爬取bian图网的图片

将下列代码复制粘贴到一个.py文件里运行就会在py文件同级目录下生成4k图片的文件夹存放下载的图片

import requests
from bs4 import BeautifulSoup
import time
import os

if not os.path.exists('./4k图片/'):
    os.mkdir('./4k图片/')

'''
彼岸图库 4k图片
第一页 https://pic.netbian.com/4kmeinv/index.html
第二页 https://pic.netbian.com/4kmeinv/index_2.html
第三页 https://pic.netbian.com/4kmeinv/index_3.html
'''
headers = {
    'cookie': '__yjs_duid=1_609256ccf97c86f63356e4e9f3fa5eb21654735480955; Hm_lvt_c59f2e992a863c2744e1ba985abaea6c=1654735481; zkhanecookieclassrecord=%2C65%2C59%2C66%2C54%2C53%2C55%2C; PHPSESSID=25p1pnl1nog1nn56lic0j2fga6; zkhanmlusername=qq803835154342; zkhanmluserid=826128; zkhanmlgroupid=3; zkhanmlrnd=VQOfLNvHK33WGXiln7nY; zkhanmlauth=264643c01db497a277bbf935b54aa3f3; Hm_lpvt_c59f2e992a863c2744e1ba985abaea6c=1654741154'
}
page = list(map(int,input('请输入要爬取的页数：').strip().split())) # 从page[0]到page[1]页爬虫,for e.g. input: 9 100
for i in range(page[0],page[1]):
    if i == 1:
        index = 'index'
    else:
        index = f'index_{i+1}'
    theme_url = f'https://pic.netbian.com/4kmeinv/{index}.html' # 要爬取主题的url
    response = requests.get(theme_url)
    response.encoding = 'gbk'
    main_page = BeautifulSoup(response.text,features="lxml")
    li_all_a = main_page.find('div',class_='slist').find_all('a') # li标签下所有的a标签

    if not os.path.exists('./4k图片/第{}页'.format(i)):
        os.mkdir('./4k图片/第{}页/'.format(i))

    for a in li_all_a:
        href = a.get('href')
        picture_num = href[8:13]
        picture_name = a.find('b').string
        down_url = f'https://pic.netbian.com/downpic.php?id={picture_num}&classid=54' # 子页面中的下载地址
        down_response = requests.get(down_url,headers=headers)
        with open(f'4k图片/'+'第{}页/'.format(i)+picture_name+'.jpg',mode='wb') as f:
            f.write(down_response.content) # 图片内容写入文件
        print('正在保存',picture_name+'.jpg')
        time.sleep(1)
    response.close()
print('程序运行完毕')

标签：index,图网,netbian,bian,response,爬取,4k,page,图片
来源： https://www.cnblogs.com/chuqianyu/p/16488955.html