added tesseract checks and debian install

create_interest_areas_from_image.py

@@ -3,19 +3,28 @@ import pandas as pd
 import io
 import csv
 import os
+from pathlib import Path
 
 if os.environ.get('TESSDATA_PREFIX') is None and os.name == 'nt':
-    os.environ['TESSDATA_PREFIX'] = 'C:/Program Files/Tesseract-OCR/tessdata/'
     tessdata_prefix = 'C:/Program Files/Tesseract-OCR/tessdata/'
+    if Path(tessdata_prefix).exists():
+        os.environ['TESSDATA_PREFIX'] = 'C:/Program Files/Tesseract-OCR/tessdata/'
+    else:
+        tessdata_prefix = None
 if os.environ.get('TESSDATA_PREFIX') is None and os.name != 'nt':
-    os.environ['TESSDATA_PREFIX'] = '/usr/share/tesseract-ocr/4.00/tessdata'
     tessdata_prefix = '/usr/share/tesseract-ocr/4.00/tessdata'
+    if Path(tessdata_prefix).exists():
+        os.environ['TESSDATA_PREFIX'] = '/usr/share/tesseract-ocr/4.00/tessdata'
+    else:
+        tessdata_prefix = None
     
 import pytesseract
 if os.name == 'nt':
-    pytesseract.pytesseract.tesseract_cmd = r'c:/Program Files/Tesseract-OCR/tesseract.exe'
+    if Path(r'c:/Program Files/Tesseract-OCR/tesseract.exe').exists():
+        pytesseract.pytesseract.tesseract_cmd = r'c:/Program Files/Tesseract-OCR/tesseract.exe'
 else:
-    pytesseract.pytesseract.tesseract_cmd =r'/usr/bin/tesseract'
+    if Path(r'/usr/bin/tesseract').exists():
+        pytesseract.pytesseract.tesseract_cmd =r'/usr/bin/tesseract'
 
 def recognize_text(image_path, tesseract_config='--psm 6 -l spa'):
     """

packages.txt

@@ -1,6 +1,6 @@
-build-essential
-curl 
-software-properties-common
 libcairo2-dev
 tesseract-ocr
-tesseract-ocr-spa
+libtesseract-dev
+tesseract-ocr-eng
+tesseract-ocr-spa
+tesseract-ocr-script-latn