python爬虫-抓取阿里巴巴商品图片

版本 1.0

import requests
from lxml import etree


url = "商品地址"
# 防反爬
headers = {"user-agent": "请求头的信息",
           "cookie":"这个必须要有，页面如果没有登陆会被要求输入验证码"
           }

pageSource = requests.get(url, headers=headers).text
pageHtml = etree.HTML(pageSource)

# 获取主图的大图地址
imgSrc = pageHtml.xpath("//a[@class='box-img']/@href")[1]

imgSource = requests.get(imgSrc, headers=headers)

imgHtml = etree.HTML(imgSource.text)

imgList = imgHtml.xpath("//a[@class='box-img']/img/@src")
j = 1
for i in imgList:
　　# 逐一获取主图，下载
    img = requests.get(i, headers=headers)

    with open(f"{j}.jpg", mode="wb") as w:
        w.write(img.content)
        j += 1