淘宝搜索定向爬取

注意：依据每个关键词的不同，正则表达式可能需要需改。本例中正则表达式，仅对应于本例中关键词。

import requests,re

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 parserHTML(infoList,html):
     try:
        plt = re.findall(r'\"price\"\:\"[\d\.]*\"',html)
        tlt = re.findall(r'\"title\"\:\".*?\"',html)
        for i in range(len(plt)):
            price = eval(plt[i].split(':')[1])
            title = eval(tlt[i].split(':')[1])
            infoList.append([price , title])
     except:
        print("")

def printInfo(infoList):
    tplt = '{:4}\t{:6}\t{:18}'
    print(tplt.format('序号','价格','名称'))
    count = 1
    for il in infoList:
        print(tplt.format(count,il[0],il[1]))
        count += 1

def main():
    deep = 5
    keyword = '笔记本电脑'
    url = 'https://s.taobao.com/search?q=' + keyword
    infoList = []
    for i in range(deep):
        try:
            tempUrl = url + '&s=' + str(44*i)
            html = getHTMLText(tempUrl)
            parserHTML(infoList,html)
        except:
            continue
    printInfo(infoList)

main()