解决预处理中表格数据可能漏掉的问题以及标点符号没去干净的问题

BiddingKG/dl/interface/Preprocessing.py

@@ -688,7 +688,7 @@ def tableToText(soup):
                                     key_values = [1]
                                 if table_occurence[i-loop_i][j]["type"] in key_values:
                                     if find_flag:
-                                        if table_occurence[i-loop_i]["text"]!=temp_head:
+                                        if table_occurence[i-loop_i][j]["text"]!=temp_head:
                                             top_head = table_occurence[i-loop_i][j]["text"]+":"+top_head
                                     else:
                                         top_head = table_occurence[i-loop_i][j]["text"]+":"+top_head