From: Ian Jackson <ijackson@chiark.greenend.org.uk>
Date: Wed, 9 Sep 2020 22:35:58 +0000 (+0100)
Subject: media-scraper: wip
X-Git-Tag: otter-0.2.0~956
X-Git-Url: https://www.chiark.greenend.org.uk/ucgi/~ianmdlvl/git?a=commitdiff_plain;h=6ab80239372798e51742392533b35ed5e92a02af;p=otter.git

media-scraper: wip

Signed-off-by: Ian Jackson <ijackson@chiark.greenend.org.uk>
---

diff --git a/library/wikimedia.toml b/library/wikimedia.toml
index 98fa65dd..af29d138 100644
--- a/library/wikimedia.toml
+++ b/library/wikimedia.toml
@@ -12,11 +12,11 @@ category = "chess"
 
 files = """
 blt45	a white bishop
-adt45	a black knight
+#adt45	a black knight
 """
 [chess.scraper]
 
 method = "wikimedia"
 licences = [ "Cc-by-sa-3.0", "GFDL|migration=relicense" ]
-url_prefix = "https://commons.wikimedia.org/wiki/File:Chess "
-url_suffix = ".svg"
+url_prefix = "https://commons.wikimedia.org/wiki/File:Chess_"
+url_suffix = ".svg?action=raw"
diff --git a/media-scraper b/media-scraper
index 8967e806..65a82fda 100755
--- a/media-scraper
+++ b/media-scraper
@@ -1,6 +1,5 @@
 #!/usr/bin/perl -w
 use strict;
-use autodie;
 
 use POSIX;
 use TOML::Parser;
@@ -14,7 +13,7 @@ our $max_rate = 2; # per second
 open DEBUG, ">&STDERR" or die $!;
 
 sub run_curl {
-  my (@curl) = (qw(curl), @_);
+  my (@curl) = (qw(curl -Ssf -L --proto-redir -all), @_);
   our $last_curl;
   $last_curl //= 0.;
   my $now = Time::HiRes::time;