Exit strategy

find_chapters.py

@@ -26,13 +26,14 @@
 __author__ = "kthoden@mpiwg-berlin.mpg.de"
 
 import re
+import sys
 import argparse
 import logging
 from PyPDF2 import PdfFileWriter, PdfFileReader
 
 logging.basicConfig(level=logging.DEBUG, format=' %(asctime)s - %(levelname)s - %(message)s')
 
-CHAPTER_LABEL_REGEX = r"chapter\d+_.*?"
+CHAPTER_LABEL_REGEX = r"chap\d+_.*?"
 # \newlabel{chapter01_caraffa}{{1}{5}{Objects of Value: Challenging Conventional Hierarchies in the Photo Archive\EOAauthor {Costanza Caraffa}}{section*.4}{}}
 NEWLABEL_REGEX = r"\\newlabel\{" + CHAPTER_LABEL_REGEX + "\}\{\{\d+\}\{(\d+)\}"
 
@@ -55,14 +56,18 @@ def main():
 
     parser = argparse.ArgumentParser()
     parser.add_argument("auxfile", help="The auxfile that is used to read the page numbers from.")
-    parser.add_argument("pdffile", help="The PDF file that is going to be split in chapters..")
+    parser.add_argument("pdffile", help="The PDF file that is going to be split in chapters.")
     args = parser.parse_args()
 
     with open(args.auxfile) as aux_file:
         aux_lines = aux_file.read()
 
     references = re.findall(NEWLABEL_REGEX, aux_lines)
 
+    if not references:
+        logging.error("No chapter marks found. Exiting")
+        sys.exit()
+
     input1 = PdfFileReader(open(args.pdffile, "rb"))
     logging.debug("Input has %d pages.", input1.getNumPages())