# coding=utf-8
import requests
from lxml import etree
import os
import time
# 导入线程池包
from concurrent.futures import ProcessPoolExecutor
import random
"""
这里我们直接爬取P站图片内容。排行榜原始地址
https://i.pximg.net/ c/240x480 /img-master/img/2021/04/14/00/00/04/89135748_p0_master1200.jpg
高清图原始地址
https://i.pximg.net/ img-master/img/2021/04/14/00/00/04/89135748_p0_master1200.jpg
页码XHR
https://www.pixiv.net/ranking.php?p=2&format=json
"""def get_content(url=None, s_type=None, name=None):headers = {"User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/89.0.4389.128 Safari/537.36 Edg/89.0.774.77","referer":"https://www.pixiv.net/ranking.php?mode=daily&content=illust"}session = requests.Session()response = session.get(url=url, headers=headers)多进程爬取P站图片
# coding=utf-8import requestsfrom lxml import etreeimport osimport time# 导入
版权声明
本文来自互联网用户投稿，文章观点仅代表作者本人，不代表本站立场。本站仅提供信息存储空间服务，不拥有所有权，不承担相关法律责任。如若转载，请注明出处。如若内容有涉嫌抄袭侵权/违法违规/事实不符，请点击 举报 进行投诉反馈！