作者：一只蟲

轉載請註明出處

Mt端的Tmall解決了Pc端3頁廢除通用cookies的機制,只是mt端的數據有點少19/page

import requests
from lxml import etree
from pymysql import *
from tkinter import *
from urllib import parse

window = Tk()
window.title("天貓列表商品采集")
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 Tmall(object):
    def __init__(self,name,to_page, w_page):

        self.url = ‘https://list.tmall.com/m/search_items.htm?page_size=20&page_no={}&q=‘ + name
        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.proxies = {
            "http": "http://113.207.44.70:3128",
        }

        # 生成url列表
        self.url_list = [self.url.format(i) for i in range(to_page, w_page + 1)]

    # 請求url
    def get_data(self, url):
        try:
            response = requests.get(url, headers=self.headers, proxies=self.proxies, timeout=10)
            return response.json()
        except Exception as e:
            ‘‘‘吧報錯信息寫入log日誌‘‘‘
            with open(‘log.txt‘, ‘a‘,encoding=‘utf-8‘) as f:
                f.write(repr(e) + ‘\n‘)
    # 解析數據
    def parse_data(self, data):
        try:
            data_list = []
            for i in data["item"]:
                # 圖片鏈接
                img_link = i[‘img‘] if i[‘img‘] else i[‘img‘]
                # 商品鏈接
                goods_link = i[‘url‘] if i[‘url‘] else "空"
                # 商品價格
                price = i[‘price‘] if i[‘price‘] else "空"
                # 商品名稱
                title = i[‘title‘]  if i[‘title‘] else "空"
                # 公司
                company = i[‘shop_name‘] if i[‘shop_name‘] else "空"
                # 月交易
                deal_count = i[‘sold‘] if i[‘sold‘] else "空"
                # 評論數
                comment_count = i[‘comment_num‘] if i[‘comment_num‘] else "空"
                time = {
                    ‘name‘: ‘天貓‘,
                    ‘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
        except Exception as e:
            ‘‘‘吧報錯信息寫入log日誌‘‘‘
            with open(‘log.txt‘, ‘a‘,encoding=‘utf-8‘) as f:
                f.write(repr(e) + ‘\n‘)

    # 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‘,encoding=‘utf-8‘) 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 = Tmall(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Tmall商品列表Mt端。