From 39150d0fec3a444d9fa2786aa19e7c098c8247df Mon Sep 17 00:00:00 2001 From: Bryan Newbold Date: Tue, 23 Apr 2019 17:31:26 -0700 Subject: don't spam about missing URLs --- arabesque.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arabesque.py b/arabesque.py index 1c5663b..9b12b68 100755 --- a/arabesque.py +++ b/arabesque.py @@ -518,7 +518,7 @@ def forward(seed_id_file, map_db, output_db): # simple for redirect case (no branching); arbitrary for the fan-out case first_row = lookup_referrer_row(m, seed_url) if not first_row: - print("MISSING url: {}".format(raw_line.strip())) + #print("MISSING url: {}".format(raw_line.strip())) # need to insert *something* in this case... initial_domain = urllib3.util.parse_url(seed_url).host c.execute("INSERT INTO crawl_result VALUES (?,?,?,?,?,?,?,?,?,?,?,?,?)", -- cgit v1.2.3