python爬取淘宝店铺货源

以下是使用Python爬取淘宝店铺货源的步骤：

1. 导入必要的库

import requests
import re

2. 获取搜索页面HTML代码

def getHTMLText(url):
    try:
        r = requests.get(url, timeout=30)
        r.raise_for_status()
        r.encoding = r.apparent_encoding
        return r.text
    except:
        return ""

3. 解析搜索页面HTML代码，获取商品列表

def parsePage(ilt, html):
    try:
        plt = re.findall(r'\"view_price\"\:\"[\d\.]*\"',html) # 商品价格
        tlt = re.findall(r'\"raw_title\"\:\".*?\"',html) # 商品名称
        for i in range(len(plt)):
            price = eval(plt[i].split(':')[1]) # 将价格字符串转为浮点数
            title = eval(tlt[i].split(':')[1]) # 将商品名称字符串转为Unicode编码
            ilt.append([price, title])
    except:
        print("")

def getGoodsList(keywords):
    goods = []
    depth = 2 # 爬取深度
    start_url = 'https://s.taobao.com/search?q=' + keywords
    for i in range(depth):
        try:
            url = start_url + '&s=' + str(44*i)
            html = getHTMLText(url)
            parsePage(goods, html)
        except:
            continue
    return goods

4. 输出商品列表

def printGoodsList(goods):
    tplt = "{:4}\t{:8}\t{:16}" # 表格模板
    print(tplt.format("序号", "价格", "商品名称"))
    count = 0
    for g in goods:
        count += 1
        print(tplt.format(count, g[0], g[1]))

5. 调用函数并输出结果

goods = getGoodsList('手机') # 搜索关键词为手机的商品
printGoodsList(goods)