인프런 파일명 변경 테스트 for loop 병렬 처리

logic_inflearn.py

@@ -18,9 +18,10 @@ import asyncio
 from urllib.parse import urlparse
 import json
 
+
 import aiohttp
 
-packages = ["beautifulsoup4"]
+packages = ["beautifulsoup4", "joblib"]
 for package in packages:
     try:
         import package
@@ -31,6 +32,7 @@ for package in packages:
 
 # third-party
 import requests
+from joblib import Parallel, delayed
 from lxml import html, etree
 from bs4 import BeautifulSoup
 from urllib import parse
@@ -847,74 +849,20 @@ class LogicInflearn(object):
             #
             # logger.debug(f"ret_data():: ret_data=> {ret_data}")
 
-            for idx, item in enumerate(items):
+            temp1 = Parallel(n_jobs=4, prefer="threads")(
-                #
+                delayed(LogicInflearn.parsing_info)(
-                temp1 = {}
+                    item, idx, base_url, code, main_title, data
-                print("idx::", idx)
-                data_id = item["data-id"]
-
-                run_time = ""
-                title = item.find("div", attrs={"class": "title"}).get_text()
-                if item.find("span", {"class": "runtime"}) is not None:
-                    run_time = item.find("span", {"class": "runtime"}).get_text()
-                api_url = f"{base_url}/api/course/{code}/lecture/{data_id}"
-
-                temp1["season"] = "1"
-                LogicInflearn.season = "1"
-                # logger.debug(api_url)
-                m3u8_info = LogicInflearn.getM3u8_info(
-                    api_url, LogicInflearn.season, idx, main_title
                 )
-                # print(api_url)
+                for idx, item in enumerate(items)
-                # print('type::::', type(m3u8_url))
-                logger.debug(m3u8_info)
-                # ws.append(
-                #     [
-                #         title,
-                #         data_id,
-                #         run_time,
-                #         api_url,
-                #         m3u8_info["name"],
-                #         m3u8_info["hlsUrl"],
-                #     ]
-                # )
-
-                # temp.append(title, data_id, run_time, api_url,m3u8_info['name'], m3u8_info['hlsUrl'])
-                # temp1['title'] = title
-                temp1["save_folder"] = Util.change_text_for_use_filename(
-                    data["save_folder"]
             )
 
-                # logger.debug(temp1["save_folder"])
+            logger.debug(temp1)
 
-                tmp_save_path = ModelSetting.get("download_path")
-                if ModelSetting.get("auto_make_folder") == "True":
-                    program_path = os.path.join(tmp_save_path, temp1["save_folder"])
-                    temp1["save_path"] = program_path
-                    if ModelSetting.get("inflearn_auto_make_season_folder"):
-                        temp1["save_path"] = os.path.join(
-                            temp1["save_path"], "Season %s" % int(temp1["season"])
-                        )
-
-                temp1["title"] = title
-                temp1["data_id"] = data_id
-                temp1["item_id"] = m3u8_info["data_id"]
-                temp1["code"] = temp1["item_id"]
-                temp1["run_time"] = run_time
-                temp1["api_url"] = api_url
-                temp1["name"] = m3u8_info["name"]
-                temp1["filename"] = m3u8_info["filename"]
-                # logger.debug(temp1["name"])
-                # logger.debug(temp1["filename"])
-                temp1["url"] = m3u8_info["hlsUrl"]
-                # temp1["url"] = m3u8_info["hlsUrl"]
-                temp1["size"] = m3u8_info["size"]
             temp.append(temp1)
-
             # print(temp)
             # logger.info('data', data)
             # LogicInflearn.current_data = temp
-            data["episode"] = temp
+            data["episode"] = temp1
             LogicInflearn.current_data = data
             # logger.debug(data)
 
@@ -982,6 +930,62 @@ class LogicInflearn(object):
             "filename": filename,
         }
 
+    @staticmethod
+    def parsing_info(item, idx, base_url, code, main_title, data):
+
+        #
+        temp1 = {}
+        # print("idx::", idx)
+        data_id = item["data-id"]
+
+        run_time = ""
+        title = item.find("div", attrs={"class": "title"}).get_text()
+        if item.find("span", {"class": "runtime"}) is not None:
+            run_time = item.find("span", {"class": "runtime"}).get_text()
+
+        api_url = f"{base_url}/api/course/{code}/lecture/{data_id}"
+
+        temp1["season"] = "1"
+        LogicInflearn.season = "1"
+        # logger.debug(api_url)
+        m3u8_info = LogicInflearn.getM3u8_info(
+            api_url, LogicInflearn.season, idx, main_title
+        )
+        # print(api_url)
+        # print('type::::', type(m3u8_url))
+        logger.debug(m3u8_info)
+
+        # temp1['title'] = title
+        temp1["save_folder"] = Util.change_text_for_use_filename(data["save_folder"])
+
+        # logger.debug(temp1["save_folder"])
+
+        tmp_save_path = ModelSetting.get("download_path")
+        if ModelSetting.get("auto_make_folder") == "True":
+            program_path = os.path.join(tmp_save_path, temp1["save_folder"])
+            temp1["save_path"] = program_path
+            if ModelSetting.get("inflearn_auto_make_season_folder"):
+                temp1["save_path"] = os.path.join(
+                    temp1["save_path"], "Season %s" % int(temp1["season"])
+                )
+
+        temp1["title"] = title
+        temp1["data_id"] = data_id
+        temp1["item_id"] = m3u8_info["data_id"]
+        temp1["code"] = temp1["item_id"]
+        temp1["run_time"] = run_time
+        temp1["api_url"] = api_url
+        temp1["name"] = m3u8_info["name"]
+        temp1["filename"] = m3u8_info["filename"]
+        # logger.debug(temp1["name"])
+        # logger.debug(temp1["filename"])
+        temp1["url"] = m3u8_info["hlsUrl"]
+        # temp1["url"] = m3u8_info["hlsUrl"]
+        temp1["size"] = m3u8_info["size"]
+
+        # temp.append(temp1)
+        return temp1
+
     @staticmethod
     def getHtml(url, header):
         o = parse.urlparse(url)