python爬虫爬取壁纸

• • 导入用到的库
  • 目标网址
  • 利用正则表达式获取图片详情页的网址
  • 完整代码

import requests
import re
import time

for page in range(2, 140):  # 对网站多个网页进行爬取
    download_one_page('https://pic.netbian.com/4kdongman/index_' + str(page) + '.html')

 re_temp = '
  # 正则表达式匹配所需要的图片详情页连接

import requests
import re
import time


def download(url, name):
    time.sleep(2)  # 避免对服务器造成破坏
    resp = requests.get(url)
    resp.encoding = 'gbk'  # 网页编码格式
    suffix = url.split('.')[-1]
    name.replace(' ', '')
    address = "E:壁纸动漫壁纸" + "\" + name + '.' + suffix
    try:
        with open(address, 'wb') as file:
            file.write(resp.content)
    except:
        print('下载错误：', name)


def download_next_one_page(url):
    time.sleep(2)
    response = requests.get(url)
    response.encoding = 'gbk'
    re_temp = ''
    result = re.findall(re_temp, response.text)

    download('https://pic.netbian.com' + result[0][0], result[0][2])


def download_one_page(one_page_url):
    time.sleep(1)
    response = requests.get(one_page_url)
    response.encoding = 'gbk'  # 网站编码
    re_temp = '
  # 正则表达式匹配所需要的图片详情页连接
    result = re.findall(re_temp, response.text)
    for i in result:
        download_next_one_page('https://pic.netbian.com' + i)  # name url


for page in range(2, 140):  # 对网站多个网页进行爬取
    download_one_page('https://pic.netbian.com/4kdongman/index_' + str(page) + '.html')

仅用作技术交流和分享，请勿对网站进行破坏，要有逼格！