base

base_file.py

@@ -0,0 +1,95 @@
+#coding:utf-8
+
+import os
+import json
+import re
+
+
+# 扫描件-投标文件
+HEADERS = set({'序号', '项目编码', '项目名称', '项目特征', '单位', '工程量', '全费用综合单价', '合价', '备注', '主材名称', '规格型号', '不低于下列同档次品牌', '投标选用品牌及规格型号', '名称', '事项', '数量', '含税单价（元）', '含税合价（元）', '条款号', '评分因素', '评分标准', '页码'})
+
+
+def is_title(line: str) -> bool:
+    title_word = re.findall('^[（\(][一二三四五六七八九十]+[\)）]|^\d\.|^1\d\.|^2\d\.|^[第][一二三四五六七八九十\d]+[章节条]|[一二三四五六七八九十]+[、要是]', line.strip())
+    if title_word:
+        return True
+    title_word = re.findall('^附录|^参考文献|^附表', line.strip())
+    if title_word:
+        return True
+    return False
+
+lines = open('三峡左岸地坪商务标_合并_ocr.txt', 'r', encoding='utf-8').read()
+# lines = open('data_1.json', 'r', encoding='utf-8').read()
+json_line = json.loads(lines)
+print(json_line.keys())
+para_nodes = json_line['para_nodes']
+table_flag = 0
+contents = ""
+for i in range(len(para_nodes)):
+    # '评审因素'
+    # ''
+    if para_nodes[i]['node_type'] == 'contents':
+        contents = para_nodes[i]['text']
+        break
+
+contents = re.sub('[\.\d]+', '', contents)
+table_flag = 0
+title_list = []
+char_hight = 13
+_index = 0
+page_num = -1
+for i in range(len(para_nodes)):    
+    # if not para_nodes[i]['node_type'] in ["contents",'table', 'text', 'head_tail']:
+    #     print(para_nodes[i])
+    if i < table_flag:
+        continue
+    if not para_nodes[i]['position']:
+        continue
+    if para_nodes[i]['position'][0]['pageno'] != page_num:
+        page_num = para_nodes[i]['position'][0]['pageno']
+        _index = 0
+    if para_nodes[i]['position'][0]['pageno'] == page_num:
+        # page_num = para_nodes[i]['position'][0]['pageno']
+        _index = _index + 1
+    # para_nodes[i]['position'][0]['pageno']
+    
+    if para_nodes[i]['node_type'] == 'title' and para_nodes[i]['position'][0]['box'][-1]:
+        title_list.append((para_nodes[i]['text'], para_nodes[i]['position'][0]['pageno']))
+    elif _index < 3 and is_title(para_nodes[i]['text']) and len(para_nodes[i]['text']) < 20:
+        title_list.append((para_nodes[i]['text'], para_nodes[i]['position'][0]['pageno']))
+        # print(para_nodes[i]['text'])
+    if para_nodes[i]['node_type'] == 'seal':  #印章
+        print(para_nodes[i])
+    # if len(para_nodes[i]['text']) > 5 and para_nodes[i]['text'] in contents and para_nodes[i]['position'][0]['box'][-1] >= char_hight:
+    #     print(para_nodes[i]['text'])
+    if para_nodes[i]['node_type'] != 'table' and ('报价汇总表' in para_nodes[i]['text'] or '分项报价表' in para_nodes[i]['text'] or '工程量清单报价表' in para_nodes[i]['text'] or '报价明细表' in para_nodes[i]['text']):
+        flag_word = re.findall('报价汇总表|分项报价表|工程量清单报价表|报价明细表', para_nodes[i]['text'])[0]
+        position_page_id = para_nodes[i]['position'][0]['pageno']
+        for j in range(i, len(para_nodes)):
+            if para_nodes[j]['para_type'] != 'table' and position_page_id + 2 < para_nodes[j]['position'][0]['pageno']:
+                break
+            if para_nodes[i]['position'][0]['pageno'] - position_page_id < 2:
+                # print(position_page_id)
+                position_page_id = para_nodes[i]['position'][0]['pageno']
+        
+        # print(i, j)
+        lines = ""
+        for k in range(i, j+1):
+            if para_nodes[k]['node_type'] != 'table':
+                word_flag = re.findall('报价汇总表|分项报价表|工程量清单报价表|报价明细表|安全文明措施', para_nodes[k]['text'])
+            # print(word_flag, flag_word)
+            table_flag = k
+            if word_flag and word_flag[0] != flag_word:
+                break
+            if para_nodes[k]['para_type'] != 'table':
+                # print(para_nodes[k]['text'])
+                continue
+            lines = lines + para_nodes[k]['text']
+        print(para_nodes[i]['text'], 'xxxxxxxxxx', lines)
+
+# file_content = json_line['para_nodes']
+# for y in range(len(file_content[10:20])):
+#     print(file_content[y])
+
+print(title_list)
+print(contents)