淘宝商品信息定向爬虫.py（亲测有效）

import requests
import re

def getHTMLText(url):
    try:
        kv = {
            \'cookie\': \'\', #要换成自己网页的cookie
            \'user-agent\':\'Mozilla/5.0\'  # 请求头;指定访问浏览器为Mozilla5.0版本的浏览器
        }
        r = requests.get(url,timeout=30,headers=kv)
        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])  # eval函数去掉最外层的单引号，双引号
            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 = \'书包\'
    depth = 2
    start_url = \'https://s.taobao.com/search?q=\' + goods

    infoList = []
    for i in range(depth):
        try:
            url = start_url + \'&s=\' + str(44*i)
            html = getHTMLText(url)
            parsePage(infoList,html)
        except:
            continue
    printGoodsList(infoList)

main()

View Code

查找自己cookie的步骤如下：

（1）进入淘宝页面

 

 

 

（2）按下F12，刷新页面，点击最上面的NetWork，找到下面文件

 

 

（3）找到RequestHeaders，找到里面的Cookie复制即可