使用python抓取某某图库的单线程写法

最新推荐文章于 2024-07-20 17:12:48 发布

予倾

最新推荐文章于 2024-07-20 17:12:48 发布

阅读量77

点赞数

分类专栏： python 文章标签： python 开发语言

本文链接：https://blog.csdn.net/QZ9420/article/details/130764155

版权

python 专栏收录该内容

1 篇文章 0 订阅

订阅专栏

import requests
from lxml import etree
i = 1
while i < 1106:
    res = ''
    if i == 1:
        res = requests.get('https://pic.netbian.com/index.html')
    else:
        res = requests.get(f'https://pic.netbian.com/index_{i}.html')
    res.encoding = "gbk"
    et = etree.HTML(res.text)
    lis = et.xpath("//ul[@class='clearfix']/li")
    for li in lis:
        aia1 = li.xpath("./a/@href")
        aia2 = li.xpath("./a/@title")
        # print(f"{aia2[0]},https://pic.netbian.com{aia1[0]}")
        resChild = requests.get(f"https://pic.netbian.com{aia1[0]}")
        resChild.encoding = "gbk"
        et2 = etree.HTML(resChild.text)
        resChildNode = et2.xpath("//a[@id='img']")[0]
        FpicTitle = resChildNode.xpath("./img/@title")[0]
        FpicUrl = resChildNode.xpath("./img/@src")[0]
        # print(f"https://pic.netbian.com{FpicUrl[0]}")
        img_res = requests.get(f"https://pic.netbian.com{FpicUrl}")
        with open(f"./images/{FpicTitle}.jpg", mode="wb") as f:
            f.write(img_res.content)
            print(f"{FpicTitle}下载完毕！")
    i += 1