最近寫了個專門爬百度的，后來又想爬京東的，還是采用上次的BeautifulSoup+requests模塊
下面直接上代碼，看不懂的可以看這篇文章或者注釋來學習
#!/usr/bin/env python # -*- coding: utf-8 -*- #written by DY #http://dyblog.tk #e-mail:duyun888888@qq.com ########import############### import requests from bs4 import BeautifulSoup #from openpyxl import *#寫入表格使用，寫入txt時報錯 import time from tkinter import * import tkinter.messagebox from tkinter import ttk ########import結束############ #----------全局變量----------- https = 'https:' headers = { "Accept":"text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.9", "User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.16 Safari/537.36", }#定義頭部信息，防止被網站阻止 name = [] price = [] introduct = [] urlss = [] #----------全局變量結束------- #===============函數區域============== #--------圖形界面函數開始-------- def genxin(): top = Tk() top.title("'%s'在'京東'中查詢結果"%E1.get()) top.geometry("800x600+600+100") columns = ("物品名", "價格", "簡介", "鏈接") treeview = ttk.Treeview(top, show="headings", columns=columns, height='100') treeview.column("物品名", width=200, anchor='center') treeview.column("價格", width=50, anchor='center') treeview.column("簡介", width=200, anchor='center') treeview.column("鏈接", width=50, anchor='center') treeview.heading("物品名", text="物品名") treeview.heading("價格", text="價格") treeview.heading("簡介", text="簡介") treeview.heading("鏈接", text="鏈接") treeview.pack() print(name) print(price) print(introduct) print(urlss) for write_ in range(min(len(name),len(price),len(introduct),len(urlss))): # 寫入數據 treeview.insert('', write_, values=(name[write_], price[write_], introduct[write_], urlss[write_])) top.mainloop() #--------圖形界面函數結束-------- def searchstart():#打開頁面查找，獲取html url='https://search.jd.com/Search?keyword='+E1.get() url = str(url) html = requests.get(url,headers=headers).text#打開鏈接，獲取html soup = BeautifulSoup(html, 'html.parser') for div in soup.find_all('div',class_="ml-wrap"):#包含價格，銷量，商品，頁數 for shangpin in div.find_all('div',class_="goods-list-v2 gl-type-1 J-goods-list"): for prices in shangpin.find_all('div',class_="p-price"):#商品價格 for pricess in prices.find_all('i'): if pricess=='': pricess='無' price.append(pricess.text) for shangpin in div.find_all('div',class_="goods-list-v2 gl-type-1 J-goods-list"):#商品 for name_ in shangpin.find_all('div',class_="p-name p-name-type-2"): for titlename in name_.find_all('em'):#簡介 if titlename=='': titlename='無' introduct.append(titlename.text) for name_ in shangpin.find_all('div',class_="p-name p-name-type-2"): for introduction in name_.find_all('a',target="_blank"):#商品名 introduction = introduction.get('title') if introduction=='': introduction='無' name.append(introduction) for url in shangpin.find_all('div',class_="p-name p-name-type-2"): for urls in url.find_all('a'): urlss.append(https+urls['href']) print(introduct) print(name) genxin() #===============函數區域結束========== ##########圖形界面開始######### root = Tk() root.title('京東商品 查詢') root.geometry('250x160') L1 = Label(root, text="商品名： ") L1.place(x = 5,y = 15) E1 = Entry(root, bd =2) E1.place(x = 60,y = 15) A = Button(root, text ="確定",font=('Arial', 12), width=10, height=1,command=searchstart) A.place(x = 350,y = 10)#確定按鈕 root.mainloop() ###########圖形界面結束######### #written by DY #http://dyblog.tk #e-mail:duyun888888@qq.com
運行截圖：
如果有不懂的，可以直接留言或者聯系duyun888888@qq.com。