求Python代码:要求淘宝网站搜索某种商品（比如充电宝），使用Python提取该类商品的“店铺网

Posted 2023-03-20

求Python代码:要求淘宝网站搜索某种商品（比如充电宝），使用Python提取该类商品的“店铺网址”+“产品参数”数据，并保存到文件中，要求至少提取10个商品的数据。

参考技术A 只提供思路 用 scrapy 或者 pyspider 等网页爬虫框架写一个爬虫脚本就ok了

python爬虫之：淘宝商品搜索爬虫（收集商品信息/下载详情图）

一、获取商品信息：

#!/usr/bin/python3.5
#coding:utf8


import xlsxwriter as wx
import re
import cgi
import requests
import os
import time
import urllib


page=1
downsuccess = 0
downfaild = 0
shop = [("店铺名称","商品","商品售价￥","商品购买数","产地","商品详情地址","商品展示图")]

shop2 = [("店铺名称","商品","商品售价￥","商品购买数","产地","商品详情地址","商品展示图")]
#用于生成EXCEL
detailpage = ""
#keyword="公仔"

keyword = input("[+] 输入搜索关键词：")
page = input("[+] 输入查找页数:")

url="https://s.taobao.com/search?q=%s"%(keyword)
now = time.strftime("%Y%m%d_%H%M%S")
imglocalpath=[("商品图示")] 

def getPicIMG(url,path,imgname):
    """
    下载商品展示图片

    """
    if os.path.exists(path):
        pass
    else:
        os.mkdir(path)
    try:
        imgdir = path+"/"+imgname.replace(".jpeg","")    
        os.mkdir(imgdir)
        imgdata = requests.get(url).content
        print("[*]下载图片：%s" % imgname)
        f = open(imgdir+"/"+imgname,"wb")
        f.write(imgdata)
        f.close()
        imglocalpath.append([imgdir+"/"+imgname])
        global downsuccess
        downsuccess += 1
    except:
        print("[!]啊哦出错了")
        global downfaild
        downfaild += 1
        pass

def getHTML(url,s):
    """
    获取HTML源代码
    """
    try:
        if s == 0:
            responText = requests.get(url) #第一页
        else:
            responText = requests.get(url+"&s=%s"%(str(44*s))) #其他页
        return responText
    except:
        return ‘"nice":"error"‘

def get(url):
    """
    Http Get方法
    """
    try:
        respon = requestss.get(url)
        return respon
    except:
        return 1


def Regx(Text):
    """
    提取商品信息
    
    """
    #Text = str(Text)
    print(type(Text))
    Titleregx = re.findall(‘"raw_title":"(.*?)"‘,Text)
    PiceRegx = re.findall(‘"view_price":"([\d+.]*)"‘,Text)
    item_loc = re.findall(‘"item_loc":"(.*?)"‘,Text)
    nice = re.findall(‘"nick":"(.*?)"‘,Text)
    purl = re.findall(‘"pic_url":"(.*?)"‘,Text)
    detail = re.findall(‘"detail_url":"(.*?)"‘,Text)
    sales = re.findall(‘"view_sales":"(\d+.*?)"‘,Text)
    #shop.append([Titleregx.findall(Text),PiceRegx])
    for i in range(Titleregx.__len__()):
        imgurl = "https:"+purl[i]
        shop.append((nice[i],Titleregx[i],PiceRegx[i],sales[i],item_loc[i],"https:"+detail[i].replace("\\u003d","=").replace("\\u0026","&"),imgurl)) 
        shop2.append((nice[i],Titleregx[i],PiceRegx[i],sales[i],item_loc[i],"https:"+detail[i].replace("\\u003d","=").replace("\\u0026","&"),"./公仔"+now+"/"+Titleregx[i]+"/"+Titleregx[i]+".jpeg")) 


def writeexcel(path,dealcontent):
         """
         将数据插入Excel   
         """
        
         workbook = wx.Workbook(path)
         top = workbook.add_format({‘border‘:1,‘align‘:‘center‘,‘bg_color‘:‘white‘,‘font_size‘:11,‘font_name‘: ‘微软雅黑‘})
         red = workbook.add_format({‘font_color‘:‘white‘,‘border‘:1,‘align‘:‘center‘,‘bg_color‘:‘800000‘,‘font_size‘:11,‘font_name‘: ‘微软雅黑‘,‘bold‘:True})
         image = workbook.add_format({‘border‘:1,‘align‘:‘center‘,‘bg_color‘:‘white‘,‘font_size‘:11,‘font_name‘: ‘微软雅黑‘})
         formatt=top
         formatt.set_align(‘vcenter‘) #设置单元格垂直对齐
         worksheet = workbook.add_worksheet("Mr.RaoJL-商品爬虫-”"+keyword+"“详情表单")        #创建一个工作表对象
         width=len(dealcontent[0])
         worksheet.set_column(0,width,38.5)            #设定列的宽度为22像素
         for i in range(0,len(dealcontent)):
                 if i==0:
                         formatt=red
                 else:
                         formatt=top
                 for j in range(0,len(dealcontent[i])):
                         if i!=0 and j==len(dealcontent[i])-1:
                                 if dealcontent[i][j]==‘‘:
                                         worksheet.write(i,j,‘ ‘,formatt)
                                 else:
                                         try:
                                                 worksheet.insert_image(i,j,dealcontent[i][j])
                                         except:
                                                 worksheet.write(i,j,‘ ‘,formatt)
                                                 
                         else:
                                 if dealcontent[i][j]:
                                         worksheet.write(i,j,dealcontent[i][j].replace(‘ ‘,‘‘),formatt)
                                 else:
                                         worksheet.write(i,j,‘无‘,formatt)
         workbook.close()

if __name__ == "__main__":
    HTML=""
    #keyword = input("[+] 输入搜索关键词：")
    #page = input("[+] 输入查找页数:")
    for i in range(0,int(page)):
        HTML+=getHTML(url,i).text
    Regx(HTML)
    detailtxt=open("detail_url.txt","w")
    nav = "{:8}\t{:18}\t{:4}\t{:16}\t{:32}\t{:32}\t{:32}"
    print(nav.format("店铺名","商品","价格","购买量","产地","商品图片","商品详情"))
    for i in shop:
        imgurl = i[6]
        imgname = i[1]
        path = keyword+now
        detailu = i[5]
        #print(nav.format(i[0],i[1],i[2],i[3],i[4],i[5],i[6]))
        detailtxt.write("%s" % (detailu+"\n"))
        getPicIMG(imgurl,path,imgname+".jpeg")
    #print(len(shop))
    detailtxt.close()
    writeexcel("%s%s.xlsx"%(keyword,now),shop)
    print("[*]下载成功：%s" % str(downsuccess))
    print("[!]下载失败：%s" % str(downfaild))

二、下载商品详情图

#!/usr/bin/python3.5
#eoding:utf8

import os
import requests
import re
import time
import json

now = time.strftime("%Y%m%d_%H%M%S")
keyword="test"
img = {} 
total = []
tmall = "tamll.com"
https = "https:"
detailPrixe = "https://img.alicdn.com/imgextra/i1/"
sellerId=""

#def __init__(self):
#return None

def get(url):
	try:
		ret = requests.get(url).text
		return ret
	except:
		return 1

def fiterData(text):
	urllist = []
	text=str(text)
	title = re.findall(‘<title>(.*)</title>‘,text)
	imgapi = re.findall(‘apiImgInfo[\s]*:[\s]*\‘(.*)\‘‘,text)
	stateID = re.findall(‘sellerId         : \‘(\d+)\‘‘,text)
	#sellerId = stateID[0]
	try:
		url = https+imgapi[0]

		imgdata = get(url).replace("\r","").replace("\n","").replace("\t","").replace("$callback","").replace(")","").replace("(","")
		imgdata = json.loads(imgdata)
		for i in imgdata:
			if len(i) >= 43:
				urllist.append(i)
			else:
				pass
		img[title[0].replace("-淘宝网","")] = urllist
	except:
		print("[!] Error")
	
def CreateDir(path,url):
	dedir = path+"/detail"
	if os.path.exists(path):
		if os.path.exists(dedir):
			pass
		else:
			os.mkdir(dedir)
	else:
		try:
			os.mkdir(path)
			if not os.path.exists(dedir):
				os.mkdir(dedir)
			else:
				pass
		except FileNotFoundError:
			print("[-] %s " % "FILE NOT FUOUND!")
	print("[*] download detatil %s" % url )
	try:
		ifile = open(dedir+"/"+str(int(time.time()))+".jpg","wb")
		data = requests.get(url).content
		ifile.write(data)
		ifile.close()
	except OSError as e:
		print("[!] OPS error "+e)
		pass
	except:
		print("req")


def ReadListFile():
	try:
		a=open("detail_url.txt","r").read()
		a=a.split("\n")
		return a
	except OSError:
		print("Unoblue file")
		return false


for uite in ReadListFile():
	if uite != "":
		print("[+] %s " %uite)
		html=requests.get(uite).text
		fiterData(html)


for key,value in img.items().__iter__():
	print(key)
	for j in range(len(value)):
		iname = value[j]
		try:
			sellerId=re.findall(‘(\d+).jpg‘,iname)[0]
			ImgUrl=detailPrixe+"%s/" % (sellerId) +iname
			path="%s/%s" %("公仔20170609_183403",key)
			CreateDir(path,ImgUrl)
		except IndexError:
			#print()
			pass
		

本文出自 “独孤无愁” 博客，转载请与作者联系！