diff options
author | Christian Pointner <equinox@helsinki.at> | 2019-01-30 13:36:34 (GMT) |
---|---|---|
committer | Christian Pointner <equinox@helsinki.at> | 2019-01-30 13:36:34 (GMT) |
commit | d188f194c29c616b0a5366cbacd5eba052d121b1 (patch) | |
tree | 1fef26e92b4685746b6ba0319d0826bbd9a3cc90 /graveyard | |
parent | 01ff101609b75b59b55e9530073a74e83f527af6 (diff) |
moved old importer to graveyard
Diffstat (limited to 'graveyard')
-rw-r--r-- | graveyard/INFO | 17 | ||||
-rw-r--r-- | graveyard/cron.disabled | 28 | ||||
-rwxr-xr-x | graveyard/rhautoimport-dte | 205 | ||||
-rwxr-xr-x | graveyard/rhautoimport-er | 210 | ||||
-rwxr-xr-x | graveyard/rhautoimport-fb | 207 | ||||
-rwxr-xr-x | graveyard/rhautoimport-fl | 216 | ||||
-rwxr-xr-x | graveyard/rhautoimport-nw | 216 |
7 files changed, 1099 insertions, 0 deletions
diff --git a/graveyard/INFO b/graveyard/INFO new file mode 100644 index 0000000..f031b4a --- /dev/null +++ b/graveyard/INFO @@ -0,0 +1,17 @@ +- (dte) Die Toten Europas: + https://cba.fro.at/series/die-toten-europas/feed + + Original: abgeschlossene Reihe betehend aus 34 Episoden + Upload: bereits vollständig vorhanden + Such-Kriterium: fortlaufende Nummer in Titel und Dateiname + RH: wöchentlich, Dienstag 10:00-10:30 und Samstag 15:00-15:30 + keine Wiederholung + +- (fb) Fokus Bildung: + https://cba.fro.at/series/fokus-bildung-bildung-im-fokus/feed + + Original: erster Montag im Monat + Upload: immer ein paar Tage früher, meistens Fr + Such-Kriterium: cba:broadcastDate + nicht immer gesetzt!! (~1 von 5 mal) + RH: 4wöchentlich, Woche 2, Mittwoch, 14:30-15:00 diff --git a/graveyard/cron.disabled b/graveyard/cron.disabled new file mode 100644 index 0000000..00f9923 --- /dev/null +++ b/graveyard/cron.disabled @@ -0,0 +1,28 @@ +############## +# netwatcher +03 22 * * 6 autoimport /usr/bin/rhautoimport nw +03 1,3,5 * * 7 autoimport /usr/bin/rhautoimport nw +03 1,3,5 * * 1-2 autoimport /usr/bin/rhautoimport nw +03 1,3 * * 3 autoimport /usr/bin/rhautoimport nw +03 5 * * 3 autoimport /usr/bin/rhautoimport nw last + +############## +# Die Toten Europas +01 2,4,6 * * 1-7 autoimport /usr/bin/rhautoimport dte +01 9 * * 2 autoimport /usr/bin/rhautoimport dte last +01 9 * * 6 autoimport /usr/bin/rhautoimport dte last + +############## +# Ergo +09 2,4,6 * * 1-7 autoimport /usr/bin/rhautoimport er +09 10 * * 5 autoimport /usr/bin/rhautoimport er last + +############## +# Frequenz Leitwolf +17 2,4,6 * * 1-7 autoimport /usr/bin/rhautoimport fl +17 12 * * 6 autoimport /usr/bin/rhautoimport fl last + +############## +# Fokus Bildung +57 2,4,6 * * 1-7 autoimport /usr/bin/rhautoimport fb +57 9 * * 3 autoimport /usr/bin/rhautoimport fb last diff --git a/graveyard/rhautoimport-dte b/graveyard/rhautoimport-dte new file mode 100755 index 0000000..532cd01 --- /dev/null +++ b/graveyard/rhautoimport-dte @@ -0,0 +1,205 @@ +#!/usr/bin/perl -w +# +# +# rhautoimport +# +# Copyright (C) 2009-2018 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 XML::Feed; +use XML::Feed::Entry; +use XML::Feed::Content; +use XML::Feed::Enclosure; +use URI::URL; +use HTML::Entities; +use RHRD::utils; + +use lib '/usr/local/share/rhautoimport/'; +use rhautoimport; + +my $STAT_FILE = $ENV{'HOME'} . "/rhautoimport-dte.stat"; +my $LAST_FILE = $ENV{'HOME'} . "/rhautoimport-dte.last"; +my $RSS_URL = "https://cba.fro.at/series/die-toten-europas/feed"; +$XML::Feed::MULTIPLE_ENCLOSURES=1; +my $RD_GROUP = "dietoteneu"; +my $RD_CART_TU = 118201; +my $RD_CART_SA = 118204; +my $PV_ID = '719'; +my $TITLE="Die Toten Europas"; +my $LAST_RUN = 0; + +binmode(STDIN, ":utf8"); +binmode(STDOUT, ":utf8"); +binmode(STDERR, ":utf8"); + +if($#ARGV >= 0 && $ARGV[0] eq 'last') { + print "!!!This is the last attempt, there won't be a retry on error!!!\n"; + $LAST_RUN = 1; +} +rhautoimport::report_title_and_last($TITLE, $LAST_RUN); + +my @allowed_dbs = rhautoimport::get_dropboxes($RD_GROUP); +if(!defined $allowed_dbs[0] && defined $allowed_dbs[1]) { + print "$allowed_dbs[1]\n"; + exit 1; +} +if(scalar(@allowed_dbs) != 2) { + print "found more or less than two Dropboxes for this group?!\n"; + exit 1; +} +my $idx_tu = 0; +my $idx_sa = 1; +if($allowed_dbs[0]->{'SHOWDOW'} != 2) { + $idx_sa = 0; + $idx_tu = 1; +} + +my $show_id = 0; +my $show_title = ""; +my $rd_cart = 0; + +my @today = Date::Calc::Today(); +my $dow = Date::Calc::Day_of_Week(@today); +my @import_date = Date::Calc::Standard_to_Business(@today); + +if($dow <= 2 || $dow > 6) { + $show_id = $allowed_dbs[$idx_tu]->{'SHOWID'}; + $show_title = $allowed_dbs[$idx_tu]->{'SHOWTITLE'}; + $rd_cart=$RD_CART_TU; + $import_date[2] = 2; +} else { + $show_id = $allowed_dbs[$idx_sa]->{'SHOWID'}; + $show_title = $allowed_dbs[$idx_sa]->{'SHOWTITLE'}; + $rd_cart=$RD_CART_SA; + $import_date[2] = 6; +} + +@import_date = Date::Calc::Business_to_Standard(@import_date); +if($dow > 6) { + @import_date = Date::Calc::Add_Delta_Days(@import_date, 7); +} + +my $broadcast_num = `cat $LAST_FILE`; +$broadcast_num += 1; +my $bdfileexp = sprintf("^%02d-", $broadcast_num); + +print "today: " . Date::Calc::Date_to_Text(@today) . "\n"; +print "day of next Radio Helsinki broadcast: " . Date::Calc::Date_to_Text(@import_date) . "\n"; +print "Number of next broadcast: " . $broadcast_num . "\n\n"; + +my $id = sprintf("%04d-%02d-%02d", @import_date); + +my $current_stat = `cat $STAT_FILE`; +my ($current_id, $current_file) = $current_stat =~ m/^(.*)\n(.*)/; +if($current_id eq $id) { + print "Already downloaded current file\n"; + exit 42; +} + +print "looking for file #$broadcast_num using $bdfileexp in RSS Feed\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 $j = 0; + for my $enclosure($entry->enclosure) { + $j++; + if($enclosure->type eq "audio/mpeg" || $enclosure->type eq "audio/ogg") { + my $orig_uri = $enclosure->url; + if($orig_uri =~ /^(.*)_cut(\.[^\.]+)$/) { + $orig_uri = $1 . $2; + } + + $sum_title = decode_entities($entry->title); + $sum_text = decode_entities($entry->content->body); + $uri = new URI::URL($orig_uri); + my @path = $uri->path_components; + $file = $path[-1]; + unless ($file =~ /$bdfileexp/) { + $uri = ""; + } + + if(!rhautoimport::check_file_extension($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; + } + + last; + } + } + last if $uri ne ""; +} +if($uri eq "") { + print "No Entry for #$broadcast_num (there are no more shows available) - "; + if($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; +} + +my $exit_code = 0; +print "summary:\n" . $sum_title . "\n\n" . $sum_text . "\n"; +print "\n\nwill import '$uri' to show $show_id, $show_title at cart $rd_cart\n\n"; + +my ($ret, $log) = rhautoimport::import_uri($show_id, $uri->as_string, undef, $rd_cart); +if($ret) { + print "\nImport Error:\n\n"; + print $log; + print "\n\nNot adding PV note!!"; + exit 1; +} +print "\nImport Success:\n\n"; +print $log; +print "\n"; +($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); + +unlink($LAST_FILE); +open($fhs, '>', $LAST_FILE); +print $fhs "$broadcast_num"; +close($fhs); + +exit $exit_code; diff --git a/graveyard/rhautoimport-er b/graveyard/rhautoimport-er new file mode 100755 index 0000000..52dd24b --- /dev/null +++ b/graveyard/rhautoimport-er @@ -0,0 +1,210 @@ +#!/usr/bin/perl -w +# +# +# rhautoimport +# +# Copyright (C) 2009-2017 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 XML::Feed; +use XML::Feed::Entry; +use XML::Feed::Content; +use XML::Feed::Enclosure; +use URI::URL; +use HTML::Entities; +use RHRD::utils; + +use lib '/usr/local/share/rhautoimport/'; +use rhautoimport; + +my $STAT_FILE = $ENV{'HOME'} . "/rhautoimport-er.stat"; +my $LAST_FILE = $ENV{'HOME'} . "/rhautoimport-er.last"; +my $RSS_URL = "https://cba.fro.at/series/ergo/feed"; +$XML::Feed::MULTIPLE_ENCLOSURES=1; +my $RD_GROUP = "ergo"; +my $PV_ID = '569'; +my $TITLE="Ergo"; +my $LAST_RUN = 0; + +binmode(STDIN, ":utf8"); +binmode(STDOUT, ":utf8"); +binmode(STDERR, ":utf8"); + +my $curweek = RHRD::utils::get_rd_week(); + +if($curweek == 1 || $curweek == 3) { + if($#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, $LAST_RUN); + + +my @allowed_dbs = rhautoimport::get_dropboxes($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 = $allowed_dbs[0]->{'SHOWTITLE'}; + +my @today = Date::Calc::Today(); +my @import_date = Date::Calc::Standard_to_Business(@today); +$import_date[2] = 5; +@import_date = Date::Calc::Business_to_Standard(@import_date); + +my $dow = Date::Calc::Day_of_Week(@today); +if($curweek == 1 || $curweek == 3) { + if($dow > 5) { + @import_date = Date::Calc::Add_Delta_Days(@import_date, 14); + } +} else { + @import_date = Date::Calc::Add_Delta_Days(@import_date, 7); +} +my $broadcast_num = `cat $LAST_FILE`; +$broadcast_num += 1; + +print "today: " . Date::Calc::Date_to_Text(@today) . " (Week: " . $curweek . ")\n"; +print "day of next Radio Helsinki broadcast: " . Date::Calc::Date_to_Text(@import_date) . "\n"; +print "Number of next broadcast: " . $broadcast_num . "\n\n"; + +my $id = sprintf("%04d-%02d-%02d", @import_date); + +my $current_stat = `cat $STAT_FILE`; +my ($current_id, $current_file) = $current_stat =~ m/^(.*)\n(.*)/; +if($current_id eq $id) { + print "Already downloaded current file\n"; + exit 42; +} + +print "looking for file #$broadcast_num in RSS Feed\n"; +print " -> $RSS_URL\n"; + +my $bdnumexp = "^Ergo\\s+#(\\d+)\\s*:"; + +my ($result, $feed) = rhautoimport::fetch_parse_rss_cba($RSS_URL); +unless ($result) { + print "Error fetching feed: $feed\n"; + exit 1; +} + +my $max_broadcast_num = $broadcast_num; +my $uri = ""; +my $file = ""; +my $sum_title = ""; +my $sum_text = ""; + +my $i = 0; +for my $entry ($feed->entries) { + $i++; + next unless $entry->enclosure; + my $j = 0; + for my $enclosure($entry->enclosure) { + $j++; + if($enclosure->type eq "audio/mpeg" || $enclosure->type eq "audio/ogg") { + my $orig_uri = $enclosure->url; + if($orig_uri =~ /^(.*)_cut(\.[^\.]+)$/) { + $orig_uri = $1 . $2; + } + + $sum_title = decode_entities($entry->title); + next unless $sum_title =~ /$bdnumexp/; + + if($max_broadcast_num < $1) { + $max_broadcast_num = $1; + } + next if $broadcast_num != $1; + + $sum_text = decode_entities($entry->content->body); + $uri = new URI::URL($orig_uri); + my @path = $uri->path_components; + $file = $path[-1]; + + if(!rhautoimport::check_file_extension($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; + } + + last; + } + } + last if $uri ne ""; +} +if($uri eq "") { + print "No Entry for #$broadcast_num (there are no new shows available) - "; + if($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; +} + +my $exit_code = 0; +my $shows_left = $max_broadcast_num - $broadcast_num; +if($shows_left <= 0) { + print "\n ****** There are *no* shows remaining! ******\n\n"; + $exit_code = 23 +} elsif($shows_left < 3) { + print "\n ** There are only $shows_left shows remaining! **\n\n"; + $exit_code = 23; +} else { + print "\nThere are $shows_left shows remaining\n\n"; +} + +print "summary:\n" . $sum_title . "\n\n" . $sum_text . "\n"; +print "\n\nwill import '$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 $log; +print "\n"; +($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); + +unlink($LAST_FILE); +open($fhs, '>', $LAST_FILE); +print $fhs "$broadcast_num"; +close($fhs); + +exit $exit_code; diff --git a/graveyard/rhautoimport-fb b/graveyard/rhautoimport-fb new file mode 100755 index 0000000..917ddf5 --- /dev/null +++ b/graveyard/rhautoimport-fb @@ -0,0 +1,207 @@ +#!/usr/bin/perl -w +# +# +# rhautoimport +# +# Copyright (C) 2009-2017 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 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 RHRD::utils; + +use lib '/usr/local/share/rhautoimport/'; +use rhautoimport; + +my $STAT_FILE = $ENV{'HOME'} . "/rhautoimport-fb.stat"; +my $RSS_URL = "https://cba.fro.at/series/fokus-bildung-bildung-im-fokus/feed"; +$XML::Feed::MULTIPLE_ENCLOSURES=1; +my $RD_GROUP = "fokusbildu"; +my $PV_ID = '488'; +my $TITLE = "Fokus Bildung"; +my $LAST_RUN = 0; +my $upload_delay_days = -3; # files are usally there at least 3 days before original broadcast + +binmode(STDIN, ":utf8"); +binmode(STDOUT, ":utf8"); +binmode(STDERR, ":utf8"); + +my $curweek = RHRD::utils::get_rd_week(); + +if($curweek == 2) { + 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] = 3; +@import_date = Date::Calc::Business_to_Standard(@import_date); + +my $dow = Date::Calc::Day_of_Week(@today); +if($curweek == 1) { + @import_date = Date::Calc::Add_Delta_Days(@import_date, 7); +} elsif($curweek == 2) { + if($dow > 3) { + @import_date = Date::Calc::Add_Delta_Days(@import_date, 28); + } +} elsif($curweek == 3) { + @import_date = Date::Calc::Add_Delta_Days(@import_date, 21); +} else { + @import_date = Date::Calc::Add_Delta_Days(@import_date, 14); +} +print "day of next Radio Helsinki broadcast: " . Date::Calc::Date_to_Text(@import_date) . "\n"; + + +my @allowed_dbs = rhautoimport::get_dropboxes($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 = $allowed_dbs[0]->{'SHOWTITLE'}; + +my @broadcast_date = Date::Calc::Nth_Weekday_of_Month_Year($import_date[0], $import_date[1], 1, 1); +if(Date::Calc::Delta_Days(@broadcast_date, @import_date) <= 0) { + my @tmp_date = Date::Calc::Add_Delta_YM(@broadcast_date, 0, -1); + @broadcast_date = Date::Calc::Nth_Weekday_of_Month_Year($tmp_date[0], $tmp_date[1], 1, 1); +} +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\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'}; + 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 $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; diff --git a/graveyard/rhautoimport-fl b/graveyard/rhautoimport-fl new file mode 100755 index 0000000..1080cc1 --- /dev/null +++ b/graveyard/rhautoimport-fl @@ -0,0 +1,216 @@ +#!/usr/bin/perl -w +# +# +# rhautoimport +# +# Copyright (C) 2009-2017 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 DateTime; +use DateTime::Format::ISO8601; +use XML::Feed; +use XML::Feed::Entry; +use XML::Feed::Content; +use XML::Feed::Enclosure; +use URI::URL; +use HTML::Entities; +use RHRD::utils; + +use lib '/usr/local/share/rhautoimport/'; +use rhautoimport; + +my $STAT_FILE = $ENV{'HOME'} . "/rhautoimport-fl.stat"; +my $LAST_FILE = $ENV{'HOME'} . "/rhautoimport-fl.last"; +my $RSS_URL = "https://cba.fro.at/series/frequenz-leitwolf/feed"; +$XML::Feed::MULTIPLE_ENCLOSURES=1; +my $RD_GROUP = "leitwolf"; +my $PV_ID = '571'; +my $TITLE="Frequenz Leitwolf"; +my $LAST_RUN = 0; + +binmode(STDIN, ":utf8"); +binmode(STDOUT, ":utf8"); +binmode(STDERR, ":utf8"); + +my $curweek = RHRD::utils::get_rd_week(); + +if($curweek == 1 || $curweek == 3) { + if($#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, $LAST_RUN); + + +my @allowed_dbs = rhautoimport::get_dropboxes($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 = $allowed_dbs[0]->{'SHOWTITLE'}; + +my @today = Date::Calc::Today(); +my @import_date = Date::Calc::Standard_to_Business(@today); +$import_date[2] = 6; +@import_date = Date::Calc::Business_to_Standard(@import_date); + +my $dow = Date::Calc::Day_of_Week(@today); +if($curweek == 1 || $curweek == 3) { + if($dow > 6) { + @import_date = Date::Calc::Add_Delta_Days(@import_date, 14); + } +} else { + @import_date = Date::Calc::Add_Delta_Days(@import_date, 7); +} +my $last_broadcast = DateTime->from_epoch(epoch => 0); +my $last_broadcast_str = `cat $LAST_FILE`; +chomp($last_broadcast_str); +if(defined($last_broadcast_str) && $last_broadcast_str ne "") { + $last_broadcast = DateTime::Format::ISO8601->parse_datetime($last_broadcast_str); +} + +print "today: " . Date::Calc::Date_to_Text(@today) . " (Week: " . $curweek . ")\n"; +print "day of next Radio Helsinki broadcast: " . Date::Calc::Date_to_Text(@import_date) . "\n"; +print "Last broadcast was on: " . $last_broadcast . "\n\n"; + +my $id = sprintf("%04d-%02d-%02d", @import_date); + +my $current_stat = `cat $STAT_FILE`; +my ($current_id, $current_file) = $current_stat =~ m/^(.*)\n(.*)/; +if($current_id eq $id) { + print "Already downloaded current file\n"; + exit 42; +} + +print "looking for file after $last_broadcast in RSS Feed\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 $shows_left = -1; +my $uri = ""; +my $file = ""; +my $sum_title = ""; +my $sum_text = ""; +my $this_broadcast = $last_broadcast; + +my $i = 0; +for my $entry ($feed->entries) { + $i++; + next unless $entry->enclosure; + + my $issued = $entry->issued; + next unless (defined $issued); + my $idt = DateTime::Format::ISO8601->parse_datetime($issued); + + my $diff = $idt->subtract_datetime_absolute($last_broadcast); + last if($diff->is_zero || $diff->is_negative); + + $shows_left++; + $sum_title = decode_entities($entry->title); + $sum_text = decode_entities($entry->content->body); + my $j = 0; + for my $enclosure($entry->enclosure) { + $j++; + if($enclosure->type eq "audio/mpeg" || $enclosure->type eq "audio/ogg") { + 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 = $path[-1]; + + if(!rhautoimport::check_file_extension($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; + } + + $this_broadcast = $idt; + last; + } + } +} +if($uri eq "") { + print "No Entry for $last_broadcast (there are no new shows available) - "; + if($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; +} + +my $exit_code = 0; +if($shows_left <= 0) { + print "\n ****** There are *no* shows remaining! ******\n\n"; + $exit_code = 23 +} elsif($shows_left < 4) { + print "\n ** There are only $shows_left shows remaining! **\n\n"; + $exit_code = 23; +} else { + print "\nThere are $shows_left shows remaining\n\n"; +} + +print "summary:\n" . $sum_title . "\n\n" . $sum_text . "\n"; +print "\n\nwill import '$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 $log; +print "\n"; +($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); + +unlink($LAST_FILE); +open($fhs, '>', $LAST_FILE); +print $fhs $this_broadcast->iso8601(); +close($fhs); + +exit $exit_code; diff --git a/graveyard/rhautoimport-nw b/graveyard/rhautoimport-nw new file mode 100755 index 0000000..e24a998 --- /dev/null +++ b/graveyard/rhautoimport-nw @@ -0,0 +1,216 @@ +#!/usr/bin/perl -w +# +# +# rhautoimport +# +# Copyright (C) 2009-2017 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 XML::Feed; +use XML::Feed::Entry; +use XML::Feed::Content; +use XML::Feed::Enclosure; +use URI::URL; +use HTML::Entities; + +use lib '/usr/local/share/rhautoimport/'; +use rhautoimport; + +my $STAT_FILE = $ENV{'HOME'} . "/rhautoimport-nw.stat"; +my $RSS_URL = "https://cba.fro.at/series/radio-netwatcher/feed"; +$XML::Feed::MULTIPLE_ENCLOSURES=1; +my $RD_GROUP = "netwatcher"; +my $PV_ID = '73'; +my $TITLE="netwatcher"; +my $LAST_RUN = 0; + +binmode(STDIN, ":utf8"); +binmode(STDOUT, ":utf8"); +binmode(STDERR, ":utf8"); + +if($#ARGV >= 0 && $ARGV[0] eq 'last') { + print "!!!This is the last attempt, there won't be a retry on error!!!\n"; + $LAST_RUN = 1; +} +rhautoimport::report_title_and_last($TITLE, $LAST_RUN); + + +my @allowed_dbs = rhautoimport::get_dropboxes($RD_GROUP); +if(!defined $allowed_dbs[0] && defined $allowed_dbs[1]) { + print "$allowed_dbs[1]\n"; + exit 1; +} + +my $idx = 0; +my $idx_reb = 1; +if(scalar(@allowed_dbs) != 2) { + print "found more or less than 2 Dropboxes for this group?!\n"; + exit 1; +} +my $show_id = $allowed_dbs[$idx]->{'SHOWID'}; +my $show_title = $allowed_dbs[$idx]->{'SHOWTITLE'}; +my $show_id_reb = $allowed_dbs[$idx_reb]->{'SHOWID'}; +my $show_title_reb = $allowed_dbs[$idx_reb]->{'SHOWTITLE'}; + + +my @today = Date::Calc::Today(); + +my @import_date = @today; +if( Date::Calc::Day_of_Week(@today) > 3 ) { + @import_date = Date::Calc::Add_Delta_Days(@import_date, 7); +} +if( Date::Calc::Day_of_Week(@today) != 3 ) { + @import_date = Date::Calc::Standard_to_Business(@import_date); + $import_date[2] = 3; + @import_date = Date::Calc::Business_to_Standard(@import_date); +} +my @broadcast_day = Date::Calc::Add_Delta_Days(@import_date, -5); +my @import_date_reb = Date::Calc::Add_Delta_Days(@import_date, 3); +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_date) . "\n"; +print "day of Radio Helsinki rebroadcast: " . Date::Calc::Date_to_Text(@import_date_reb) . "\n"; + +my $id = sprintf("%04d-%02d-%02d", @import_date); +my $bd = sprintf("%04d-%02d-%02d", @broadcast_day); +my $bdfile = sprintf("NETWATCHER[-_]?%04d%02d%02d(.*)\.MP3", @broadcast_day); + +print "looking for files like '$bdfile' in RSS Feed\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 $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 = $path[-1]; + unless(uc($file) =~ $bdfile) { # file not from correct day + $uri = ""; + next; + } + + my $current_file = `cat $STAT_FILE`; + if($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; +} + +my $exit_code = 0; +print "\n\nwill import '$uri' to show $show_id, $show_title\n"; +my ($ret, $log, $keptfile_uri) = rhautoimport::import_uri($show_id, $uri->as_string, "keep"); +if($ret == 0) { + print "\nImport Success:\n\n"; + print $log; + print "\n"; + ($ret, $log) = rhautoimport::pv_add_note($sum_title, $sum_text, $PV_ID, sprintf("%04d-%02d-%02d", @import_date), "1"); + print $log; + if($ret) { + print "\nIgnoring failed note import - manual intervention necessary!\n"; + $exit_code = 23; + } + + print "\n"; + + if(!defined($keptfile_uri)) { + print "rhimportd didn't provide a clue where to find the kept file... will import '$uri' to rebroadcast $show_id_reb, $show_title_reb\n"; + ($ret, $log) = rhautoimport::import_uri($show_id_reb, $uri->as_string); + } else { + print "re-using kept file '$keptfile_uri' to import rebroadcast $show_id_reb, $show_title_reb\n"; + ($ret, $log) = rhautoimport::import_uri($show_id_reb, $keptfile_uri, "delete"); + } + + if($ret == 0) { + print "\nImport Success:\n\n"; + print $log; + print "\n"; + ($ret, $log) = rhautoimport::pv_add_note($sum_title, $sum_text, $PV_ID, sprintf("%04d-%02d-%02d", @import_date_reb), "2"); + print $log; + if($ret) { + print "\nIgnoring failed note import - manual intervention necessary!\n"; + $exit_code = 23; + } + + } else { + print "\nImport Error:\n\n"; + print $log; + print "\n\nNot adding PV note!!"; + print "\n\nSince the import for the regular broadcast went through we will not retry this import!!!"; + print "\nYou need to manually import the rebroadcast."; + print "\n\n --> https://import.helsinki.at/shows/$show_id_reb\n"; + $exit_code = 23; + } +} else { + print "\nImport Error:\n\n"; + print $log; + print "\n\nNot adding PV note!!"; + exit 1; +} + +unlink($STAT_FILE); +open(my $fhs, '>', $STAT_FILE); +print $fhs "$file"; +close($fhs); + +exit $exit_code; |