Create 源验证.py

This commit is contained in:
frxz751113
2024-08-15 15:12:28 +08:00
committed by GitHub
parent bc92b7a812
commit 1131312ec0
+147
View File
@@ -0,0 +1,147 @@
import time
import concurrent.futures
from selenium import webdriver
from selenium.webdriver.chrome.options import Options
from concurrent.futures import ThreadPoolExecutor
import requests
import re
import os
import threading
from queue import Queue
import queue
from datetime import datetime
import replace
import fileinput
from tqdm import tqdm
from pypinyin import lazy_pinyin
from opencc import OpenCC
import base64
import cv2
from bs4 import BeautifulSoup
from urllib.parse import urlparse
from translate import Translator
url = "https://raw.githubusercontent.com/frxz751113/collect-tv-txt/main/merged_output.txt" #源采集地址
r = requests.get(url)
open('源.txt','wb').write(r.content)
#################################################### 对整理好的频道列表测试HTTP连接
def test_connectivity(url, max_attempts=1): #定义测试HTTP连接的次数
# 尝试连接指定次数
for _ in range(max_attempts):
try:
response = requests.head(url, timeout=3) # 发送HEAD请求,仅支持V4,修改此行数字可定义链接超时##////////////////////////////////////////////////////////////////////////////////////////////////////////////////
#response = requests.get(url, timeout=1) # 发送get请求,支持V6,修改此行数字可定义链接超时##############################//////////////////////////////////////////////////////////////////////////////////////
return response.status_code == 200 # 返回True如果状态码为200
except requests.RequestException: # 捕获requests引发的异常
pass # 发生异常时忽略
#return False # 如果所有尝试都失败,返回False
pass
# 使用队列来收集结果的函数
def process_line(line, result_queue):
parts = line.strip().split(",") # 去除行首尾空白并按逗号分割
if len(parts) == 2 and parts[1]: # 确保有URL,并且URL不为空
channel_name, channel_url = parts # 分别赋值频道名称和URL
if test_connectivity(channel_url): # 测试URL是否有效
result_queue.put((channel_name, channel_url, "有效")) # 将结果放入队列
else:
result_queue.put((channel_name, channel_url, "无效")) # 将结果放入队列
else:
# 格式不正确的行不放入队列
pass
# 主函数
def main(source_file_path, output_file_path):
with open(source_file_path, "r", encoding="utf-8") as source_file: # 打开源文件
lines = source_file.readlines() # 读取所有行s
result_queue = queue.Queue() # 创建队列
threads = [] # 初始化线程列表
for line in tqdm(lines, desc="检测进行中"): # 显示进度条
thread = threading.Thread(target=process_line, args=(line, result_queue)) # 创建线程
thread.start() # 启动线程
threads.append(thread) # 将线程加入线程列表
for thread in threads: # 等待所有线程完成
thread.join()
# 初始化计数器
valid_count = 0
invalid_count = 0
with open(output_file_path, "w", encoding="utf-8") as output_file: # 打开输出文件
for _ in range(result_queue.qsize()): # 使用队列的大小来循环
item = result_queue.get() # 获取队列中的项目
# 只有在队列中存在有效的项目时才写入文件
if item[0] and item[1]: # 确保channel_name和channel_url都不为None
output_file.write(f"{item[0]},{item[1]},{item[2]}\n") # 写入文件
if item[2] == "有效": # 统计有效源数量
valid_count += 1
else: # 统计无效源数量
invalid_count += 1
print(f"任务完成, 有效源数量: {valid_count}, 无效源数量: {invalid_count}") # 打印结果
if __name__ == "__main__":
try:
source_file_path = "源.txt" # 输入源文件路径
output_file_path = "源.txt" # 设置输出文件路径
main(source_file_path, output_file_path) # 调用main函数
except Exception as e:
print(f"程序发生错误: {e}") # 打印错误信息
# 初始化酒店源字典
detected_ips = {}
# 存储文件路径
file_path = "源.txt"
output_file_path = "优选.txt"
def get_ip_key(url):
"""从URL中提取IP地址,并构造一个唯一的键"""
# 找到'//'到第三个'.'之间的字符串
start = url.find('://') + 3 # '://'.length 是 3
end = start
dot_count = 0
while dot_count < 3:
end = url.find('.', end)
if end == -1: # 如果没有找到第三个'.',就结束
break
dot_count += 1
return url[start:end] if dot_count == 3 else None
# 打开输入文件和输出文件
with open(file_path, 'r', encoding='utf-8') as file:
lines = file.readlines()
# 获取总行数用于进度条
total_lines = len(lines)
# 写入通过检测的行到新文件
with open(output_file_path, 'w', encoding='utf-8') as output_file:
# 使用tqdm显示进度条
for i, line in tqdm(enumerate(lines), total=total_lines, desc="Processing", unit='line'):
# 检查是否包含 'genre'
if 'genre' in line:
output_file.write(line)
continue
# 分割频道名称和URL,并去除空白字符
parts = line.split(',', 1)
if len(parts) == 2:
channel_name, url = parts
channel_name = channel_name.strip()
url = url.strip()
# 构造IP键
ip_key = get_ip_key(url)
if ip_key and ip_key in detected_ips:
# 如果IP键已存在,根据之前的结果决定是否写入新文件
if detected_ips[ip_key]['status'] == 'ok':
output_file.write(line)
elif ip_key: # 新IP键,进行检测
# 进行检测
cap = cv2.VideoCapture(url)
start_time = time.time()
frame_count = 0
# 尝试捕获5秒内的帧
while frame_count < 66 and (time.time() - start_time) < 3:#//////////////////////////////////////////////////////////////////////////////////////###########
ret, frame = cap.read()
if not ret:
break
frame_count += 1
# 释放资源
cap.release()
# 根据捕获的帧数判断状态并记录结果#////////////////////////////////////////////////////////////////////////////////////////////////////////////////###########
if frame_count >= 66: #5秒内超过100帧则写入#/////////////////////////////////////////////////////////////////////////////////////////////////////###########
detected_ips[ip_key] = {'status': 'ok'}
output_file.write(line) # 写入检测通过的行
else:
detected_ips[ip_key] = {'status': 'fail'}
# 打印酒店源
for ip_key, result in detected_ips.items():
print(f"IP Key: {ip_key}, Status: {result['status']}")