爬取天堂图片网

点击网页到你想下载图片的网址

链接: 跳转.

按F12或者点击右键检查

获得图片地址

找到原图下载地址

链接: 跳转.

查看一下图片地址

再点击下面的查看原图

找到原图地址

话不多说,上代码

import requests
from lxml import etree
from pathlib import Path
#获取电脑桌面地址
path = Path.home()
path1 = str(path / 'Desktop/')

#图片主地址
#//img.ivsky.com/img/tupian/t/202104/08/gouzai.jpg

#图片主页面
url="https://www.ivsky.com/tupian/gouzai_v66492/"
#headers是用来防止被识别的
headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/50.0.2661.102 UBrowser/6.1.2107.204 Safari/537.36'}
iid=requests.get(url,headers=headers)
getid = etree.HTML(iid.text)
#获得所有的图片地址
allid=getid.xpath("//*[@class='left']/ul[1]/li/p[1]/a[1]/@href")
#拼接得到真正图片地址
for i in allid:
    ul="https://www.ivsky.com/"+i
    ulid= requests.get(ul, headers=headers)
    # 获得图片的图片地址
    getulid = etree.HTML(ulid.text)
    ullid = getulid.xpath("//*[@id='pic_con']/div[1]/img/@src")
    for i1 in ullid:
        uld="https:"+i1
        #得到网页图片地址
        # https://img-pre.ivsky.com/img/tupian/pre/202104/08/gouzai.jpg
        #查看原图的地址
        # https://img-picdown.ivsky.com/img/tupian/pic/202104/08/gouzai.jpg
        #替换
        ur=str(uld).replace("img-pre",'img-picdown').replace("pre","pic")
        #获得末尾
        last=str(uld).split("/")[-1]
        down = requests.get(ur, headers=headers)
        with open(path1 + "\\"+last, "wb")as f:
            f.write(down.content)
    #一秒延迟下载
    import time
    time.sleep(1)