Update 测绘站采集.py

py/测绘站采集.py

@@ -31,6 +31,35 @@ from bs4 import BeautifulSoup
 from urllib.parse import urlparse
 from translate import Translator  # 导入Translator类,用于文本翻译
 
+######################################################################################################################
+# 获取rtp目录下的文件名,组播IP采集
+files = os.listdir('rtp')
+files_name = []
+# 去除后缀名并保存至provinces_isps
+for file in files:
+    name, extension = os.path.splitext(file)
+    files_name.append(name)
+#忽略不符合要求的文件名
+provinces_isps = [name for name in files_name if name.count('_') == 1]
+print(f"本次查询：{provinces_isps}的组播节目") 
+keywords = []
+for province_isp in provinces_isps:
+    # 读取文件并删除空白行
+    try:
+        with open(f'rtp/{province_isp}.txt', 'r', encoding='utf-8') as file:
+            lines = file.readlines()
+            lines = [line.strip() for line in lines if line.strip()]
+        # 获取第二行中以包含 "rtp://" 的值作为 mcast
+        if lines:
+            first_line = lines[1]
+            if "rtp://" in first_line:
+                mcast = first_line.split("rtp://")[1].split(" ")[0]
+                keywords.append(province_isp + "_" + mcast)
+    except FileNotFoundError:
+    # 如果文件不存在,则捕获 FileNotFoundError 异常并打印提示信息
+        print(f"文件 '{province_isp}.txt' 不存在. 跳过此文件.")
+requested_urls = set()  # 用于记录已经请求过的地址
+parse_count = {}  # 用于记录每个 URL 的解析次数
 ######################################################################################################################
 # 获取rtp目录下的文件名,组播IP采集
 files = os.listdir('rtp')
@@ -62,8 +91,8 @@ requested_urls = set()  # 用于记录已经请求过的地址
 parse_count = {}  # 用于记录每个 URL 的解析次数
 for keyword in keywords:
     province, isp, mcast = keyword.split("_")
-    #将省份转成英文小写
-    # 根据不同的 isp 设置不同的 org 值
+    # 将省份转成英文小写
+    # 根据不同的isp设置不同的org值
     if province == "北京" and isp == "联通":
         isp_en = "cucc"
         org = "China Unicom Beijing Province NeTwork"
@@ -81,13 +110,13 @@ for keyword in keywords:
     timeout_cnt = 0
     result_urls = set()
     should_continue_while = True
-    while should_continue_while and len(result_urls) == 0 and timeout_cnt <= 5:
+    while should_continue_while and len(result_urls) == 0 and timeout_cnt <= 2:
         try:
             search_url = 'https://fofa.info/result?qbase64='
-            search_txt = f'\"udpxy\" && country=\"CN\" && region=\"{province}\"'  # && org=\"{org}\"
+            search_txt = f'"udpxy" && country="CN" && region="{province}"'  # && org="{org}"
             # 将字符串编码为字节流
             bytes_string = search_txt.encode('utf-8')
-            # 使用 base64 进行编码
+            # 使用base64进行编码
             search_txt = base64.b64encode(bytes_string).decode('utf-8')
             search_url += search_txt
             if search_url not in requested_urls:  # 仅当地址未被请求过时才进行请求
@@ -119,12 +148,9 @@ for keyword in keywords:
         except (requests.Timeout, requests.RequestException) as e:
             timeout_cnt += 1
             print(f"{current_time} [{province}]搜索请求发生超时,异常次数：{timeout_cnt}")
-            if timeout_cnt <= 5:
-                # 退出循环迭代
+            if timeout_cnt > 2:
+                print(f"{current_time} 搜索IPTV频道源[{province}{isp}],超时次数过多：{timeout_cnt} 次,停止处理")
                 break
-            else:
-                print(f"{current_time} 搜索IPTV频道源[],超时次数过多：{timeout_cnt} 次,停止处理")
-
 
     valid_ips = []
     # 遍历所有视频链接
@@ -147,26 +173,16 @@ for keyword in keywords:
             cap.release()
 
     if valid_ips:
-                #生成节目列表 省份运营商.txt
+        # 生成节目列表 省份运营商.txt
         rtp_filename = f'rtp/{province}_{isp}.txt'
+        txt_filename = f'playlist/{province}{isp}.txt'
         with open(rtp_filename, 'r', encoding='utf-8') as file:
             data = file.read()
-                txt_filename = f'playlist/{province}{isp}.txt'
-                with open(txt_filename, 'a') as new_file:  #以追加形式写入
+        with open(txt_filename, 'a') as new_file:  # 以追加形式写入
             for url in valid_ips:
                 new_data = data.replace("rtp://", f"{url}/rtp/")
                 new_file.write(new_data)
         print(f'已生成播放列表,保存至{txt_filename}')
-        except (requests.Timeout, requests.RequestException) as e:
-            timeout_cnt += 1
-            print(f"{current_time} [{province}]搜索请求发生超时,异常次数：{timeout_cnt}")
-            if timeout_cnt <= 5:
-                    # 退出循环迭代
-                break
-            else:
-                print(f"{current_time} 搜索IPTV频道源[],超时次数过多：{timeout_cnt} 次,停止处理")
-print('节目表制作完成！ 文件输出在playlist文件夹！')
-
 
 print('对playlist文件夹里面的所有txt文件进行去重处理')
 def remove_duplicates_keep_order(folder_path):