作者:一只虫
转载请注明出处
Mt端的Tmall解决了Pc端3页废除通用cookies的机制,只是mt端的数据有点少19/page
import requests
from lxml import etree
from pymysql import *
from tkinter import *
from urllib import parse
window = Tk()
window.title("天猫列表商品采集")
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 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)]
# 请求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:
‘‘‘吧报错信息写入log日志‘‘‘
with open(‘log.txt‘, ‘a‘,encoding=‘utf-8‘) as f:
f.write(repr(e) + ‘\n‘)
# 解析数据
def parse_data(self, data):
try:
data_list = []
for i in data["item"]:
# 图片链接
img_link = i[‘img‘] if i[‘img‘] else i[‘img‘]
# 商品链接
goods_link = i[‘url‘] if i[‘url‘] else "空"
# 商品价格
price = i[‘price‘] if i[‘price‘] else "空"
# 商品名称
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"
# 评论数
comment_count = i[‘comment_num‘] if i[‘comment_num‘] else "空"
time = {
‘name‘: ‘天猫‘,
‘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:
‘‘‘吧报错信息写入log日志‘‘‘
with open(‘log.txt‘, ‘a‘,encoding=‘utf-8‘) as f:
f.write(repr(e) + ‘\n‘)
# 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‘,encoding=‘utf-8‘) 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 = Tmall(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()