|
|
@@ -29,7 +29,7 @@ class Markov:
|
|
|
return self.generate()
|
|
|
|
|
|
text = " ".join(words)
|
|
|
- text = re.sub(r"(?:^| )?((?\.\.)|(\.{2,})|(\!{2,})|(\?{2,})|([.?!,:;\(\)\"'\$\+\-–—…]))(?: |$)", r"\1 ", text)
|
|
|
+ text = re.sub(r"(?:^| )?((\?\.\.)|(\.{2,})|(\!{2,})|(\?{2,})|([.?!,:;\(\)\"'\$\+\-–—…]))(?: |$)", r"\1 ", text)
|
|
|
text = text.strip()
|
|
|
|
|
|
return text
|
|
|
@@ -46,7 +46,8 @@ class Markov:
|
|
|
|
|
|
text = text.replace("\n", " ")
|
|
|
text = re.sub(r"(@[a-z0-9_]+,?)", "", text)
|
|
|
- text = re.sub(r"((?\.\.)|(\.{2,})|(\!{2,})|(\?{2,})|[.?!,:;\(\)\"'\$\+\-–—…])", r" \1 ", text)
|
|
|
+ text = re.sub("https?:\\/\\/(?:www\\.)?[-a-zA-Z0-9@:%._\\+~#=]{1,256}\\.[a-zA-Z0-9()]{1,6}\\b(?:[-a-zA-Z0-9()@:%_\\+.~#?&\\/=]*)", "", text)
|
|
|
+ text = re.sub(r"((\?\.\.)|(\.{2,})|(\!{2,})|(\?{2,})|[.?!,:;\(\)\"'\$\+\-–—…])", r" \1 ", text)
|
|
|
text = text.split(" ")
|
|
|
text = map(lambda word: word.strip(), text)
|
|
|
text = filter(bool, text)
|
