爬虫练习（三）

用requests + re库做的小练习：定向爬取淘宝商品信息(分页)

url : 'https://s.taobao.com/search?q=' + ‘书包’+ ‘&s=’+ str(44*i)

import requests
import 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 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)):
            #eval()函数可以将获得的字符串外面的单引号或者双引号去掉
            price = eval(plt[i].split(':')[1])
            title = eval(tlt[i].split(':')[1])
            ilt.append([price, title])
    except:
        print("")


def printGoodsList(ilt):
    #先定义打印模板
    #分为三个位置，后面的数字表示给定的长度
    tplt = "{:4}\t{:8}\t{:16}"
    print(tplt.format("序号","价格","商品名称", chr(12288)))
    count = 0
    for g in ilt:
        count = count + 1
        print(tplt.format(count, g[0], g[1], chr(12288)))


def saveGoodsList(list):
    pass


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)
            print
            parsePage(infoList, html)
            print(infoList)
        except:
            continue
    printGoodsList(infoList)


if __name__ == '__main__':
    main()

经验总结：

1.re库匹配页面内容，bs4库匹配网页节点信息