某办公网站高清摄影图片爬取

zwj

[Python] 纯文本查看 复制代码

import os
import requests
import re

def soushu(zzbds,html):
    ab = re.compile(zzbds, re.S)
    zml = re.findall(ab, html)
    return zml
def openwangye0(url):
    headers = {
        'cookie':'auth_token=VPu9LKcXvbqKjlosWxOLRM2aCWq4BrdF_VwKuWW64Yjb5tB4l-AHDlYhn59T6Cix0z9Xh1t4PtirXCbkp4vzNA',
    }
    htl = requests.get(url,headers=headers,timeout=10)   
    return htl
url = 'https://www.tukuppt.com/peitu/p199/'
html = openwangye0(url).text
zzbds = 'pid="(.*?)" issc="." isfrom="."></span>\r\n    <a href=".*?" target="_blank"><img title="(.*?)"'
pagetpml = soushu(zzbds,html)
print(len(pagetpml),pagetpml)
a = 0
for i in pagetpml[a:]:
    url = f'https://www.tukuppt.com/index/down?pid={i[0]}'
    html = openwangye0(url)
    data = html.text
    zzbds = '"downurl":"(.*?)"'
    downurl = soushu(zzbds,data)
    print(data)
    downurl1 = re.sub('\\\\','',downurl[0])   
    data = openwangye0(downurl1).content   
    path = r'D:\xmbgtp'
    if not os.path.exists(path):
        os.mkdir(path)
    filname = os.path.join(path,f'{i[1]}.jpg')
    with open(filname,'wb') as f:
        f.write(data)
    print(f'{i[1]}下载完成')

duinieryan009

谢谢分享

mengzhisuoliu5

多谢楼主分享

2596

6666

跳跃蘑菇

支持楼主，谢谢分享。

telcom1981

谢谢分享！

mlj2003318

谢谢分享

zheng3021

Beau

感谢楼主分享！大牛有你更精彩！

笑东风丶

感谢大佬分享，大佬666666