python

#!/usr/bin/python3

# -*- coding: UTF-8 -*-

 

import urllib

from urllib.parse import urlencode

from urllib.request import Request, urlopen

import re

import time

import os

 

times = 0

def download_pic(pic_url,root_url,down_times):

url = pic_url

Referer = root_url

down_time = down_times

headers = {

'User-Agent':'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/83.0.4103.61 Safari/537.36',

'Referer':Referer

}

down_path = str(down_time)+'.jpg'

print (down_path)

requests = Request(url, headers=headers)

data = urlopen(requests).read()

with open(down_path, 'wb') as f:

f.write(data)

f.close()

down_time+=1

return down_time

def jiexi_rootPic_url(next_rootUrl,down_times):

url = next_rootUrl

headers = {

'User-Agent':'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/83.0.4103.61 Safari/537.36'

}

downtime = down_times

request_url = Request(url, headers=headers)

response = urlopen(request_url).read().decode("utf-8")

pattern = re.compile('<img src="(.*?)"', re.IGNORECASE)

pic_path = pattern.findall(response)

for i in pic_path:

print ('download_prepare')

downtime = download_pic(i,url,downtime)

time.sleep(2)

print(i)

return downtime

def jiexi_url(root_url,down_times):

headers = {

'User-Agent':'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/83.0.4103.61 Safari/537.36'

}

downtime = down_times

url = root_url

request_url = Request(url, headers=headers)

html = urlopen(request_url).read().decode("utf-8")

response = re.compile('/rnyy(.*?).html', re.IGNORECASE)

all_next_root = response.findall(html)

for i in all_next_root:

path = 'http://mmff30.com/rnyy'+i+'.html'

print (path)

# downtime = jiexi_rootPic_url(path,downtime)

jiexi_url('http://mmff30.com/rwmy_9_14.html',0)