import requests
from pymysql import *
from tkinter import *

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

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

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

Label(window, text=‘采集結束頁‘).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)]

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

    # 解析數據
    def parse_data(self, data):
        # 源碼數據
        # 定義各個字段正則匹配規則
        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":"(.*?)"‘

        # 查找滿足匹配規則的內容，並存在列表中
        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 = ‘淘寶‘
            goods_link = "https://detail.tmall.com/item.htm?id=" + goodsL[j]  # 商品鏈接
            img_link = "http:" + imgL[j]  # 商品圖片鏈接
            title = nameL[j]  # 商品名稱
            company = companyL[j]  # 淘寶店鋪名稱
            price = priceL[j]  # 商品價格
            deal_count = dealL[j]  # 商品付款人數
            comment_count = commentL[j]  # 商品評論數，會存在為空值的情況
            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

        # 保存數據

    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()
            # 執行insert語句，並返回受影響的行數：添加一條數據
            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‘]))
                # 關閉Cursor對象
                print(count)
            cs1.close()
            # 提交之前的操作，此處為insert操作
            conn.commit()
        except Exception as e:
            ‘‘‘吧報錯信息寫入log日誌‘‘‘
            with open(‘log.txt‘, ‘a‘) as f:
                f.write(repr(e) + ‘\n‘)
        finally:
            # 關閉Connection對象
            conn.close()

    def run(self):
        # 構建url
        # 構建請求頭
        # 發起請求
        for url in self.url_list:
            data = self.get_data(url)
            # 解析響應，抽取數據
            data_list = self.parse_data(data)
            #  保存數據
            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="確定", relief=‘groove‘, width=9, height=1, bd=4, command=main).pack()
    window.mainloop()

gui采集淘寶列表商品[後期有空更新采集各大電商平臺]