功能描述

目标：获取淘宝搜索页面的信息，提取其中商品的名称和价格
理解： 获得淘宝的搜索接口， 翻页的处理
技术路线：requests- re
注意： 通过查取相关协议，发现淘宝不允许任何爬虫爬取相关页面

程序设计

爬取淘宝的页面信息，需要模拟淘宝登陆才可以

代码：

import requests
import re
kv = {
   'user-agent': 'Mozilla/5.0'}

def getHTMLText(url):
    try:
        r = requests.get(url, timeout = 30, headers = kv)
        r.raise_for_status()
        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])
            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 += 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()