#!/usr/bin/perl -w # # # rhautoimport # # Copyright (C) 2009-2017 Christian Pointner # # 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 . # use strict; 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 HTML::Entities; use lib '../rhrdlibs/lib/'; use RHRD::utils; use lib '/usr/local/share/rhautoimport/'; use lib './'; use rhautoimport; my $STAT_FILE = $ENV{'HOME'} . "/rhautoimport-mc.stat"; my $RSS_URL = "https://cba.fro.at/podcast/music-circus/feed"; $XML::Feed::MULTIPLE_ENCLOSURES=1; my $RD_GROUP = "mucirchh"; my $PV_ID = '929'; my $TITLE = "music circus hip hop show"; my $LAST_RUN = 0; my $upload_delay_days = 0; binmode(STDIN, ":utf8"); binmode(STDOUT, ":utf8"); binmode(STDERR, ":utf8"); my $curweek = RHRD::utils::get_rd_week(); if($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"; $LAST_RUN = 1; } } rhautoimport::report_title_and_last($TITLE, $LAST_RUN); 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] = 1; @import_date = Date::Calc::Business_to_Standard(@import_date); my $dow = Date::Calc::Day_of_Week(@today); if($curweek == 2 || $curweek == 4) { @import_date = Date::Calc::Add_Delta_Days(@import_date, 7); } else { @import_date = Date::Calc::Add_Delta_Days(@import_date, 14); } print "day of next Radio Helsinki broadcast: " . Date::Calc::Date_to_Text(@import_date) . "\n"; my @allowed_dbs = rhautoimport::get_dropboxes($RD_GROUP); if(!defined $allowed_dbs[0] && defined $allowed_dbs[1]) { print "$allowed_dbs[1]\n"; exit 1; } if(scalar(@allowed_dbs) != 1) { print "found more or less than one Dropbox for this group?!\n"; exit 1; } my $show_id = $allowed_dbs[0]->{'SHOWID'}; my $show_title = $allowed_dbs[0]->{'SHOWTITLE'}; my @broadcast_date = Date::Calc::Add_Delta_Days(@import_date, -9); 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) <= $upload_delay_days) { print "File won't be available by now!\n"; exit 42; } my $id = sprintf("%04d-%02d-%02d", @import_date); my $bd = sprintf("%04d-%02d-%02d", @broadcast_date); print "looking for files with cba:broadcastDate $bd in RSS Feed (will be using cba:productionDate if cba:broadcastDate is not set)\n"; print " -> $RSS_URL\n"; my ($result, $feed) = rhautoimport::fetch_parse_rss_cba($RSS_URL); unless ($result) { print "Error fetching feed: $feed\n"; exit 1; } my $uri = ""; my $file = ""; my $sum_title = ""; my $sum_text = ""; my $i = 0; for my $entry ($feed->entries) { $i++; next unless $entry->enclosure; my $entry_bdt = $entry->{'entry'}{'https://cba.fro.at/help#feeds'}{'broadcastDate'}; my $format_string = "%a, %d %b %Y %H:%M:%S"; unless (defined $entry_bdt) { $entry_bdt = $entry->{'entry'}{'https://cba.fro.at/help#feeds'}{'productionDate'}; $format_string = "%a, %d %b %Y"; } next unless (defined $entry_bdt); my $bdt = DateTime::Format::Strptime::strptime($format_string, $entry_bdt); next unless($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 $orig_uri = $enclosure->url; if($orig_uri =~ /^(.*)_cut(\.[^\.]+)$/) { $orig_uri = $1 . $2; } $uri = new URI::URL($orig_uri); my @path = $uri->path_components; $file = $path[-1]; my $current_stat = `cat $STAT_FILE`; my ($current_id, $current_file) = $current_stat =~ m/^(.*)\n(.*)/; if($current_id eq $id && $current_file eq $file) { print "Already downloaded file of today\n"; exit 42; } if(!rhautoimport::check_file_extension($file)) { print "\n\nThe extension of the matching file '". $file . "' seems to be wrong - manual import necessary!!!\n"; print "\n\n --> https://import.helsinki.at/shows/$show_id\n"; exit 1; } $sum_title = decode_entities($entry->title); $sum_text = decode_entities($entry->content->body); print "summary:\n" . $sum_title . "\n\n" . $sum_text . "\n"; last; } } last if $uri ne ""; } if($uri eq "") { print "No Entry found from $bd - "; if($LAST_RUN) { print "giving up, manual import necessary!!!\n"; print "\n\n --> https://import.helsinki.at/shows/$show_id\n"; } else { print "will retry later\n"; } exit 1; } print "\n\nwill import '$uri' to show $show_id, $show_title\n\n"; my ($ret, $log) = rhautoimport::import_uri($show_id, $uri->as_string); if($ret) { print "\nImport Error:\n\n"; print $log; print "\n\nNot adding PV note!!"; exit 1; } print "\nImport Success:\n\n"; print $log; print "\n"; my $exit_code = 0; ($ret, $log) = rhautoimport::pv_add_note($sum_title, $sum_text, $PV_ID, $id, "1"); print $log; if($ret) { print "\nIgnoring failed note import - manual intervention necessary!\n"; $exit_code = 23; } unlink($STAT_FILE); open(my $fhs, '>', $STAT_FILE); print $fhs "$id\n$file"; close($fhs); exit $exit_code;