这是一个使用Python编写的Ivsky网站图片爬虫程序，通过BeautifulSoup解析HTML，获取图片列表并下载高清图片，同时根据分类创建文件夹保存图片。
# -*- coding:utf-8 -*-
from urllib import request
from bs4 import BeautifulSoup
import os
class IvskySpider(object):
def __init__(self):
self.url = 'http://www.ivsky.com'
self.headers = {
'User-Agent':'Mozilla/5.0 (Windows NT 6.1; WOW64; rv:52.0) Gecko/20100101 Firefox/52.0',
'Host':"www.ivsky.com"
}
self.html = ''
# 请求函数
def get_html(self,url):
req = request.Request(url,headers=self.headers)
response = request.urlopen(req)
self.html = response.read().decode('utf-8')
# 解析列表页函数
def parse_list(self):
# 创建bs对象
bs = BeautifulSoup(self.html,'lxml')
res
from urllib import request
from bs4 import BeautifulSoup
import os
class IvskySpider(object):
def __init__(self):
self.url = 'http://www.ivsky.com'
self.headers = {
'User-Agent':'Mozilla/5.0 (Windows NT 6.1; WOW64; rv:52.0) Gecko/20100101 Firefox/52.0',
'Host':"www.ivsky.com"
}
self.html = ''
# 请求函数
def get_html(self,url):
req = request.Request(url,headers=self.headers)
response = request.urlopen(req)
self.html = response.read().decode('utf-8')
# 解析列表页函数
def parse_list(self):
# 创建bs对象
bs = BeautifulSoup(self.html,'lxml')
res
最低0.47元/天 解锁文章
扫一扫
1万+
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
