Added sample document file and proper docx library

1 files changed, 17 insertions, 10 deletions

diff --git a/FBGM.py b/FBGM.py
index 09821f8..4f2a8cd 100644
--- a/FBGM.py
+++ b/FBGM.py
@@ -1,7 +1,9 @@
 from ftplib import parse150
-import os, sys
+import os, sys, docx
 from string import punctuation
 
+
+#Text file handler
 def paragraph_parser(contents):
         punctuation = [".", "?", "!", '"']
         paragraph_end = [".\n\n", "?\n\n", "!\n\n", '"\n\n', "|E"]
@@ -49,8 +51,19 @@ def paragraph_parser(contents):
                 paragraph[paragraph_number]="<h2>"+article[article_index.index(x)-1]+"</h2>\n<p>"+paragraph[paragraph_number][len(article[article_index.index(x)-1]):]
                 print("Header "+str(x)+" is in paragraph "+str(paragraph_number))
         paragraph[-1] = paragraph[-1][:-5]+paragraph[-1][-4:]
-        print(paragraph[-1])
         return ''.join(paragraph)
+
+
+#Document file Handler
+def dochandler(path):
+    doc = docx.Document(path)
+    fullText = []
+    for para in doc.paragraphs:
+        fullText.append(para.text)
+        print(para.text, para.style.name)
+    return '\n'.join(path)
+    
+
             
             
 
@@ -93,16 +106,10 @@ def pdfhandler(path):
     return 0
     
 
-def dochandler(path):
-    f = open(path)
-    print(f.read())
-    return 0
-
-
 
 #Attempting to pass txt file in path 
-#path = 'C:/Users/a big fuck/Documents/beansandtoast.txt'
-path = 'C:/Code/texttohtml/memes.txt'
+path = 'C:/Code/texttohtml/ThisOne.docx'
+#path = 'C:/Code/texttohtml/memes.txt'
 
 
 extension = path[path.rfind('.')+1: len(path)]