Continued:

- skip wordpress.com instances as the public API is always different to the
  "instance"
- skip empty doc (BeautifulSoup4) result (HTML parser failed)
- tpzo fixed

diff --git a/fba/commands.py b/fba/commands.py
index adc2c87d9e97ffb219ca37060e761631e9e2aa19..31d216d9043c5a730ef8f76244a9d59cd0416ce4 100644 (file)
--- a/fba/commands.py
+++ b/fba/commands.py
@@ -94,7 +94,7 @@ def check_nodeinfo(args: argparse.Namespace) -> int:
     # Fetch rows
     database.cursor.execute("SELECT domain, software, nodeinfo_url \
 FROM instances \
-WHERE nodeinfo_url IS NOT NULL \
+WHERE nodeinfo_url IS NOT NULL AND nodeinfo_url NOT LIKE '%public-api.wordpress.com%' \
 ORDER BY domain ASC")
 
     cnt = 0
@@ -107,7 +107,7 @@ ORDER BY domain ASC")
         logger.debug("punycode='%s' - AFTER!", punycode)
 
         if row["nodeinfo_url"].startswith("/"):
-            logger.debug("row[nodeinfo_url]='%s' is a relative URL and always matches - SKIP!", row["nodeinfo_url"])
+            logger.debug("row[nodeinfo_url]='%s' is a relative URL and matches always - SKIP!", row["nodeinfo_url"])
             continue
         elif row["nodeinfo_url"].find(punycode) == -1 and row["nodeinfo_url"].find(row["domain"]) == -1:
             logger.warning("punycode='%s' is not found in row[nodeinfo_url]='%s',row[software]='%s'", punycode, row["nodeinfo_url"], row["software"])
@@ -1835,7 +1835,10 @@ def fetch_relays(args: argparse.Namespace) -> int:
             continue
 
         logger.debug("row[software]='%s'", row["software"])
-        if row["software"] == "activityrelay":
+        if doc is None:
+            logger.debug("row[domain]='%s' does not return valid HTML - SKIPPED!", row["domain"])
+            continue
+        elif row["software"] == "activityrelay":
             logger.debug("Checking row[domain]='%s' ...", row["domain"])
             tags = doc.findAll("p")