python3爬取全站美眉图片

爬取网站：https://www.169tp.com/xingganmeinv

该网站美眉图片有数百页，每页24张，共上万张图片,全部爬取下来

import urllib.request
import re
import os
from bs4 import BeautifulSoup

page_flag = 0
base_url = "https://www.169tp.com/xingganmeinv/"
first_url ="https://www.169tp.com/xingganmeinv/list_1_1.html"
Imgnums = 0

def get_html(url):
    response = urllib.request.urlopen(url)
    html = response.read().decode('gb18030')
    return html

def get_Imgurl_list(html):
    img_urllist = re.findall('src=["\']{1}(.+?\.jpg)["\']{1}', html)
    return img_urllist


def Download(img_urllist,page_flag,final_path,Imgnums):
    num = 1
    for imgurl in img_urllist:
        imgname = "{}{}{}{}.jpg".format(final_path,page_flag,'_',num)
        urllib.request.urlretrieve(imgurl,imgname)
        print("已经爬取图片名:",imgname)
        Imgnums += 1
        num += 1

def makedir(path):
    path = path.strip()
    isExists = os.path.exists(path)
    if not isExists:
        print("创建了路径为 ",path," 的文件夹")
        os.makedirs(path)
        return True
    else:
        print("路径为 ",path," 的文件夹已经存在")
        return False


filepath = input("请输入保持图片的文件夹路径:")
print(filepath)
name = input("请输入保存图片的文件夹名:")
print(name)
finalpath = filepath + name
makedir(finalpath)
finalpath += '\\'
print(f"图片保存路径: {finalpath}")

Download(get_Imgurl_list(first_url),page_flag,finalpath,Imgnums)
mysoup = BeautifulSoup(get_html(first_url),'html.parser')
next_page = mysoup.find('div',attrs = {'class':'page'}).find('li',text = '下一页').find('a')
while next_page:
    new_url = base_url + next_page['href']
    page_flag += 1
    Download(get_Imgurl_list(get_html(new_url)),page_flag,finalpath,Imgnums)
    mysoup = BeautifulSoup(get_html(new_url),'html.parser')
    next_page = mysoup.find('div',attrs = {'class':'page'}).find('li',text = '下一页').find('a')
print(f"下载完成,共下载了 {Imgnums} 张图片!")

运行截图:

图片名命名规则:存储路径+页码+下划线+图片号+.jpg

图片文件夹截图: