/TB2.mTddVXXXXbeXpXXXXXXXXXX_!!2596264565.jpg\" style=\"line-height:1.5;\" size=\"750x653\"><img align=\"absmiddle\" src=\"//img.alicdn.com/imgextra/i3/2596264565/TB21Ro.jl0lpuFjSszdXXcdxFXa_!!2596264565.jpg\" size=\"750x653\"> <img align=\"absmiddle\" src=\"//img.alicdn.com/imgextra/i4/2596264565/TB2q9CelVXXXXcUXXXXXXXXXXXX_!!2596264565.jpg\" size=\"750x340\"><img align=\"absmiddle\" src=\"//img.alicdn.com/imgextra/i3/2596264565/TB21EX9lVXXXXaXXpXXXXXXXXXX_!!2596264565.jpg\" size=\"750x416\"><img align=\"absmiddle\" src=\"//img.alicdn.com/imgextra/i3/2596264565/TB2udCylVXXXXXgXXXXXXXXXXXX_!!2596264565.jpg_q90.jpg\"><img align=\"absmiddle\" src=\"//img.alicdn.com/imgextra/i1/2596264565/TB2EARxjB8lpuFjSspaXXXJKpXa_!!2596264565.jpg\" size=\"750x515\"> <img align=\"absmiddle\" src=\"//img.alicdn.com/imgextra/i3/2596264565/TB2ssuwlVXXXXafXXXXXXXXXXXX_!!2596264565.jpg_q90.jpg\"><img align=\"absmiddle\" src=\"//img.alicdn.com/imgextra/i2/2596264565/TB2nAHqgyC9MuFjSZFoXXbUzFXa_!!2596264565.jpg\" size=\"750x606\"> <img align=\"absmiddle\" src=\"//img.alicdn.com/imgextra/i3/2596264565/TB2ahCelVXXXXc_XXXXXXXXXXXX_!!2596264565.jpg_q90.jpg\"><img align=\"absmiddle\" src=\"//img.alicdn.com/imgextra/i3/2596264565/TB2w1JnjwRkpuFjy1zeXXc.6FXa_!!2596264565.jpg\" size=\"750x469\"> <img align=\"absmiddle\" src=\"//img.alicdn.com/imgextra/i3/2596264565/TB2C902lVXXXXbnXpXXXXXXXXXX_!!2596264565.jpg_q90.jpg\"><img align=\"absmiddle\" src=\"//img.alicdn.com/imgextra/i1/2596264565/TB2sGR3lVXXXXblXpXXXXXXXXXX_!!2596264565.jpg_q90.jpg\"><img align=\"absmiddle\" src=\"//img.alicdn.com/imgextra/i1/2596264565/TB2ZBGxlVXXXXXMXXXXXXXXXXXX_!!2596264565.jpg_q90.jpg\"><img align=\"absmiddle\" src=\"//img.alicdn.com/imgextra/i1/2596264565/TB2MjWklVXXXXcaXXXXXXXXXXXX_!!2596264565.jpg_q90.jpg\"><img align=\"absmiddle\" src=\"//img.alicdn.com/imgextra/i2/2596264565/TB2UgV3lVXXXXbdXpXXXXXXXXXX_!!2596264565.jpg_q90.jpg\"><img align=\"absmiddle\" src=\"//img.alicdn.com/imgextra/i2/2596264565/TB2ip5XlVXXXXX2XpXXXXXXXXXX_!!2596264565.jpg_q90.jpg\"> <img align=\"absmiddle\" src=\"//img.alicdn.com/imgextra/i2/2596264565/TB2sMTBdVXXXXXlXXXXXXXXXXXX_!!2596264565.jpg_q90.jpg\" style=\"line-height:1.5;\"><img align=\"absmiddle\" src=\"//img.alicdn.com/imgextra/i3/2596264565/TB2d3HfdVXXXXahXpXXXXXXXXXX_!!2596264565.jpg_q90.jpg\" style=\"line-height:1.5;\"><img align=\"absmiddle\" src=\"//img.alicdn.com/imgextra/i4/2596264565/TB2AVbBdVXXXXXkXXXXXXXXXXXX_!!2596264565.jpg_q90.jpg\" style=\"line-height:1.5;\"><img align=\"absmiddle\" src=\"//img.alicdn.com/imgextra/i2/2596264565/TB2nf_wdVXXXXaMXXXXXXXXXXXX_!!2596264565.jpg_q90.jpg\" style=\"line-height:1.5;\"><img align=\"absmiddle\" src=\"//img.alicdn.com/imgextra/i4/2596264565/TB2dLYddVXXXXbtXpXXXXXXXXXX_!!2596264565.jpg_q90.jpg\" style=\"line-height:1.5;\"><img align=\"absmiddle\" src=\"//img.alicdn.com/imgextra/i2/2596264565/TB2H1_adVXXXXbWXpXXXXXXXXXX_!!2596264565.jpg_q90.jpg\" style=\"line-height:1.5;\"><img align=\"absmiddle\" src=\"//img.alicdn.com/imgextra/i2/2596264565/TB2eBzsdVXXXXbuXXXXXXXXXXXX_!!2596264565.jpg_q90.jpg\" style=\"line-height:1.5;\"><img align=\"absmiddle\" src=\"//img.alicdn.com/imgextra/i4/2596264565/TB2dOTndVXXXXcCXXXXXXXXXXXX_!!2596264565.jpg_q90.jpg\" style=\"line-height:1.5;\"><img align=\"absmiddle\" src=\"//img.alicdn.com/imgextra/i2/2596264565/TB2fK2tdVXXXXbkXXXXXXXXXXXX_!!2596264565.jpg_q90.jpg\" style=\"line-height:1.5;\"><img align=\"absmiddle\" src=\"//img.alicdn.com/imgextra/i2/2596264565/TB29zjedVXXXXaFXpXXXXXXXXXX_!!2596264565.jpg_q90.jpg\" style=\"line-height:1.5;\"><img align=\"absmiddle\" src=\"//img.alicdn.com/imgextra/i3/2596264565/TB2i7rmdVXXXXcTXXXXXXXXXXXX_!!2596264565.jpg_q90.jpg\" style=\"line-height:1.5;\" /></p>",
"item_imgs": [
{
"url": "//img.alicdn.com/imgextra/i4/2596264565/TB2p30elFXXXXXQXpXXXXXXXXXX_!!2596264565.jpg"
},
{
"url": "//img.alicdn.com/imgextra/i2/2596264565/TB2onxRlVXXXXcDXpXXXXXXXXXX_!!2596264565.jpg"
},
{
"url": "//img.alicdn.com/imgextra/i1/2596264565/TB2a.x.lVXXXXXPXpXXXXXXXXXX_!!2596264565.jpg"
},
{
"url": "//img.alicdn.com/imgextra/i2/2596264565/TB2iWE6bKZkyKJjSszbXXblwFXa_!!2596264565.jpg"
},
{
"url": "//img.alicdn.com/imgextra/i4/2596264565/TB2j2cTXib_F1JjSZFzXXc6KXXa_!!2596264565.jpg"
}
],
"item_weight": "0",
"item_size": "",
"location": "广东深圳",
"post_fee": "",
"express_fee": "0.00",
"ems_fee": "",
"shipping_to": "广东广州白云区",
"has_discount": "false",
"video": [],
"is_virtual": "",
"sample_id": "",
"is_promotion": "false",
"props_name": "1627207:1347647754:颜色分类:长方形带开瓶器+送工具刀卡+链子;1627207:1347647753:颜色分类:椭圆形带开瓶器+送工具刀卡+链子;1627207:1195392087:颜色分类:GJ018X钥匙刀+送工具刀卡+链子;1627207:1331112595:颜色分类:超凡大师套餐【送工具卡+链子】;1627207:1331112594:颜色分类:最强王者套餐【送工具卡+链子】;1627207:1331264247:颜色分类:璀璨钻石套餐【送工具卡+链子】",
"prop_imgs": {
"prop_img": [
{
"properties": "1627207:1347647754",
"url": "//img.alicdn.com/imgextra/i3/2596264565/TB2.XeblVXXXXXkXpXXXXXXXXXX_!!2596264565.jpg"
},
{
"properties": "1627207:1347647753",
"url": "//img.alicdn.com/imgextra/i4/2596264565/TB2dTrjdVXXXXXBXpXXXXXXXXXX_!!2596264565.jpg"
},
{
"properties": "1627207:1195392087",
"url": "//img.alicdn.com/imgextra/i2/2596264565/TB2j22kdVXXXXXdXpXXXXXXXXXX_!!2596264565.jpg"
},
{
"properties": "1627207:1331112595",
"url": "//img.alicdn.com/imgextra/i4/2596264565/TB2_uiXnFXXXXXBXXXXXXXXXXXX_!!2596264565.jpg"
},
{
"properties": "1627207:1331112594",
"url": "//img.alicdn.com/imgextra/i4/2596264565/TB2Gm9xnFXXXXbmXXXXXXXXXXXX_!!2596264565.jpg"
},
{
"properties": "1627207:1331264247",
"url": "//img.alicdn.com/imgextra/i3/2596264565/TB2wWohmXXXXXX8XXXXXXXXXXXX_!!2596264565.jpg"
}
]
},
"property_alias": "1627207:1347647754:长方形带开瓶器+送工具刀卡+链子;1627207:1347647753:椭圆形带开瓶器+送工具刀卡+链子;1627207:1195392087:GJ018X钥匙刀+送工具刀卡+链子;1627207:1331112595:超凡大师套餐【送工具卡+链子】;1627207:1331112594:最强王者套餐【送工具卡+链子】;1627207:1331264247:璀璨钻石套餐【送工具卡+链子】",
"props": [
{
"name": "品牌",
"value": "三刃木"
},
{
"name": "产地",
"value": "中国"
},
{
"name": "颜色分类",
"value": "长方形带开瓶器+送工具刀卡+链子,椭圆形带开瓶器+送工具刀卡+链子,GJ018X钥匙刀+送工具刀卡+链子,超凡大师套餐【送工具卡+链子】,最强王者套餐【送工具卡+链子】,璀璨钻石套餐【送工具卡+链子】"
},
{
"name": "吊牌价",
"value": "46"
},
{
"name": "功能数量",
"value": "5个及以下"
},
{
"name": "货号",
"value": "GJ019C"
},
{
"name": "附加功能",
"value": "开瓶器,刀,螺丝刀,钥匙圈,其他"
}
],
"total_sold": "1",
"skus": {
"sku": [
{
"price": "39",
"orginal_price": "39.00",
"properties": "1627207:1347647754",
"properties_name": "1627207:1347647754:颜色分类:长方形带开瓶器+送工具刀卡+链子",
"quantity": "104",
"sku_id": "3166598625985"
},
{
"price": "39",
"orginal_price": "39.00",
"properties": "1627207:1347647753",
"properties_name": "1627207:1347647753:颜色分类:椭圆形带开瓶器+送工具刀卡+链子",
"quantity": "370",
"sku_id": "3166598625984"
},
{
"price": "25.8",
"orginal_price": "25.80",
"properties": "1627207:1195392087",
"properties_name": "1627207:1195392087:颜色分类:GJ018X钥匙刀+送工具刀卡+链子",
"quantity": "34",
"sku_id": "3144644292458"
},
{
"price": "73.8",
"orginal_price": "73.80",
"properties": "1627207:1331112595",
"properties_name": "1627207:1331112595:颜色分类:超凡大师套餐【送工具卡+链子】",
"quantity": "157",
"sku_id": "3161300228970"
},
{
"price": "91.8",
"orginal_price": "91.80",
"properties": "1627207:1331112594",
"properties_name": "1627207:1331112594:颜色分类:最强王者套餐【送工具卡+链子】",
"quantity": "0",
"sku_id": "3161300228969"
},
{
"price": "63.8",
"orginal_price": "63.80",
"properties": "1627207:1331264247",
"properties_name": "1627207:1331264247:颜色分类:璀璨钻石套餐【送工具卡+链子】",
"quantity": "167",
"sku_id": "3161107666655"
}
]
},
"seller_id": "2596264565",
"sales": "1",
"shop_id": "127203758",
"props_list": {
"1627207:1347647754": "颜色分类:长方形带开瓶器+送工具刀卡+链子",
"1627207:1347647753": "颜色分类:椭圆形带开瓶器+送工具刀卡+链子",
"1627207:1195392087": "颜色分类:GJ018X钥匙刀+送工具刀卡+链子",
"1627207:1331112595": "颜色分类:超凡大师套餐【送工具卡+链子】",
"1627207:1331112594": "颜色分类:最强王者套餐【送工具卡+链子】",
"1627207:1331264247": "颜色分类:璀璨钻石套餐【送工具卡+链子】"
},
"seller_info": {
"title": "欢乐购客栈",
"shop_name": "欢乐购客栈",
"sid": "127203758",
"zhuy": "//shop127203758.taobao.com",
"level": "12",
"shop_type": "C",
"user_num_id": "2596264565",
"nick": "欢乐购客栈",
"cid": null,
"delivery_score": "4.8 ",
"item_score": "4.8 ",
"score_p": "4.8 "
},
"tmall": "false",
"error": "",
"warning": "",
"url_log": [],
"stuff_status": "",
"shopinfo": {
"shop_name": "欢乐购客栈",
"shop_id": "127203758"
},
"data_from": "mtop",
"method": "item_mtop:item_get",
"promo_type": null,
"props_img": {
"1627207:1347647754": "//img.alicdn.com/imgextra/i3/2596264565/TB2.XeblVXXXXXkXpXXXXXXXXXX_!!2596264565.jpg",
"1627207:1347647753": "//img.alicdn.com/imgextra/i4/2596264565/TB2dTrjdVXXXXXBXpXXXXXXXXXX_!!2596264565.jpg",
"1627207:1195392087": "//img.alicdn.com/imgextra/i2/2596264565/TB2j22kdVXXXXXdXpXXXXXXXXXX_!!2596264565.jpg",
"1627207:1331112595": "//img.alicdn.com/imgextra/i4/2596264565/TB2_uiXnFXXXXXBXXXXXXXXXXXX_!!2596264565.jpg",
"1627207:1331112594": "//img.alicdn.com/imgextra/i4/2596264565/TB2Gm9xnFXXXXbmXXXXXXXXXXXX_!!2596264565.jpg",
"1627207:1331264247": "//img.alicdn.com/imgextra/i3/2596264565/TB2wWohmXXXXXX8XXXXXXXXXXXX_!!2596264565.jpg"
},
"rate_grade": "",
"shop_item": [],
"relate_items": []
},
"secache": "d8bd20b8f0d9df02dd030dd374110240",
"secache_time": 1591841298,
"secache_date": "2020-06-11 10:08:18",
"translate_status": "error",
"translate_time": 0.001,
"language": {
"current_lang": "zh-CN",
"source_lang": "cn"
},
"error": "",
"reason": "",
"error_code": "0000",
"cache": 1,
"api_info": "today:7033 max:10000",
"execution_time": 0.211,
"server_time": "Beijing/2020-06-11 10:12:27",
"call_args": {
"num_iid": "520813250866",
"area_id": "440111"
},
"api_type": "taobao",
"translate_language": "zh-CN",
"translate_engine": "google_cn",
"server_memory": "8.26MB",
"request_id": "15ee1930b4e098"
}
二、数据库数据导入csv文件并建模分析
class Test_myqsl(object):
# 运行数据库和建立游标对象
def __init__(self):
self.connect = pymysql.connect(host="127.0.0.1", port=3306, user="root", password="xxxxxxx", database="webcrawlers",
charset="utf8mb4")
# 返回一个cursor对象,也就是游标对象
self.cursor = self.connect.cursor(cursor=pymysql.cursors.DictCursor)
# 关闭数据库和游标对象
def __del__(self):
self.connect.close()
self.cursor.close()
def write(self):
# 将数据转化成DataFrame数据格式
data = pd.DataFrame(self.read())
# 把id设置成行索引
data_1 = data.set_index("id", drop=True)
# 写写入数据数据
pd.DataFrame.to_csv(data_1, "e:/python1/taobaodatatest.csv", encoding="gbk")
print("写入成功")
def read(self):
# 读取数据库的所有数据
data = self.cursor.execute("""select * from information""")
field_2 = self.cursor.fetchall()
# pprint(field_2)
return field_2
# 封装
def main():
write = Test_myqsl()
此时,我们在e盘中的python1文件中,就有了taobaodatatest.csv这个文件。里面的数据是由webcrawlers数据库information这个表导入的。
在我们进行数据分析之前,我们要拿到商品的价格price_product、和购买人数number_purchase
这里面的数据包含了一些无用符号,比如说' '、万、+、人付款、元。我们需要它的数据进行分析。所以我们把这些符号处理一下,拿到我们所需要的数据。
# TODO 对csv文件进行符号、文字的替换
f = open('E:/python1/taobaodatatest.csv', encoding='gbk')
content_f = f.read()
with open('E:/python1/taobaodatatest.csv', 'w', encoding='gbk') as f1:
t = content_f.replace("'", ' ')
f1.write(t)
f.close()
f = open('E:/python1/taobaodatatest.csv', encoding='gbk')
content_f = f.read()
with open('E:/python1/taobaodatatest.csv', 'w', encoding='gbk') as f2:
g = content_f.replace('万', '0000')
f2.write(g)
f.close()
f = open('E:/python1/taobaodatatest.csv', encoding='gbk')
content_f = f.read()
with open('E:/python1/taobaodatatest.csv', 'w', encoding='gbk') as f3:
h = content_f.replace('+', '')
f3.write(h)
f.close()
f = open('E:/python1/taobaodatatest.csv', encoding='gbk')
content_f = f.read()
with open('E:/python1/taobaodatatest.csv', 'w', encoding='gbk') as f4:
j = content_f.replace('人付款', '')
f4.write(j)
f.close()
f = open('E:/python1/taobaodatatest.csv', encoding='gbk')
content_f = f.read()
with open('E:/python1/taobaodatatest.csv', 'w', encoding='gbk') as f5:
k = content_f.replace('元', '')
f5.write(k)
f.close()
将taobaodatatest.csv文件的特殊符号处理完之后,进行数据分析、建模
# TODO 1.分析商品价格对销量的影响
tbdata = pd.read_csv('e:/python1/taobaodatatest.csv', encoding='gbk')
sns.set(style="darkgrid")
sns.jointplot(x="price_product", y='number_purchaser', data=tbdata, kind='scatter', color='purple')
plt.rcParams['font.sans-serif'] = ['SimHei']
plt.rcParams['axes.unicode_minus'] = False
plt.title('商品价格对销量的影响', loc='right')
plt.show()
# TODO 2.分析商品价格对销售总额的影响
plt.rcParams['font.sans-serif'] = ['SimHei']
plt.rcParams['axes.unicode_minus'] = False
tbdata['GMV'] = (tbdata['price_product']) * (tbdata['number_purchaser'])
sns.regplot(x="price_product", y="GMV", data=tbdata, color='purple')
plt.title('商品价格对销售总额的影响')
plt.show()
# TODO 3.分析不同省份的店铺数量分布
plt.rcParams['font.sans-serif'] = ['SimHei']
plt.rcParams['axes.unicode_minus'] = False
plt.figure(figsize=(8, 4))
province = tbdata['address_store']
province.value_counts().plot(kind='bar', color='purple')
plt.xticks(rotation=90)
plt.xlabel('省份')
plt.ylabel('店铺数量')
plt.title('不同省份的店铺数量分布')
plt.show()
# TODO 4.直观地表示价格、省份、销量三者之间的关系(这里采用三维绘图表示三者关系)
x, y = np.mgrid[-2:2:20j, -2:2:20j]
z = x * np.exp(-x ** 2 - y ** 2)
ax = plt.subplot(111, projection='3d')
ax.plot_surface(x, y, z, rstride=2, cstride=1, cmap=plt.cm.Blues_r)
ax.set_xlabel("price_product")
ax.set_ylabel("address_store")
ax.set_zlabel("number_purchaser")
plt.title('价格、省份、销量三者之间的关系')
plt.show()
此时爬取的数据进行分析结果如图: