From de3449ae562b5a3f60190ec63842b0d2fc1dd890 Mon Sep 17 00:00:00 2001
From: Lynne <thecoolone3@gmail.com>
Date: Fri, 11 Jan 2019 22:55:31 +1000
Subject: [PATCH] added extract_toot function to functions.py

---
 functions.py | 23 +++++++++++++++++++++++
 1 file changed, 23 insertions(+)

diff --git a/functions.py b/functions.py
index 80ec6fe..31caf36 100755
--- a/functions.py
+++ b/functions.py
@@ -60,3 +60,26 @@ def make_toot_markov(query = None):
 			"toot": toot,
 			"media": None
 		}
+
+def extract_toot(toot):
+	soup = BeautifulSoup(toot, "html.parser")
+	for lb in soup.select("br"): #replace <br> with linebreak
+		lb.insert_after("\n")
+		lb.decompose()
+
+	for p in soup.select("p"): #ditto for <p>
+		p.insert_after("\n")
+		p.unwrap()
+
+	for ht in soup.select("a.hashtag"): #make hashtags no longer links, just text
+		ht.unwrap()
+
+	for link in soup.select("a"): #ocnvert <a href='https://example.com>example.com</a> to just https://example.com
+		link.insert_after(link["href"])
+		link.decompose()
+
+	toot = soup.get_text()
+	text = re.sub("https://([^/]+)/(@[^ ]+)", r"\2@\1", text) #put mastodon-style mentions back in
+	text = re.sub("https://([^/]+)/users/([^ ]+)", r"@\2@\1", text) #put pleroma-style mentions back in
+	text = text.rstrip("\n") #remove trailing newline
+	return text
\ No newline at end of file