淘宝商品信息定向爬虫

import requests
import re
 
def getHTMLText(url,kv):
    try:
        r = requests.get(url,headers=kv,timeout=30)
        r.raise_for_status()
        r.encoding = r.apparent_encoding
        return r.text
    except:
        return ""
     
def parsePage(ilt, html):
    try:
        plt = re.findall(r'\"view_price\"\:\"[\d\.]*\"',html)
        tlt = re.findall(r'\"raw_title\"\:\".*?\"',html)
        for i in range(len(plt)):
            price = eval(plt[i].split(':')[1])
            title = eval(tlt[i].split(':')[1])
            ilt.append([price , title])
    except:
        print("")
 
def printGoodsList(ilt):
    tplt = "{:4}\t{:8}\t{:16}"
    print(tplt.format("序号", "价格", "商品名称"))
    count = 0
    for g in ilt:
        count = count + 1
        print(tplt.format(count, g[0], g[1]))
         
def main():
    goods = '电脑'
    depth = 3
    start_url = 'https://s.taobao.com/search?q=' + goods
    cook="thw=cn; cna=aguVFS4cU0cCAT2k2sXKqV4p; t=2d7f47f00720d7fbe9b3dadcb093a495; hng=CN%7Czh-CN%7CCNY%7C156; tracknick=%5Cu80E1%5Cu7FFC421181; lgc=%5Cu80E1%5Cu7FFC421181; _cc_=VFC%2FuZ9ajQ%3D%3D; tg=0; mt=ci=-1_0; v=0; _tb_token_=5fbeeb31efe31; alitrackid=www.sogou.com; lastalitrackid=www.sogou.com; x=e%3D1%26p%3D*%26s%3D0%26c%3D0%26f%3D0%26g%3D0%26t%3D0; swfstore=273068; uc1=cookie14=UoTaHPGiQRohqg%3D%3D; l=cBO-vB9qqEMKOcbbBOCgIZiu5u7OSIRAguWjZXTMi_5Q16LsigQOk7AUeFp6VjWdtdLB4qPsYQ29-etksdy06Pt-g3fP.; isg=BK6u9M1Bf949OotdVjgA2boZ_wR6d1etywgrOdh3G7Fsu04VQD1tueuxc2fyY2rB"
    kv={'cookie':cook,'user-agent':'Mozilla/5.0'}
    infoList = []
    for i in range(depth):
        try:
            url = start_url + '&s=' + str(44*i)
            html = getHTMLText(url,kv)
            parsePage(infoList, html)
        except:
            continue
    printGoodsList(infoList)
     
main()

注：
kv的格式应该是这样的：
kv = {‘cookie’:‘cookie’,‘user-agent’:‘Mozilla/5.0’}
注意都应该用 ‘’ ，然后还有个英文的 逗号,
kv写完要在后面的代码中添加
r = requests.get(url, headers=kv,timeout=30)

注：
cookile查看;
1.F12在浏览器的控制面板console中输入document.cookie查看：