爬虫淘宝商品案例

import requests
import re

def getHtml(keyword, page=1):
    payload = {'q': keyword,
               's': str((page-1)*44)}
    headers = {'authority': 's.taobao.com',
                'user-agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 \
                (KHTML, like Gecko) Chrome/57.0.2987.98 Safari/537.36',
               'cookie': 'Your cookie'}

    url = 'https://s.taobao.com/search'
    response = requests.get(url, params=payload, headers= headers, timeout=30)
    response.raise_for_status()
    response.encoding = response.apparent_encoding

    return response.text

# def open_url(keyword, page=1):
#     keyload = {'q': keyword, 's': str((page - 1) * 44), 'sort': 'sale-desc'}

def parserHtml(ilt, html):
    try:
        # item = re.search(r'g_page_config = (.*);\n', html) # 爬取整个商品页面
        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])
            ilt.append([price, title])
        return ilt
    except:
        print("解析错误")


def printList(ilt):
    try:
        tplt = "{:4}\t{:8}\t{:16}"
        print(tplt.format("序号", "价格", "名称"))
        count = 0
        for i in ilt:
            count += 1
            print(tplt.format(count, i[0], i[1]))
    except:
        print("打印出现错误")

def main():
    ilt = []
    keyword = input("你想搜索的商品")
    html = getHtml(keyword, page=2)
    ilt = parserHtml(ilt, html)
    printList(ilt)

main()

上一篇:(一)、ElasticSearch简介


下一篇:vue 过滤使用(搜索)