sanxa_alg/base_file.py

#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)