淘宝商品信息定向爬虫实例介绍

功能描述:
1)目标: 获取淘宝搜索页面的信息, 提取其中的商品名称和价格.
2)理解: 淘宝的搜索接口, 翻页的处理
3)技术路线  requests-re


import re

"""
1, 提交商品搜索请求, 循环获取页面
2, 对于每个页面, 提取商品名称和价格信息
3, 将信息输出到屏幕上
"""


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)  # *?为最小匹配
        for i in range(len(plt)):
            price = eval(plt[i].split(\':\')[1])
            title = eval(tlt[i].split(\':\')[1])
            ilt.append([price, title])
    except:
        print("")


def printGoodList(ilt):
    tplt = "{:4}\t{:8}\t{:16}"
    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]))


def main():
    goods = \'书包\'
    depth = 2
    start_url = \'https://s.taobao.com/search?q=\' + goods
    info_list = []
    for i in range(depth):
        try:
            url = start_url + \'&s=\' + str(44 * i)
            html = getHtmlText(url)
            parsePage(info_list, html)
        except:
            continue
    printGoodList(info_list)


main()