interpreter = PDFPageInterpreter(rsrcmgr, device)
for page in PDFPage.create_pages(doc):
interpreter.process_page(page)
return output_string.getvalue()
# root_path = os.path.normpath("J:/32_IZ224_SIEMENS_Herne/60_Construction/10_Sx_Input/30_Sx_Project_Documentation/10_Mechanical_Engineering_Project/40_Piping_Iso")
root_path = os.path.normpath("D:/00_herne/test/workfiles")
#save_path = os.path.normpath("D:/00_herne/01_py_script_export/sys")
#file_name = "pdf_extracted_br"
time_now = datetime.now().strftime("%Y-%m-%d_%H%M%S")
search_for = "BR"
exclude = ["00_Archive", "01_Archive", "00_Document_templates"]
log_file = "log_error"
log = log.get_logger(log_file)
xls_file = "D:/00_herne/00_ISO_list_2020-10-01.xlsx"
wb = load_workbook(xls_file, read_only=False)
sh1 = wb["ISO_LIST"] # isometric line list
line_list = next(i for i in sh1.iter_cols(
min_row=1, max_row=2970, min_col=1, max_col=1)) # line kks list
data = {
"KKS": [],
"REV": [],
"DATE": [],
"FILE": [],
"PATH": [],
"KKS_connected": [],
dlist = dl.dir_list(root_path,
obj_type="f",
src_for="60*BR*",
ext="pdf",
exclude=exclude_dir) # list of required files
wb_save_path = Path("D:\\00_HERNE\\_tracking\\") # workbook save path
wb_file_name = "deleted_lines_pdf_parsed_support_list" # workbook save filename
wb_rev = "00" # workbook revision
wb = Workbook() # workbook
ws = wb.active # workbook sheet activate
r = 1 # initial row number
log_file = "error_logfile"
log = log.get_logger(f"{wb_file_name}_{log_file}")
for file in dlist:
try:
raw_pdf_data = pdf_parser.parse(file)
raw_str_list = list(map(str, raw_pdf_data.split()))
pattern = r"(\d\d)(BQ)"
for string in raw_str_list:
if re.search(pattern, string):
ws.cell(r, 1, f'=HYPERLINK("{file}","Open")')
ws.cell(r, 2, file.parts[-2]) # system
ws.cell(r, 3, file.stem.split("_")[0]) # KKS
ws.cell(r, 4, file.stem.split("_")[1]) # UNID
ws.cell(r, 5, file.stem.split("_")[-1][-1]) # revision
ws.cell(
r, 6,
import os
import re
import pandas as pd
from openpyxl import Workbook, load_workbook
from datetime import datetime
from win32com import client
import logging
import logging_error
path = "D:/00_herne/01_py_script_export/logs"
file_name = "testiranje"
logger = logging_error.get_logger(file_name)
# logging.basicConfig(level=logging.DEBUG, format='%(levelname)s - %(asctime)s - %(message)s', datefmt='T(%d.%m.%Y. %H:%M)')
a = 2
b = 0
for i in range(a):
try:
print(i / b)
except Exception as error:
logger.exception(f"{error}", exc_info=False)
log_file = "VT_bulk_print"
log_path = "D:/00_herne/01_py_script_export/logs"
exclude = ["00_Archive", "01_Archive",
"00_Document_templates"] # excluded folders
wb = load_workbook(xls_file, read_only=False)
sh1 = wb.worksheets[0] # Template
sh2 = wb.worksheets[1] # Weldmap
sh3 = wb.worksheets[2] # Linelist
ref_vt_list = get_vt_list(root_path) # list of kks with VT file
weldmap_kks = next(i for i in sh2.iter_cols(
min_row=2, max_row=7305, min_col=1, max_col=1)) # weldmap kks list
linelist_kks = next(i for i in sh3.iter_cols(
min_row=2, max_row=2952, min_col=1, max_col=1)) # line kks list
logger = logging_error.get_logger(log_file)
for kks in ref_vt_list:
try:
vt_temp(kks)
wb_dst = os.path.join(kks, f"{os.path.basename(kks)}.xlsx")
replace_sheet(xls_file, wb_dst)
pdf_file = os.path.join(kks, f"06_1_VT.pdf")
export_pdf(xls_file, pdf_file)
except Exception as error:
logger.exception(f"{kks} -- {error}", exc_info=True)
wb.close()
del ref_vt_list, weldmap_kks, linelist_kks