Update main.py

main.py

@@ -36,7 +36,7 @@ from secrets import SystemRandom
 from random import randint, sample
 
 from enum import Enum
-from re import sub
+from re import sub, findall, escape
 
 from functools import partial
 
@@ -197,18 +197,26 @@ async def __ocr(im, file_id):
     return out
 
 def convert_links_to_text(text):
-  """Converts all Markdown links in a string to their link text.
+    txt = text
 
-  Args:
-    text: The input string containing Markdown links.
-
-  Returns:
-    The modified string with links replaced by their text.
-  """
+    # Anything that isn't a square closing bracket
+    name_regex = "[^]]+"
+    # http:// or https:// followed by anything but a closing paren
+    url_regex = "http[s]?://[^)]+"
+    
+    markup_regex = '\[({0})]\(\s*({1})\s*\)'.format(name_regex, url_regex)
+    
+    for match in findall(markup_regex,txt):
+    	link_str = f"[{match[0]}]({match[1]})"
+    	txt = txt.replace(link_str, match[0])
 
-  link_pattern = r"\[(.*?)\]\(.*?\)"
-  return sub(link_pattern, r"\1", text)
+    return txt
 
+def remove_wikipedia_footnote_ptrs(text):
+    txt = text
+    wiki_footnote_regex = r'\\\[\d+\\]'
+    txt = sub(wiki_footnote_regex, '', txt)
+    return txt
 
 async def __convert2md(inp):
     # Use gfm-raw_html to strip styling data from source file
@@ -539,7 +547,7 @@ async def generate_questions(request):
 
     # __raw_outputs = [await p for p in ptasks]
     __raw_outputs = await asyncio.gather(*ptasks)
-    
+    print(__raw_outputs)
     for pgph_i, o in enumerate(__raw_outputs):
         # print(o)
         # print(pgph_i)