diff --git a/tetras_extraction/script/src/transform.py b/tetras_extraction/script/src/transform.py index 92a774ea86859bdb718077527eb756adc846fdb3..89cf6c23161b2e0d54a089436d0f98c66480718d 100644 --- a/tetras_extraction/script/src/transform.py +++ b/tetras_extraction/script/src/transform.py @@ -71,7 +71,15 @@ def prepareHTMLforMD(str): def postEditMD(str1): + ################################################### + # Various string cleaning and replacements + ################################################### str1 = str1.replace(r"\_","_").replace(r" - ","\n- ").replace(r"| --- |", "").replace(r"|","") + str1 = str1.replace("Ecoutez","Écoutez").replace("Ecouter","Écouter").replace("Enoncés","Énoncés").replace(r"A l'oral",r"À l'oral").replace("Enoncé","Énoncé").replace("A un bout","À un bout").replace("A l","À l") + + + + ################################################### # Add audio players for audio extracted from SWF ###################################################