爬虫初步五

淘宝商品价格对比

实例：找一个淘宝商品，可以自定义显示几页的商品信息

代码：

# 淘宝商品价格对比爬虫
import requests
import re


def get_all_http(url):
    try:
        r = requests.get(url, timeout=30)
        r.coding = r.apparent_encoding
        r.raise_for_status()
        return r.text
    except:
        return ""


def analyse_my_data(data, lst1):
    try:
        plt = re.findall(r'\"view_price\"\:\"[\d\.]*\"', data)  # 商品价格 正则表达式
        plt1 = re.findall(r'\"raw_title\"\:\".*?\"', data)  # 商品名称 .*?是最小匹配，取得：后的内容 再一系列直接存入表格
        for i in range(len(plt)):  # 关联两个信息
            price = eval(plt[i].split(':')[1])
            title = eval(plt1[i].split(':')[1])
            lst1.append([price, title])
        return lst1
    except:
        return ""




def print_data(lst1):
    ptlt = "{0:^10}\t{1:^10}\t{2:{3}^10}"
    print(ptlt.format("序号", "价格", "商品",chr(12288)))
    n = 0
    for i in lst1:
        n = n+1
        print(ptlt.format(n,i[0], i[1],chr(12288)))


def main(deepth):
    # 找到淘宝页面url的规律
    url0 = "https://s.taobao.com/search?q=mac+pro+2017&imgfile=&js=1&stats_click=search_radio_all%3A1&initiative_id=staobaoz_20180615&ie=utf8"
    url1 = "https://s.taobao.com/search?q=mac+pro+2017&imgfile=&js=1&stats_click=search_radio_all%3A1&initiative_id=staobaoz_20180615&ie=utf8&bcoffset=4&p4ppushleft=1%2C48&s=44&ntoffset=4"
    url2 = "https://s.taobao.com/search?q=mac+pro+2017&imgfile=&js=1&stats_click=search_radio_all%3A1&initiative_id=staobaoz_20180615&ie=utf8&bcoffset=4&p4ppushleft=1%2C48&ntoffset=4&s="
    for i in range(deepth):
        if i == 0:
            url = url0
        elif i == 1:
            url = url1
        else:
            url1 = url2+str(i*44)

    # 爬取所有网页 的资源
        data = get_all_http(url)
    #解析网页资源
        data2 = analyse_my_data(data, [])
    # 显示商品 价格
        print_data(data2)


main(5)