淘宝比价定向爬虫

淘宝比价定向爬虫

• 目标：获取淘宝搜索页面信息，获得商品名称和价格
• 理解：淘宝搜索的接口，翻页的处理

步骤：

步骤一：提交商品搜索请求，循环获取页面
步骤二：对于每一个页面，提取商品名称和价格信息
步骤三：将信息输出到屏幕上

import requests
import re
#可以看到页面里面是脚本不能用bs
def getHTMLText(url):
    try:
        r = requests.get(url, timeout = 30)
        r.raise_for_status()
        r.encoding = r.apparent_encoding
        print(r.url)
        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)):
            #用eval可以将最外层的双引号或单引号去掉
            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 = '书包'
    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)
            html = getHTMLText(url)
            parsePage(infoList, html)
        except:
            continue
    printGoodsList(infoList)
main()