renamed rhimport to rhautoimport

1 files changed, 239 insertions, 0 deletions

diff --git a/rhautoimport-dn b/rhautoimport-dn
new file mode 100755
index 0000000..9e54460
--- /dev/null
+++ b/rhautoimport-dn
@@ -0,0 +1,239 @@
+#!/usr/bin/perl -w
+#
+#
+#  rhautoimport
+#
+#  Copyright (C) 2009-2015 Christian Pointner <equinox@helsinki.at>
+#
+#  This file is part of rhautoimport.
+#
+#  rhautoimport is free software: you can redistribute it and/or modify
+#  it under the terms of the GNU General Public License as published by
+#  the Free Software Foundation, either version 3 of the License, or
+#  any later version.
+#
+#  rhautoimport is distributed in the hope that it will be useful,
+#  but WITHOUT ANY WARRANTY; without even the implied warranty of
+#  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+#  GNU General Public License for more details.
+#
+#  You should have received a copy of the GNU General Public License
+#  along with rhautoimport. If not, see <http://www.gnu.org/licenses/>.
+#
+
+use strict;
+use Date::Calc;
+use Time::localtime;
+use XML::Feed;
+use XML::Feed::Entry;
+use XML::Feed::Content;
+use XML::Feed::Enclosure;
+use URI::URL;
+use IO::Handle;
+use IPC::Open3;
+use RHRD::rddb;
+
+use lib '/usr/local/share/rhautoimport/';
+use rhautoimport;
+
+my $STAT_FILE = $ENV{'HOME'} . "/rhautoimport-dn.stat";
+my $FILES_RSS_URL = "http://www.democracynow.org/podcast-stations.xml";
+my $HEADLINES_RSS_URL = "http://www.democracynow.org/podcast.xml";
+my $IGNORE_HEADLINE = 0;
+my $PV_ID = '111';
+
+binmode(STDIN, ":utf8");
+binmode(STDOUT, ":utf8");
+binmode(STDERR, ":utf8");
+
+if($#ARGV >= 0 && $ARGV[0] eq 'last') {
+  print "!!!This is the last attempt, there won't be a retry on error!!!\n"
+}
+
+if($#ARGV >= 0 && $ARGV[0] eq 'noheadline') {
+  $IGNORE_HEADLINE = 1;
+  $STAT_FILE = $ENV{'HOME'} . "/rhautoimport-dn-noheadline.stat";
+}
+
+my $user = `/usr/bin/id -un`;
+$user =~ s/\n//;
+my $group = "democracyn";
+
+my ($dbh, $errorstring) = RHRD::rddb::opendb();
+if(!defined $dbh) {
+  print "$errorstring\n";
+  exit 1;
+}
+my @allowed_dbs = RHRD::rddb::get_dropboxes($dbh, $user, $group);
+if(!defined $allowed_dbs[0] && defined $allowed_dbs[2]) {
+  print "$allowed_dbs[2]\n";
+  exit 1;
+}
+
+my $dropbox = "";
+my $to_cart = 0;
+
+my @today = Date::Calc::Today();
+my @yesterday = Date::Calc::Add_Delta_Days($today[0], $today[1], $today[2], -1);
+my @tomorrow = Date::Calc::Add_Delta_Days($today[0], $today[1], $today[2], 1);
+
+my @broadcast_day = @yesterday;
+my @import_day = @today;
+if(localtime->hour >= 12) {
+  print "It's past noon, assuming to import file from today\n";
+  @broadcast_day = @today;
+  @import_day = @tomorrow;
+}
+
+print "day of original broadcast: " . Date::Calc::Date_to_Text(@broadcast_day) . "\n";
+print "day of Radio Helsinki broadcast: " . Date::Calc::Date_to_Text(@import_day) . "\n";
+
+for my $href ( @allowed_dbs ) {
+  my $dow = Date::Calc::Day_of_Week(@import_day);
+  if ($dow == int(substr($href->{'NAME'},0,2))) {
+    $dropbox = $href->{'PATH'};
+    $to_cart = $href->{'TO_CART'};
+  }
+}
+
+if($dropbox eq "") {
+  print "no dropbox for day in question\n";
+  RHRD::rddb::closedb($dbh);
+  exit 0;
+}
+
+my $y = sprintf("%04d-%02d-%02d", $broadcast_day[0], $broadcast_day[1], $broadcast_day[2]);
+my $yc = sprintf("%04d-%02d%02d", $broadcast_day[0], $broadcast_day[1], $broadcast_day[2]);
+
+print "looking for files from date $y in RSS Feed\n";
+print " -> $FILES_RSS_URL\n";
+
+my $files_feed = XML::Feed->parse(URI->new($FILES_RSS_URL))
+  or die "Error fetching feed: " . XML::Feed->errstr;
+
+my $file = "";
+my $out_file = "";
+for my $entry ($files_feed->entries) {
+  if($entry->enclosure && $entry->enclosure->type eq "audio/mpeg") {
+    if($entry->enclosure->url =~ /^https?:\/\/.*\.democracynow\.org\/dn([0-9-]+)-1\.mp3$/) {
+      next if($yc ne $1);
+
+      my $url = new URI::URL($entry->enclosure->url);
+      my @path = $url->path_components;
+
+      my $current_file = `cat $STAT_FILE`;
+      if($current_file eq $path[-1]) {
+        print "Already downloaded file of day in question\n";
+        RHRD::rddb::closedb($dbh);
+        exit 0;
+      }
+      $out_file = $path[-1];
+      if(!rhautoimport::check_file_extension($out_file)) {
+        print "\n\nThe extension of the matching file '". $out_file . "' seems to be wrong - manual import necessary!!!\n";
+        RHRD::rddb::closedb($dbh);
+        exit 1;
+      }
+
+      print $1 . ": downloading " . $entry->enclosure->url . " (" . $entry->enclosure->length . " Bytes) .. ";
+
+      $file = "/tmp/" . $out_file;
+      system("wget", "--quiet", "--no-check-certificate", $url, "-O", $file);
+      if( $! != 0) {
+        die "wget returned with error: " . $!;
+      }
+      print "ok\n";
+
+      last;
+    }
+  }
+}
+if($file eq "" || !(-e "$file")) {
+  print "No Entry found from day in qeustion or download error - ";
+  if($#ARGV >= 0 && $ARGV[0] eq 'last') {
+    print "giving up, manual import necessary!!!\n";
+  } else {
+    print "will retry later\n";
+  }
+  exit 1;
+}
+
+
+unless($IGNORE_HEADLINE) {
+  print "\nlooking for headlines from date $y in RSS Feed\n";
+  print " -> $HEADLINES_RSS_URL\n";
+
+  my $headlines_feed = XML::Feed->parse(URI->new($HEADLINES_RSS_URL))
+    or die "Error fetching feed: " . XML::Feed->errstr;
+
+  for my $entry ($headlines_feed->entries) {
+    if($entry->enclosure && $entry->enclosure->type eq "audio/mpeg") {
+      my $sum_title = $entry->title;
+      my $sum_text = $entry->summary->body . "\n<br />\n<a href=\"" . $entry->link . "\">" . $entry->link . "</a>\n";
+
+      if($entry->id =~ /tag:democracynow.org,([0-9-]+):media\/mp3download\/[^\/]+/) {
+        next if($y ne $1);
+
+        print "summary:\n" . $sum_title . "\n\n" . $sum_text . "\n";
+        rhautoimport::pv_add_note($sum_title, $sum_text, $PV_ID, sprintf("%04d-%02d-%02d", @import_day), "1", 0);
+        print "\n";
+        rhautoimport::pv_add_note($sum_title, $sum_text, $PV_ID, sprintf("%04d-%02d-%02d", @import_day), "1", 1);
+        print "\n";
+
+        last;
+      }
+    }
+  }
+} else {
+  print "\nignoring headlines for they are not available by now\n";
+  my $dow_string = Date::Calc::Day_of_Week_to_Text(Date::Calc::Day_of_Week(@broadcast_day));
+  my $sum_title = sprintf("Democracy Now! %04d-%02d-%02d %s", @broadcast_day, $dow_string);
+  my $sum_text = "";
+  print "summary:\n" . $sum_title . "\n\n" . $sum_text . "\n";
+  rhautoimport::pv_add_note($sum_title, $sum_text, $PV_ID, sprintf("%04d-%02d-%02d", @broadcast_day), "1", 2);
+  print "\n";
+}
+
+print "converting $file ... ";
+my $infile = $file;
+$file =~ s/\.mp3$/.wav/;
+system("ffmpeg", "-i", $infile, "-acodec", "pcm_s16le", $file);
+if( $! != 0) {
+  die "ffmpeg returned with error: " . $!;
+}
+print "ok\n";
+unlink $infile;
+
+print "will import $file to dropbox $dropbox (cart=$to_cart)\n\n";
+
+my $error_cb = sub {
+  my ($text) = @_;
+
+  print "\n$text";
+  return 0;
+};
+
+rhautoimport::check_key_file() or die "Import Key not found, use rhautoimport-create-id to create one\n";
+
+my $ret;
+my $log;
+$log = rhautoimport::clear_carts($dbh, $group, $to_cart);
+my $import_log;
+($ret, $import_log) = rhautoimport::import_single($file, $dropbox, $user, 0, $error_cb);
+$log .= $import_log;
+
+RHRD::rddb::closedb($dbh);
+
+unlink $file;
+
+if(!$ret) {
+  print "\nImport Error:\n";
+  print $log;
+  exit 1;
+}
+
+unlink($STAT_FILE);
+open(my $fhs, '>', $STAT_FILE);
+print $fhs $out_file;
+close($fhs);
+
+exit 0;