网络爬虫信息之实战淘宝书包信息爬取14「建议收藏」

大家好，又见面了，我是你们的朋友全栈君。

# 导入requests和re正则库
import requests
import re

# 定义第一个函数实现获取网页数据
def getHTMLText(url,loginheaders):
    try:
        r = requests.get(url,headers=loginheaders, timeout=30)
        r.raise_for_status()
        r.encoding = r.apparent_encoding
        print(r.text)
        return r.text
    except:
        return ""

#定义一个函数实现把书包信息存储区来，包括编号，价格，名称
def parsePage(ilt, html):
    try:
        # 要明白 .* 代表的是任意个不同字符,而不是说必须是任意个相同的字符,其他的也是类似
        # re.findall()返回的是列表类型
        # 利用正则表达式查找价格（"view_price":"任意个数的任意数字加点"）,所以正则表达式还可在小数点后加两个0写成r'\"view_price\"\:\"[\d\.]*00\"'
        plt = re.findall(r'\"view_price\"\:\"[\d\.]*\"', html)
        # 利用正则表达式查找题目（"raw_title":"任意个数的任意字符"）
        tlt = re.findall(r'\"raw_title\"\:\".*?\"', html)
        #循环遍历价格和题目，利用:分隔符获得值
        for i in range(len(plt)):
            price = eval(plt[i].split(':')[1])
            title = eval(tlt[i].split(':')[1])
            # 添加到ilt列表当中,二维元组列表
            ilt.append([price, title])
    except:
        print("")

# 打印题目和爬取的信息
def printGoodsList(ilt):
    # 定义输出格式
    tplt = "{:4}\t{:8}\t{:16}"
    print(tplt.format("序号", "价格", "商品名称"))
    # 循环遍历打印爬取到的信息,第一种方式
    for i in range(len(ilt)):
        print(tplt.format(i + 1, ilt[i][0], ilt[i][1]))
    # 第二种方式,g是从ilt循环遍历每元组的每项,g[0],g[1]是价格和题目
    # count = 0
    # for g in ilt:
    #     count = count + 1
    #     print(tplt.format(count, g[0], g[1]))

#定义主函数，写一下变量
def main():
    goods = '书包'
    # depth是爬取的深度，也就是爬取几页
    depth = 3
    start_url = 'https://s.taobao.com/search?q=' + goods
    infoList = []
    for i in range(depth):
        try:
            url = start_url + '&s=' + str(44 * i)
            # 设置登录的头信息，注意cookie是登陆页面点击登录获取的头信息
            loginheaders = {
                "user-agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.132 Safari/537.36",
                "cookie": "t=4ddf8b70981503ff445f594236c71e96; thw=cn; cookie2=12bdc5dde93e3514edca199a193f232f; _tb_token_=e45e8be4e50be; _samesite_flag_=true; enc=201s0rRJEHeguaLLCC6IAbLJao3k%2FWpbaR4FH6jpx1T6haa1auRivMShxlx1S0Ul3c3meKsTzPUcwTv3aEzt1Q%3D%3D; hng=CN%7Czh-CN%7CCNY%7C156; alitrackid=www.taobao.com; lastalitrackid=login.taobao.com; mt=ci=0_0; JSESSIONID=C7EA2D8019D08587402413BDBF38AFF0; cna=k8/5Fvt7vU8CAbfIPj2evd1M; l=eBxklgrHqCn48L6LBOfZourza77TlIRfguPzaNbMiT5P_2fH75cAWZjFnt8MCnGVnsZw-354uljQBrT8xyUBh6Yl3ZQ7XPQo3dTh.; isg=BFFRjiZN687i_QTKjM76nskzYF3rvsUwkMIhzjPmIpg42nAseQpbAHY4fK48Ul1o; tfstk=cwyCBJqLmeYQTTeeQzsZTKVPlrkPZj_sj6gLA5hd3EP90jECibvqlvj4ZFvtMc1..; sgcookie=EjxPeg5aM1t9jg2xwmUNw; unb=2639049752; uc1=cookie14=UoTUMtQjutczRQ%3D%3D&cookie21=VFC%2FuZ9ajC0X15Rzt0LhxQ%3D%3D&pas=0&existShop=false&cookie15=WqG3DMC9VAQiUQ%3D%3D&cookie16=VT5L2FSpNgq6fDudInPRgavC%2BQ%3D%3D; uc3=nk2=2nZbzUmLMMCi2g%3D%3D&vt3=F8dBxGXMemSB7fdhNUQ%3D&lg2=V32FPkk%2Fw0dUvg%3D%3D&id2=UU6idYdXStUjdg%3D%3D; csg=8948e7ae; lgc=%5Cu90ED%5Cu5DDD%5Cu5DDD1998; cookie17=UU6idYdXStUjdg%3D%3D; dnk=%5Cu90ED%5Cu5DDD%5Cu5DDD1998; skt=b778092dd81708b9; existShop=MTU4ODQ3NzIxNQ%3D%3D; uc4=id4=0%40U2xvIZeyY044%2Fg4ssnvrOTWRM69N&nk4=0%402EwyHO%2FQs1K5Yt3PADSqX0DTequA; tracknick=%5Cu90ED%5Cu5DDD%5Cu5DDD1998; _cc_=V32FPkk%2Fhw%3D%3D; _l_g_=Ug%3D%3D; sg=82b; _nk_=%5Cu90ED%5Cu5DDD%5Cu5DDD1998; cookie1=BvGDAyiO3yivOSSiEiVryF%2FdX85RndH78rFBY0y3kOc%3D"
            }
            html = getHTMLText(url, loginheaders)
            parsePage(infoList, html)
        except:
            continue
    printGoodsList(infoList)


main()