From 344cd83278adf1da7ef3dfb31731ce823f36387c Mon Sep 17 00:00:00 2001 From: Christian Pointner Date: Thu, 2 Jun 2016 16:33:21 +0200 Subject: added panoptikum importer diff --git a/Makefile b/Makefile index a8d4aee..acf8d33 100644 --- a/Makefile +++ b/Makefile @@ -52,6 +52,7 @@ install-bin: $(INSTALL) -m 755 $(EXECUTABLE)-nw $(DESTDIR)$(BINDIR) $(INSTALL) -m 755 $(EXECUTABLE)-oi $(DESTDIR)$(BINDIR) $(INSTALL) -m 755 $(EXECUTABLE)-o94n $(DESTDIR)$(BINDIR) + $(INSTALL) -m 755 $(EXECUTABLE)-po $(DESTDIR)$(BINDIR) $(INSTALL) -m 755 $(EXECUTABLE)-rs $(DESTDIR)$(BINDIR) $(INSTALL) -m 755 $(EXECUTABLE)-ra $(DESTDIR)$(BINDIR) $(INSTALL) -m 755 $(EXECUTABLE)-sm $(DESTDIR)$(BINDIR) @@ -73,6 +74,7 @@ install-bin: @sed s#/usr/local/share/rhimport/#$(SHAREDIR)/$(EXECUTABLE)/#g -i $(DESTDIR)$(BINDIR)/$(EXECUTABLE)-nw @sed s#/usr/local/share/rhimport/#$(SHAREDIR)/$(EXECUTABLE)/#g -i $(DESTDIR)$(BINDIR)/$(EXECUTABLE)-oi @sed s#/usr/local/share/rhimport/#$(SHAREDIR)/$(EXECUTABLE)/#g -i $(DESTDIR)$(BINDIR)/$(EXECUTABLE)-o94n + @sed s#/usr/local/share/rhimport/#$(SHAREDIR)/$(EXECUTABLE)/#g -i $(DESTDIR)$(BINDIR)/$(EXECUTABLE)-po @sed s#/usr/local/share/rhimport/#$(SHAREDIR)/$(EXECUTABLE)/#g -i $(DESTDIR)$(BINDIR)/$(EXECUTABLE)-rs @sed s#/usr/local/share/rhimport/#$(SHAREDIR)/$(EXECUTABLE)/#g -i $(DESTDIR)$(BINDIR)/$(EXECUTABLE)-ra @sed s#/usr/local/share/rhimport/#$(SHAREDIR)/$(EXECUTABLE)/#g -i $(DESTDIR)$(BINDIR)/$(EXECUTABLE)-sm @@ -105,6 +107,7 @@ remove-bin: rm -f $(DESTDIR)$(BINDIR)/$(EXECUTABLE)-nw rm -f $(DESTDIR)$(BINDIR)/$(EXECUTABLE)-oi rm -f $(DESTDIR)$(BINDIR)/$(EXECUTABLE)-o94n + rm -f $(DESTDIR)$(BINDIR)/$(EXECUTABLE)-po rm -f $(DESTDIR)$(BINDIR)/$(EXECUTABLE)-rs rm -f $(DESTDIR)$(BINDIR)/$(EXECUTABLE)-ra rm -f $(DESTDIR)$(BINDIR)/$(EXECUTABLE)-sm diff --git a/debian/changelog b/debian/changelog index 0946e75..4d89024 100644 --- a/debian/changelog +++ b/debian/changelog @@ -1,3 +1,9 @@ +rhimport (0.3.15-47) unstable; urgency=medium + + * added importer for Panoptikum + + -- Christian Pointner Thu, 02 Jun 2016 16:28:18 +0200 + rhimport (0.3.15-46) unstable; urgency=medium * added importer for Ergo diff --git a/rhimport-po b/rhimport-po new file mode 100755 index 0000000..e13419b --- /dev/null +++ b/rhimport-po @@ -0,0 +1,221 @@ +#!/usr/bin/perl -w +# +# +# rhimport +# +# Copyright (C) 2009-2016 Christian Pointner +# +# This file is part of rhimport. +# +# rhimport 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. +# +# rhimport 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 rhimport. If not, see . +# + +use strict; +use DBI; +use Date::Calc; +use DateTime::Format::Strptime; +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 HTML::Entities; +use LWP::Simple; + +use lib '/usr/local/share/rhimport/'; +use rhimport; + +my $DBHOST = "airplay"; +my $DBUSER = "rivendell"; +my $DBPW = "lldriven"; +my $DB = "rivendell"; + +my $STAT_FILE = $ENV{'HOME'} . "/rhimport-po.stat"; +my $RSS_URL = "https://cba.fro.at/series/panoptikum-bildung/feed?c=Kfs2IoV2Wmd"; +$XML::Feed::MULTIPLE_ENCLOSURES=1; +my $PV_ID = '570'; +my $LAST_RUN = 0; + +binmode(STDIN, ":utf8"); +binmode(STDOUT, ":utf8"); +binmode(STDERR, ":utf8"); + +my $curweek = rhimport::get_rd_week(); + +if($curweek == 2 || $curweek == 4) { + if($#ARGV >= 0 && $ARGV[0] eq 'last') { + print "!!!This is the last attempt, there won't be a retry on error!!!\n"; + $LAST_RUN = 1; + } +} + +my $user = `/usr/bin/id -un`; +$user =~ s/\n//; +my $group = "panoptikum"; + +my $dbh = DBI->connect("DBI:mysql:$DB:$DBHOST","$DBUSER","$DBPW") or die "Database Error: $DBI::errstr"; +my @allowed_dbs = rhimport::get_dropboxes($dbh, $user, $group); + +my $idx = 0; +if(scalar(@allowed_dbs) != 1) { + print "found more or less than 1 Dropbox for this group?!\n"; + $dbh->disconnect(); + exit 1; +} +my $dropbox = $allowed_dbs[$idx]->{'PATH'}; +my $to_cart = $allowed_dbs[$idx]->{'TO_CART'}; + +my @today = Date::Calc::Today(); +print "today: " . Date::Calc::Date_to_Text(@today) . " (Week: " . $curweek . ")\n"; + +my @import_date = Date::Calc::Standard_to_Business(@today); +$import_date[2] = 4; +@import_date = Date::Calc::Business_to_Standard(@import_date); + +my $dow = Date::Calc::Day_of_Week(@today); +if($curweek == 2 || $curweek == 4) { + if($dow > 4) { + @import_date = Date::Calc::Add_Delta_Days(@import_date, 14); + } +} else { + @import_date = Date::Calc::Add_Delta_Days(@import_date, 7); +} +print "day of next Radio Helsinki broadcast: " . Date::Calc::Date_to_Text(@import_date) . "\n"; + +my @broadcast_date = Date::Calc::Nth_Weekday_of_Month_Year($import_date[0], $import_date[1], 5, 1); +if(Date::Calc::Delta_Days(@broadcast_date, @import_date) > 0) { + my @tmp_date = Date::Calc::Nth_Weekday_of_Month_Year($import_date[0], $import_date[1], 5, 3); + if(Date::Calc::Delta_Days(@tmp_date, @import_date) > 0) { + @broadcast_date = @tmp_date; + } +} else { + my @tmp_date = Date::Calc::Add_Delta_YM(@broadcast_date, 0, -1); + @broadcast_date = Date::Calc::Nth_Weekday_of_Month_Year($tmp_date[0], $tmp_date[1], 5, 3); +} +print "day of latest original broadcast before next Radio Helsinki broadcast: " . Date::Calc::Date_to_Text(@broadcast_date) . "\n"; + +if(Date::Calc::Delta_Days(@broadcast_date, @today) <= 0) { + print "File won't be available by now!\n"; + $dbh->disconnect(); + exit 0; +} + +my $id = sprintf("%04d-%02d-%02d", @import_date); +my $bd = sprintf("%04d-%02d-%02d", @broadcast_date); + +print "looking for files for broadcast date $bd in RSS Feed\n"; +print " -> $RSS_URL\n"; + +my $feed = XML::Feed->parse(URI->new($RSS_URL)) + or die "Error fetching feed: " . XML::Feed->errstr; + +my $file = ""; +my $out_file = ""; +my $i = 0; +for my $entry ($feed->entries) { + $i++; + next unless $entry->enclosure; + + my $entry_bdt = $entry->{'entry'}{'broadcastDate'}; + next unless (defined $entry_bdt); + my $bdt = DateTime::Format::Strptime::strptime("%a, %d %b %Y %H:%M:%S", $entry_bdt); + + next unless($broadcast_date[0] == $bdt->year && $broadcast_date[1] == $bdt->month && $broadcast_date[2] == $bdt->day); + + my $j = 0; + for my $enclosure($entry->enclosure) { + $j++; + if($enclosure->type eq "audio/mpeg" || $enclosure->type eq "audio/ogg") { + print "$i/$j: (" . $enclosure->type . ", " . $enclosure->length . ") " . $enclosure->url . "\n"; + my $fetchurl = $enclosure->url; + if($fetchurl =~ /^(.*)_cut(\.[^\.]+)$/) { + $fetchurl = $1 . $2; + } + + my $url = new URI::URL($fetchurl); + my @path = $url->path_components; + + my $current_stat = `cat $STAT_FILE`; + my ($current_id, $current_file) = $current_stat =~ m/^(.*)\n(.*)/; + if($current_id eq $id && $current_file eq $path[-1]) { + print "Already downloaded file of today\n"; + $dbh->disconnect(); + exit 0; + } + $out_file = $path[-1]; + if(!rhimport::check_file_extension($out_file)) { + print "\n\nThe extension of the matching file '". $out_file . "' seems to be wrong - manual import necessary!!!\n"; + $dbh->disconnect(); + exit 1; + } + + print " --> " . $entry_bdt . ": downloading " . $url . " (" . $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; + } + } + last if $file ne ""; +} + +if($file eq "" || !(-e "$file")) { + print "No Entry found from $bd or download error - "; + if($LAST_RUN) { + print "giving up, manual import necessary!!!\n"; + } else { + print "will retry later\n"; + } + exit 1; +} + +print "will import $file to dropbox $dropbox (cart=$to_cart)\n"; + +my $error_cb = sub { + my ($text) = @_; + + print "\n$text"; + return 0; +}; + +rhimport::check_key_file() or die "Import Key not found, use rhimport-create-id to create one\n"; + +my $ret; +my $log = rhimport::clear_carts($dbh, $group, $to_cart); +my $import_log; +($ret, $import_log) = rhimport::import_single($file, $dropbox, $user, 0, $error_cb); +$log .= $import_log; + +$dbh->disconnect(); + +unlink $file; + +if(!$ret) { + print "\nImport Error:\n"; + print $log; + exit 1; +} + +unlink($STAT_FILE); +open(my $fhs, '>', $STAT_FILE); +print $fhs "$id\n$out_file"; +close($fhs); + +exit 0; diff --git a/rhimport-wr b/rhimport-wr index 2fd1089..0742586 100755 --- a/rhimport-wr +++ b/rhimport-wr @@ -105,7 +105,8 @@ print "day of latest original broadcast before next Radio Helsinki broadcast: " if(Date::Calc::Delta_Days(@broadcast_date, @today) <= 0) { print "File won't be available by now!\n"; - exit 42; + $dbh->disconnect(); + exit 0; } my $id = sprintf("%04d-%02d-%02d", @import_date); -- cgit v0.10.2