gui采集淘宝列表商品[后期有空更新采集各大电商平台]

import requestsfrom pymysql import *from tkinter import *

window = Tk()window.title("淘宝列表商品采集")window.geometry(‘200x180‘)

Label(window, text=‘关键字采集‘).pack()name = StringVar()Entry(window, textvariable=name).pack()

Label(window, text=‘采集起始页‘).pack()to_page = StringVar()Entry(window, textvariable=to_page).pack()

Label(window, text=‘采集结束页‘).pack()w_page = StringVar()Entry(window, textvariable=w_page).pack()

class Taobao(object):    def __init__(self,name, to_page, w_page):

self.url = ‘https://s.taobao.com/search?q=‘+name+‘&s={}‘        self.headers = {‘accept‘:‘text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8‘,                        ‘accept-encoding‘:‘gzip, deflate, br‘,                        ‘accept-language‘:‘zh-CN,zh;q=0.9‘,                        ‘cache-control‘:‘max-age=0‘,                        ‘upgrade-insecure-requests‘:‘1‘,                        ‘user-agent‘:‘Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/64.0.3282.119 Safari/537.36‘}

self.url_list = [self.url.format(str((i) * 44)) for i in range(to_page, w_page + 1)]

# 请求url    def get_data(self, url):        response = requests.get(url, headers=self.headers, timeout=10)        return response.content.decode()

# 解析数据    def parse_data(self, data):        # 源码数据        # 定义各个字段正则匹配规则        img_urlpat = ‘"pic_url":"(//.*?)"‘        goods_urlpat = ‘"nid":"(.*?)"‘        title_pat = ‘"raw_title":"(.*?)"‘        company_pat = ‘"nick":"(.*?)"‘        price_pat = ‘"view_price":"(.*?)"‘        deal_countpat = ‘"view_sales":"(.*?)"‘        comment_countpat = ‘"comment_count":"(.*?)"‘

# 查找满足匹配规则的内容，并存在列表中        imgL = re.compile(img_urlpat).findall(data)        goodsL = re.compile(goods_urlpat).findall(data)        nameL = re.compile(title_pat).findall(data)        companyL = re.compile(company_pat).findall(data)        priceL = re.compile(price_pat).findall(data)        dealL = re.compile(deal_countpat).findall(data)        commentL = re.compile(comment_countpat).findall(data)

data_list = []        for j in range(len(imgL)):            name = ‘淘宝‘            goods_link = "https://detail.tmall.com/item.htm?id=" + goodsL[j]  # 商品链接            img_link = "http:" + imgL[j]  # 商品图片链接            title = nameL[j]  # 商品名称            company = companyL[j]  # 淘宝店铺名称            price = priceL[j]  # 商品价格            deal_count = dealL[j]  # 商品付款人数            comment_count = commentL[j]  # 商品评论数，会存在为空值的情况            if (comment_count == ""):                comment_count = 0            time = {                ‘name‘: name,                ‘img_link‘: img_link,                ‘goods_link‘: goods_link,                ‘price‘: price,                ‘title‘: title,                ‘company‘: company,                ‘deal_count‘: deal_count,                ‘comment_count‘: comment_count,            }            data_list.append(time)        return data_list

# 保存数据

def save_data(self, data_list):        try:            conn = Connect(host="127.0.0.1", user="root", password="root", database="data_list", port=3306,                           charset="utf8")            cs1 = conn.cursor()            # 执行insert语句，并返回受影响的行数：添加一条数据            for index, data in enumerate(data_list):                count = cs1.execute(                    ‘insert into data(name,goods_link,img_link,title,price,company,deal_count,comment_count) values("%s","%s","%s","%s","%s","%s","%s","%s")‘ % (                        data[‘name‘], data[‘goods_link‘], data[‘img_link‘], data[‘title‘], data[‘price‘],                        data[‘company‘], data[‘deal_count‘], data[‘comment_count‘]))                # 关闭Cursor对象                print(count)            cs1.close()            # 提交之前的操作，此处为insert操作            conn.commit()        except Exception as e:            ‘‘‘吧报错信息写入log日志‘‘‘            with open(‘log.txt‘, ‘a‘) as f:                f.write(repr(e) + ‘\n‘)        finally:            # 关闭Connection对象            conn.close()

def run(self):        # 构建url        # 构建请求头        # 发起请求        for url in self.url_list:            data = self.get_data(url)            # 解析响应，抽取数据            data_list = self.parse_data(data)            #  保存数据            self.save_data(data_list)

def main():    n = str(name.get())    t = int(to_page.get())    w = int(w_page.get())    all = Taobao(n, t, w)    all.run()

if __name__ == ‘__main__‘:    Button(window, text="确定", relief=‘groove‘, width=9, height=1, bd=4, command=main).pack()    window.mainloop()

原文地址：https://www.cnblogs.com/bkylkh/p/8629410.html