From 97fccbd60478358b72812d0346da049f095161b0 Mon Sep 17 00:00:00 2001 From: aiyingfeng Date: Wed, 2 Aug 2023 16:17:26 +0800 Subject: [PATCH] =?UTF-8?q?=E6=8F=90=E5=8F=96pdf=E6=96=87=E4=BB=B6?= =?UTF-8?q?=E4=B8=AD=E5=9B=BE=E7=89=87=E5=92=8C=E6=96=87=E5=AD=97?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit --- pdf处理/program/pdf_base.py | 2 +- pdf处理/program/testing_agency_report.py | 5 +++-- 2 files changed, 4 insertions(+), 3 deletions(-) diff --git a/pdf处理/program/pdf_base.py b/pdf处理/program/pdf_base.py index 0934d26..5afcf68 100644 --- a/pdf处理/program/pdf_base.py +++ b/pdf处理/program/pdf_base.py @@ -1,5 +1,5 @@ from datetime import datetime -from extract_from_pages import read_pdf +from program.extract_from_pages import read_pdf from base import Base from PIL import Image import pandas as pd diff --git a/pdf处理/program/testing_agency_report.py b/pdf处理/program/testing_agency_report.py index 7cf92d7..a7eac7d 100644 --- a/pdf处理/program/testing_agency_report.py +++ b/pdf处理/program/testing_agency_report.py @@ -29,7 +29,8 @@ class TestingAgencyReport(PDFBase): valid_time_list = [] for line in lines: if 'S$T' in line or 'SST' in line: - text_dict['方案编号'] = line.replace('S$T', 'SST').replace('试验方案编号:', '') + text_dict['方案编号'] = line.replace('S$T', 'SST')\ + .replace('试验方案编号:', '').replace('$', '') if 'CNAS' in line: text_dict['标志'] = 'cnas中文,' valid_time = self.is_valid_time(line) @@ -65,7 +66,7 @@ class TestingAgencyReport(PDFBase): if 'CSTBB' in line: for li in line.split(): if 'CSTBB' in li: - self.xlsx_keys['报告编号'] = li.strip().replace('报告编号：', '') + self.xlsx_keys['报告编号'] = li.strip().replace('报告编号：', '').replace('）', '') if '样品名称' in line: try: self.xlsx_keys['样品名称'] = line.split()[1].strip().replace(': ', '')