重写了connect通信程序与服务器通信系统，彻底重写了终端节点集群，对整个系统进行了较大幅度的优化,优化集群为多进程，增加轮询间隔,小优化

dcs/clients/client.py

@@ -115,7 +115,16 @@ class Client(multiprocessing.Process):
 
                 if request_map['type'] == 'request':
                     logger.info("[REQUEST] receiving help request: " + json.dumps(request_map, ensure_ascii=False))
+                    try:
                         response_map = crawl(request_map)
+                    except Exception as e:
+                        logger.error(f'[Error] {e.__class__.__name__}: {str(e)}')
+                        try:
+                            response_map = crawl(request_map)
+                        except Exception as e:
+                            logger.error(f'[Error] {e.__class__.__name__}: {str(e)}')
+                            # 爬取失败
+                            response_map = {'0': {'name': None, 'college': None, 'major': None, 'title': None}, 'failed_task': {request_map}, 'success': False}
                     response_map.update({'cookie': request_map['cookie']})
                     client_socket.sendall(generate_response(response_map))
                     logger.info(f'[RESPONSE] sending client result {response_map}...')
@@ -132,7 +141,7 @@ class Client(multiprocessing.Process):
 
                     break
             except Exception as e:
-                logger.error(str(e))
+                logger.error(f'[Error] {e.__class__.__name__}: {str(e)}')
 
 
 if __name__ == '__main__':

dcs/tests/spider_task.py

@@ -1,3 +1,5 @@
+import csv
+import random
 import socket
 import threading
 from typing import Optional
@@ -189,6 +191,7 @@ class Spider_task(threading.Thread):
                 if task.is_partial_task_crawl_completely():
                     continue
                 else:
+                    random.shuffle(free_remote_nodes)
                     current_task_thread = task.thread
                     if current_task_thread is None:
                         for f_node in free_remote_nodes:

dcs/tests/zhiwang.py

@@ -1,14 +1,11 @@
 # 知网论文数据爬取
-import csv
 
-from bs4 import BeautifulSoup
 import time
-import requests
 
+import requests
+from bs4 import BeautifulSoup
 # 定义论文类
 from loguru import logger
-from msedge.selenium_tools import webdriver
-from msedge.selenium_tools.service import Service
 from selenium.webdriver.common.by import By
 
 
@@ -39,7 +36,7 @@ def driver_open(driver, key_word):
     # 点击搜索按钮
     driver.find_element(by=By.CSS_SELECTOR,
                         value='body > div.wrapper.section1 > div.searchmain > div > div.input-box > input.search-btn').click()
-    time.sleep(1)  # 必须要等待
+    time.sleep(1.5)  # 必须要等待
     content = driver.page_source.encode('utf-8')
     # driver.close()
     soup = BeautifulSoup(content, 'lxml')