使用requests和re库对淘宝商品信息进行定向爬取

#coding=utf-8
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(list, 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])
            list.append([price, title])
    except:
        print("")

def getGoodsList(list):
    tplt = "{:4}\t{:8}\t{:16}"
    print(tplt.format("序号", "价格", "商品名称"))
    count = 0
    for g in list:
        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
    getGoodsList(infoList)
if __name__ == '__main__':
    main()