【Python爬虫】淘宝商品比价定向爬虫

https://www.taobao.com/

 

 

 

 

 

 

 

 

#CrowTaobaoPrice.py
import requests
import re
 
def getHTMLText(url):#获得网页信息
    headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/83.0.4103.116 Safari/537.36'}#使用浏览器header
    try:
        coo = 't=85db5e7cb0133f23f29f98c7d6955615; cna=3uklFEhvXUoCAd9H6ovaVLTG; isg=BM3NGT0Oqmp6Mg4qfcGPnvDY3-pNqzF2joji8w9SGWTYBu241_taTS6UdFrF3Rk0; miid=983575671563913813; thw=cn; um=535523100CBE37C36EEFF761CFAC96BC4CD04CD48E6631C3112393F438E181DF6B34171FDA66B2C2CD43AD3E795C914C34A100CE538767508DAD6914FD9E61CE; _cc_=W5iHLLyFfA%3D%3D; tg=0; enc=oRI1V9aX5p%2BnPbULesXvnR%2BUwIh9CHIuErw0qljnmbKe0Ecu1Gxwa4C4%2FzONeGVH9StU4Isw64KTx9EHQEhI2g%3D%3D; hng=CN%7Czh-CN%7CCNY%7C156; mt=ci=0_0; hibext_instdsigdipv2=1; JSESSIONID=EC33B48CDDBA7F11577AA9FEB44F0DF3'
        cookies = {}#上面的，登录淘宝后用开发者工具获取
        for line in coo.split(';'):  # 浏览器伪装
            name, value = line.strip().split('=', 1)
            cookies[name] = value

        r = requests.get(url,cookies=cookies,headers=headers,timeout=30)
        r.raise_for_status()
        r.encoding = r.apparent_encoding
        return r.text
    except:
        return ""
     
def parsePage(ilt, html):#对所得页面进行解析
    try:
        plt = re.findall(r'\"view_price\"\:\"[\d\.]*\"',html)
        tlt = re.findall(r'\"raw_title\"\:\".*?\"',html)#.*?-最小匹配/匹配的内容是商品本身的名字
        for i in range(len(plt)):
            price = eval(plt[i].split(':')[1])#通过split方法分割：后面的部分只取价格
            title = eval(tlt[i].split(':')[1])#eval去掉双引号
            ilt.append([price , title])
    except:
        print("")
 
def printGoodsList(ilt):#将淘宝得商品信息输出到屏幕上
    tplt = "{:4}\t{:8}\t{:16}"#规定输出格式
    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 = 3 # 要爬取几页
    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()

效果