Unescape html in tweets.

1 files changed, 7 insertions, 1 deletions

diff --git a/utils/twitter_import.py b/utils/twitter_import.py
index 90d0c7c..76170bb 100644
--- a/utils/twitter_import.py
+++ b/utils/twitter_import.py
@@ -14,6 +14,11 @@ def procline(x):
         r = chr(0x200b) + r # extremely hacky
     return r
 
+def htmlunescape(s):
+    return s.replace("&lt;", "<")\
+            .replace("&gt;", ">")\
+            .replace("&amp;", "&")
+
 class Tweet:
     def __init__(self, tid, text, date, tags, media, urls, replying_to):
         self.tid = tid
@@ -26,12 +31,13 @@ class Tweet:
 
     def parse(json):
         t = json["tweet"]
-        text = t["full_text"]
+        text = htmlunescape(t["full_text"])
         #tcolinks = TCORE.findall(text)
         e = t["entities"]
         ee = t["extended_entities"] if "extended_entities" in t else None
         tid = t["id"]
         tags = [tag["text"] for tag in e["hashtags"]]
+        tags = ["Tweet"] + tags
         is_reply = "in_reply_to_status_id_str" in t
         replying_to = None
         if is_reply: