python爬取整个网站js css 图片_Python爬取某网站的图片

Python爬取某网站的图片

import requests

from lxml import etree

import re

for i in range(1,100):

url = 'https://www.jdlingyu.mobi/'

headers = {

'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/78.0.3904.108 Safari/537.36'

}

data = {

'type': 'index',

'paged': i

}

response = requests.post(url=url , headers = headers,data=data)

soup = etree.HTML(response.text)

loarl = soup.xpath('//*[@id="main"]/div[2]/div')

for loarlroom in loarl:

ljie = loarlroom.xpath('div/div[1]/a/@href')[0]

jiexi = re.findall(r'https://www.jdlingyu.mobi/mzitu/(.*?.html)',ljie)

for mn in jiexi:

url1 = 'https://www.jdlingyu.mobi/mzitu/'+ str(mn)

headers = {

'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/78.0.3904.108 Safari/537.36'

}

response1 = requests.get(url=url1, headers=headers)

soup1 = etree.HTML(response1.text)

mntup = soup1.xpath('//*[@id="content-innerText"]/p/img/@src')

a = 0

for ii in mntup:

with open('j站图片\{}.jpg'.format(a), 'ab') as f:

download = requests.get(ii)

f.write(download.content)

a += 1

print("正在下载第{}张".format(a))

本文为我原创

--

--

--

分享到：

投诉或建议

评论