爬虫爬取淘宝商品信息

废话少说直接上代码：

import re
import requests

def getHtml(url):
    try:
        r=requests.get(url,timeout=30)
        r.raise_for_status()
        print(r.status_code)
        r.encoding=r.apparent_encoding
       # print(r.text)
        return r.text
    except:
        return ""


def parserPage(lis,html):
    try:
        #正则表达式
        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])
            lis.append([price,title])

    except:
        print("")

def printGoods(lis):

    tplt="{:4}\t{:8}\t{:16}"
    print(tplt.format("序号","价格","商品名称"))
    count=0
    for q in lis:
        print(q[0])
        count=count+1
        print(tplt.format(count,q[0],q[1]))
    print()

def main():
    goods="书包"
    counts =2
    start_url = "https://s.taobao.com/search?q=" + goods
    #start_urls="https://s.taobao.com/search?q=书包"
    infoList = []
    for i in range(counts):
        try:
            url="https://s.taobao.com/search?q=%E4%B9%A6%E5%8C%85&imgfile=&commend=all&ssid=s5-e&search_type=item&sourceId=tb.index&spm=a21bo.2017.201856-taobao-item.1&ie=utf8&initiative_id=tbindexz_20170306&bcoffset=3&ntoffset=0&p4ppushleft=1%2C48&s=88"
            #url=start_url+'&s=' + str(44 * i)
            #url = start_url + '&s=' + str(44 * i)
            html = getHtml(url)
            parserPage(infoList,html)
        except:
            continue
    printGoods(infoList)
main()