爬虫系列之淘宝商品爬取

import re
import requests

def getHTMLText(url):
    try:
        r = requests.get(url, timeout = 30)
        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])  #eval就是将字符串string对象转化为有效的表达式参与求值运算返回计算结果
            title = eval(tlt[i].split(":")[1])
            ilt.append([price, title])
    except:
        print("")       

def printGoodsList(ilt):
    tplt = "{:4}	{:8}	{: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]))
    print("")

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()