彼岸图网抓取，不封ip

url： http://pic.netbian.com/4kfengjing/index_2.html

import requests
from lxml import etree
import os
from urllib import request
headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.142 Safari/537.36'
}

# url = 'http://pic.netbian.com/4kfengjing/'
# url = 'http://pic.netbian.com/4kfengjing/index_%d.html'
if not os.path.exists('./fengjing'):
    os.mkdir('./fengjing')

start_page = int(input('start page num:'))
end_page = int(input('end page num:'))

url = 'http://pic.netbian.com/4kfengjing/index_%d.html'

for page in range(start_page, end_page + 1):
    if start_page == 1:
        new_url = 'http://pic.netbian.com/4kfengjing/'
    else:
        new_url = format(url%page)
    page_text = requests.get(url=new_url, headers=headers).text
    # print(page_text)
    tree = etree.HTML(page_text)
    li_list = tree.xpath('//div[@class="slist"]/ul/li')
    for li in li_list:
        img_name = li.xpath('./a/img/@alt')[0]
    #     encode('iso-8859-1').decode('gbk')
        img_name = img_name.encode('iso-8859-1').decode('gbk')+'.jpg'
        img_src = 'http://pic.netbian.com'+li.xpath('./a/img/@src')[0]
    #     print(img_name,img_src)
        img_path = './fengjing/'+img_name
        request.urlretrieve(img_src,img_path)
        print(img_name,'下载成功！！）