160 lines
5.0 KiB
Python
160 lines
5.0 KiB
Python
# coding=utf-8
|
|
# !/usr/bin/python
|
|
|
|
"""
|
|
|
|
作者 丢丢喵推荐 🚓 内容均从互联网收集而来 仅供交流学习使用 版权归原创者所有 如侵犯了您的权益 请通知作者 将及时删除侵权内容
|
|
====================Diudiumiao====================
|
|
|
|
"""
|
|
|
|
from Crypto.Util.Padding import unpad
|
|
from Crypto.Util.Padding import pad
|
|
from urllib.parse import unquote
|
|
from Crypto.Cipher import ARC4
|
|
from urllib.parse import quote
|
|
from base.spider import Spider
|
|
from Crypto.Cipher import AES
|
|
from datetime import datetime
|
|
from bs4 import BeautifulSoup
|
|
from base64 import b64decode
|
|
import urllib.request
|
|
import urllib.parse
|
|
import datetime
|
|
import binascii
|
|
import requests
|
|
import base64
|
|
import json
|
|
import time
|
|
import sys
|
|
import re
|
|
import os
|
|
|
|
sys.path.append('..')
|
|
|
|
xurl = "https://www.4kvm.net"
|
|
|
|
headerx = {
|
|
'User-Agent': 'Mozilla/5.0 (Linux; U; Android 8.0.0; zh-cn; Mi Note 2 Build/OPR1.170623.032) AppleWebKit/537.36 (KHTML, like Gecko) Version/4.0 Chrome/61.0.3163.128 Mobile Safari/537.36 XiaoMi/MiuiBrowser/10.1.1'
|
|
}
|
|
|
|
class Spider(Spider):
|
|
global xurl
|
|
global headerx
|
|
|
|
def getName(self):
|
|
return "首页"
|
|
|
|
def init(self, extend):
|
|
pass
|
|
|
|
def isVideoFormat(self, url):
|
|
pass
|
|
|
|
def manualVideoCheck(self):
|
|
pass
|
|
|
|
def extract_middle_text(self, text, start_str, end_str, pl, start_index1: str = '', end_index2: str = ''):
|
|
if pl == 3:
|
|
plx = []
|
|
while True:
|
|
start_index = text.find(start_str)
|
|
if start_index == -1:
|
|
break
|
|
end_index = text.find(end_str, start_index + len(start_str))
|
|
if end_index == -1:
|
|
break
|
|
middle_text = text[start_index + len(start_str):end_index]
|
|
plx.append(middle_text)
|
|
text = text.replace(start_str + middle_text + end_str, '')
|
|
if len(plx) > 0:
|
|
purl = ''
|
|
for i in range(len(plx)):
|
|
matches = re.findall(start_index1, plx[i])
|
|
output = ""
|
|
for match in matches:
|
|
match3 = re.search(r'(?:^|[^0-9])(\d+)(?:[^0-9]|$)', match[1])
|
|
if match3:
|
|
number = match3.group(1)
|
|
else:
|
|
number = 0
|
|
if 'http' not in match[0]:
|
|
output += f"#{match[1]}${number}{xurl}{match[0]}"
|
|
else:
|
|
output += f"#{match[1]}${number}{match[0]}"
|
|
output = output[1:]
|
|
purl = purl + output + "$$$"
|
|
purl = purl[:-3]
|
|
return purl
|
|
else:
|
|
return ""
|
|
else:
|
|
start_index = text.find(start_str)
|
|
if start_index == -1:
|
|
return ""
|
|
end_index = text.find(end_str, start_index + len(start_str))
|
|
if end_index == -1:
|
|
return ""
|
|
|
|
if pl == 0:
|
|
middle_text = text[start_index + len(start_str):end_index]
|
|
return middle_text.replace("\\", "")
|
|
|
|
if pl == 1:
|
|
middle_text = text[start_index + len(start_str):end_index]
|
|
matches = re.findall(start_index1, middle_text)
|
|
if matches:
|
|
jg = ' '.join(matches)
|
|
return jg
|
|
|
|
if pl == 2:
|
|
middle_text = text[start_index + len(start_str):end_index]
|
|
matches = re.findall(start_index1, middle_text)
|
|
if matches:
|
|
new_list = [f'{item}' for item in matches]
|
|
jg = '$$$'.join(new_list)
|
|
return jg
|
|
|
|
def homeContent(self, filter):
|
|
result = {"class": []}
|
|
|
|
detail = requests.get(url=xurl, headers=headerx)
|
|
detail.encoding = "utf-8"
|
|
res = detail.text
|
|
doc = BeautifulSoup(res, "lxml")
|
|
soups = doc.find_all('ul', class_="main-header")
|
|
|
|
for soup in soups:
|
|
vods = soup.find_all('li')
|
|
|
|
for vod in vods:
|
|
|
|
name = vod.text.strip()
|
|
|
|
if any(keyword in name for keyword in ["首页", "电视剧", "高分电影", "影片下载", "热门播放"]):
|
|
continue
|
|
|
|
id = vod.find('a')['href']
|
|
if 'http' not in id:
|
|
id = xurl + id
|
|
|
|
result["class"].append({"type_id": id, "type_name": name})
|
|
|
|
return result
|
|
|
|
def homeVideoContent(self):
|
|
videos = []
|
|
|
|
detail = requests.get(url=xurl, headers=headerx)
|
|
detail.encoding = "utf-8"
|
|
res = detail.text
|
|
doc = BeautifulSoup(res, "lxml")
|
|
|
|
soups = doc.find_all('article', class_="item movies")
|
|
|
|
for vod in soups:
|
|
|
|
name = vod.find('img')['alt']
|
|
|
|
ids = vod.find('div', class_="poster")
|
|
id = ids.find(' |