python获取网站图片_python获取网页端的图片

import requests

import re

from bs4 import BeautifulSoup

rp = r"

rgm = r"

path = r"./Picture/chengshilvyou"

url_base = "https://www.ivsky.com"

parmas = {

"User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/85.0.4183.102 Safari/537.36",

"Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.9",

"Connection":"keep-alive"

}

class Picture():

def getHtml(self):

html = requests.get(url,params=parmas).text

soup = BeautifulSoup(html,features="html.parser")

return soup

def getPic_lis(self,url):

'''获取首页图片的列表'''

html_soup = picture.getHtml()

pic_list = []

T_list= html_soup.find_all("div",class_=re.compile("il_img"))

for i in T_list:

pic = re.findall(rp,str(i))

pic_list.append(url_base + str(pic[0]).replace('"',""))

print("msgone"+str(pic_list))

return pic_list

def getImg_list(self):

'''从首页获取的图片列表中依次获取图片集列表'''

img_list = []

index_list = picture.getPic_lis(url)

for x in index_list:

html_img = requests.get(x,params=parmas).text

print("metend"+ str(html_img))

# soup_img = BeautifulSoup(html_img)

# I_list = soup_img.find_all("div",class_=re.compile("il_img"))

I_list = re.findall(rgm,html_img)

print("msg"+str(I_list))

for n in I_list:

# img_url = re.findall(rg,str(n))

img_list.append("https:" + str(n).strip('"'))

print("msg2"+str(img_list))

return img_list

def download(self,num):

imgs_url = picture.getImg_list()

m = 0

for img_url in imgs_url:

print('***** ' + str(m) + '.jpg *****' + ' Downloading...')

dir = path + str(num) + str(m) + '.jpg'

response = requests.get(img_url)

with open(dir,"wb") as file:

file.write(response.content)

print('***** ' + str(m) + '.jpg *****' + 'Done.')

m = m + 1

if __name__ == "__main__":

num = 1

while num < 101:

url = "https://www.ivsky.com/tupian/chengshilvyou/index_" + str(num) + ".html"

picture = Picture()

picture.getPic_lis(url)

picture.getImg_list()

picture.download(num)

num += 1

  • 0
    点赞
  • 0
    收藏
    觉得还不错? 一键收藏
  • 0
    评论
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值