From 9d8cab78dbc21cdc0a5918a62e9c18c3fd028017 Mon Sep 17 00:00:00 2001 From: Leonardo Taccari Date: Thu, 19 Mar 2020 23:52:19 +0100 Subject: [PATCH] ignore possible consecutive `js-stream-item' when parsing a single tweet --- tscrape.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/tscrape.c b/tscrape.c index 9daedd6..e1b48d1 100644 --- a/tscrape.c +++ b/tscrape.c @@ -159,6 +159,8 @@ xmltagstartparsed(XMLParser *x, const char *t, size_t tl, int isshort) state = 0; } else if (!strcmp(t, "li") && isclassmatch(classname, STRP("js-stream-item"))) { + if (state & Item) + return; state |= Item; datatime[0] = text[0] = timestamp[0] = itemfullname[0] = '\0'; itemid[0] = itemusername[0] = retweetid[0] = '\0'; -- 2.24.1