From 9ffdf258a9441ca680864fb468facfa261df9491 Mon Sep 17 00:00:00 2001
From: Kalle Westerling <7298727+kallewesterling@users.noreply.github.com>
Date: Sun, 6 Jun 2021 06:13:05 -0300
Subject: [PATCH] Fix Post.mentions including email addresses (#1167)

Earlier, if someone had an email address in the caption, those were provided as mentions in the Post.mentions attribute. With this update to the regular expression, email addresses are no longer ingested.

Fixes #1029.
---
 instaloader/structures.py | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/instaloader/structures.py b/instaloader/structures.py
index c1ea78b..cf90391 100644
--- a/instaloader/structures.py
+++ b/instaloader/structures.py
@@ -339,9 +339,11 @@ class Post:
         """List of all lowercased profiles that are mentioned in the Post's caption, without preceeding @."""
         if not self.caption:
             return []
-        # This regular expression is from jStassen, adjusted to use Python's \w to support Unicode
+        # This regular expression is modified from jStassen, adjusted to use Python's \w to
+        # support Unicode and a word/beginning of string delimiter at the beginning to ensure
+        # that no email addresses join the list of mentions.
         # http://blog.jstassen.com/2016/03/code-regex-for-instagram-username-and-hashtags/
-        mention_regex = re.compile(r"(?:@)(\w(?:(?:\w|(?:\.(?!\.))){0,28}(?:\w))?)")
+        mention_regex = re.compile(r"(?:^|\W|_)(?:@)(\w(?:(?:\w|(?:\.(?!\.))){0,28}(?:\w))?)")
         return re.findall(mention_regex, self.caption.lower())
 
     @property