initial work on pdf data extract

lodur_connect.py

@@ -4,7 +4,7 @@ import re
 from datetime import datetime
 import requests
 
-def create_einsatzrapport(username, password, base_url, f_id):
+def create_einsatzrapport(username, password, base_url, f_id, pdf_data):
 
     session = requests.session()
     login_data = {
@@ -40,7 +40,7 @@ def create_einsatzrapport(username, password, base_url, f_id):
         'ztb_h': (None, '12'), # 05. Zeit bis
         'ztb_m': (None, '12'), # 05. Zeit bis
         'e_ort_1': (None, '306'), # 06. Einsatzort: Urdorf 306, Birmensdorf 298
-        'eins_ereig': (None, f_id), # 07. Ereignis
+        'eins_ereig': (None, pdf_data['einsatz']), # 07. Ereignis # TODO utf-8?
         'adr': (None, 'TBD'), # 08. Adresse
         #'zh_alarmierung_h': (None, 'UNKNOWN'), # 12. Alarmierung
         #'zh_alarmierung_m': (None, 'UNKNOWN'), # 12. Alarmierung

main.py

@@ -16,6 +16,7 @@ import aioeasywebdav
 from dotenv import load_dotenv, find_dotenv
 import paho.mqtt.client as mqtt
 from lodur_connect import create_einsatzrapport, upload_alarmdepesche
+import pdf_extract
 
 _EMAIL_SUBJECTS = '(OR SUBJECT "Einsatzausdruck_FW" SUBJECT "Einsatzprotokoll" UNSEEN)'
 _INTERVAL = 10
@@ -236,6 +237,9 @@ def main():
                         # this is real - publish Einsatz on MQTT
                         mqtt_client.publish('pylokid/' + f_type, f_id)
 
+                        # get as many information from PDF as possible
+                        pdf_data = pdf_extract.get_einsatzausdruck(os.path.join(tmp_dir, file_name))
+
                         # create new Einsatzrapport in Lodur
                         logger.info('Creating Einsatzrapport in Lodur for ' + f_id)
                         lodur_id = create_einsatzrapport(
@@ -243,6 +247,7 @@ def main():
                             lodur_password,
                             lodur_base_url,
                             f_id,
+                            pdf_data,
                         )
                         logger.info('Sent data to Lodur. Assigned Lodur ID: ' + lodur_id)
                         # store lodur id in webdav

pdf_extract.py

@@ -0,0 +1,75 @@
+#!/usr/bin/env python3
+
+import io
+from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter
+from pdfminer.converter import HTMLConverter,TextConverter,XMLConverter
+from pdfminer.layout import LAParams
+from pdfminer.pdfpage import PDFPage
+
+def concatenate_to_multiline_string(data, start, end):
+    res = ''
+    counter = start
+    while counter <= end:
+        res += data[counter] + '\n'
+        counter += 1
+    return res
+
+def convert(file):
+    pagenums = set()
+    manager = PDFResourceManager()
+    codec = 'utf-8'
+    caching = True
+
+    output = io.StringIO()
+    converter = TextConverter(manager, output, codec=codec, laparams=LAParams())
+
+    interpreter = PDFPageInterpreter(manager, converter)
+    infile = open(file, 'rb')
+
+    for page in PDFPage.get_pages(infile, pagenums, caching=caching, check_extractable=True):
+        interpreter.process_page(page)
+
+    convertedPDF = output.getvalue()
+
+    infile.close()
+    converter.close()
+    output.close()
+    return convertedPDF
+
+def get_einsatzausdruck(file):
+    """ extracts as many information from the parsed Einsatzausdruck as possible """
+
+    splited = convert(file).splitlines()
+    # sometimes the "second part - below map" doesnt start at the same index
+    # depending on the lenght of the bemerkungen
+    # therefore we compute a simple offset for the second part
+    # TODO: make it better
+    second_part_offset = 29 - splited.index('Disponierte Einheiten')
+    data = {
+        'auftrag': splited[14],
+        'datum': splited[15],
+        'zeit': splited[16],
+        'melder': concatenate_to_multiline_string(splited,18,19),
+        'erfasser': splited[20],
+        'bemerkungen': concatenate_to_multiline_string(splited,23,28),
+        'einsatz': splited[34-second_part_offset],
+        'ort': splited[37-second_part_offset],
+        'strasse': splited[38-second_part_offset],
+        #'objekt': splited[],
+        'hinweis': splited[50-second_part_offset]
+    }
+    return data
+
+def get_einsatzprotokoll(file):
+    """ extracts as many information from the parsed Einsatzprotokoll as possible """
+
+    splited = convert(file).splitlines()
+    data = {
+        'auftrag': splited[26],
+        'datum': splited[25],
+        'angelegt': splited[28],
+        'disposition': splited[30],
+        'ausgerueckt': splited[32],
+        'anort': splited[33],
+    }
+    return data