diff options
author | Matthew Lemon <matt@matthewlemon.com> | 2022-09-13 21:27:18 +0100 |
---|---|---|
committer | Matthew Lemon <matt@matthewlemon.com> | 2022-09-13 21:27:18 +0100 |
commit | 2e18bc6a11af1865192c1c4651928ed461c33437 (patch) | |
tree | 47c3d17af9e444378fce19376e9d5045eac08b5e /writing_tools/create_md_links_from_journal_urls.pl | |
parent | b31e80034ec923161b91196e169e7e4c261bd4de (diff) |
good enough to generate a list of markdown urls to pipe into file
Diffstat (limited to 'writing_tools/create_md_links_from_journal_urls.pl')
-rw-r--r-- | writing_tools/create_md_links_from_journal_urls.pl | 26 |
1 files changed, 19 insertions, 7 deletions
diff --git a/writing_tools/create_md_links_from_journal_urls.pl b/writing_tools/create_md_links_from_journal_urls.pl index 52e78ca..a03aa23 100644 --- a/writing_tools/create_md_links_from_journal_urls.pl +++ b/writing_tools/create_md_links_from_journal_urls.pl @@ -7,6 +7,8 @@ use HTML::TreeBuilder 5 -weak; use HTML::HeadParser; use feature qw(say); +$| = 1; # turn on autoflush for stdout (https://stackoverflow.com/questions/40608986/print-doesnt-work-while-iterations-are-going-inside-foreach-loop) + # How to read each file in a directory $dir my $numargs = $#ARGV + 1; @@ -72,16 +74,26 @@ my @uniqueurls = keys %riddups; sub create_mdlink { my ($url, $title) = @_; + if ($title eq "") { + $title = "- UKNOWN TITLE -"; + } + return "[".$title."]"."(".$url.")" } +my @mdurls; + foreach my $url (@uniqueurls) { - my $req = HTTP::Request->new(GET => $url); - $req->header(Accept => "text/html"); - my $res = $ua->request($req); - my $p = HTML::HeadParser->new; - $p->parse($res->content) and print "not finished"; - my $title = $p->header('Title'); - print create_mdlink($url, $title), "\n"; + my $req = HTTP::Request->new(GET => $url); + $req->header(Accept => "text/html"); + my $res = $ua->request($req); + my $p = HTML::HeadParser->new; + $p->parse($res->content) and print "not finished"; + my $title = $p->header('Title'); + push @mdurls => create_mdlink($url, $title); } + +$, = "\n\n- "; +print "\n\n"; +print @mdurls; |