diff options
author | Christian Pointner <equinox@helsinki.at> | 2024-01-10 10:33:48 (GMT) |
---|---|---|
committer | Christian Pointner <equinox@helsinki.at> | 2024-01-10 10:33:48 (GMT) |
commit | 192c08b70372d6b54ad9e130f3195b092f2fb40c (patch) | |
tree | 8745226e8ee38e5714a310cd1b52eab7a7f8a472 /graveyard | |
parent | a81092d119a9996e71bc1e694edc38deaae247ab (diff) |
move a bunch of importers to graveyard
Diffstat (limited to 'graveyard')
-rw-r--r-- | graveyard/INFO | 52 | ||||
-rw-r--r-- | graveyard/cron.disabled | 32 | ||||
-rwxr-xr-x | graveyard/rhautoimport-ba | 212 | ||||
-rwxr-xr-x | graveyard/rhautoimport-btl | 178 | ||||
-rwxr-xr-x | graveyard/rhautoimport-cb | 208 | ||||
-rwxr-xr-x | graveyard/rhautoimport-dm | 212 | ||||
-rwxr-xr-x | graveyard/rhautoimport-lr | 226 | ||||
-rwxr-xr-x | graveyard/rhautoimport-mz | 212 |
8 files changed, 1332 insertions, 0 deletions
diff --git a/graveyard/INFO b/graveyard/INFO index 6ad5a78..cdf8b44 100644 --- a/graveyard/INFO +++ b/graveyard/INFO @@ -87,3 +87,55 @@ Upload: am selben Tag Such-Kriterium: cba:broadcastDate wenn gesetzt sonst cba:productionDate RH: wöchentlich, Freitag, 08:00-09:00 + +- (btl) Between the Lines + http://www.btlonline.org/rss/btl128.xml + + Original: wöchentlich Mittwochs + Upload: immer am selben Tag + Such-Kriterium: RSS Issue Date, 'broadcast-affiliate-version' im Dateinamen + es gibt wöchentlich neue Sendungen wir spielen jede zweite + RH: 2wöchentlich, Woche 2/4, Montag, 07:30-08:00 + +- (lr) literadio on air: + https://cba.media/podcast/aufdraht-literadio-on-air/feed + + Original: ohne System + Upload: ohne System + Such-Kriterium: neuester Eintrag der noch nicht importiert wurde + wenn am Freitag vor dem nächsten RH Termin kein neuer Eintrag + gefunden wird -> last attempt und nix importieren. + RH: 4wöchentlich, Woche 3, Dienstag, 16:30-17:00 + 4wöchentlich, Woche 2, Mittwoch, 14:30-15:00, Wiederholung + +- (dm) das mensch. gender_queer on air: + https://cba.media/podcast/das-mensch-gender_queer-on-air/feed + + Original: zweiter Donnerstag im Monat + Upload: meist 2-3 tage danach + Such-Kriterium: cba:broadcastDate wenn gesetzt sonst cba:productionDate + RH: 4wöchentlich, Woche 2, Dienstag, 13:00-14:00 + +- (ba) barrierefrei aufgerollt + https://cba.media/podcast/barrierefrei-aufgerollt/feed + + Original: erster Sonntag im Monat + Upload: "wir versuchen zwischen Montag und Mittwoch hochzuladen" + Such-Kriterium: cba:broadcastDate wenn gesetzt sonst cba:productionDate + RH: 4wöchentlich, Woche 2, Freitag, 17:00-17:30 + +- (cb) Crossing Borders + https://cba.media/podcast/crossing-borders/feed + + Original: erster Donnerstag im Monat + Upload: meistens 1-2 Tage später, (Ausreisser im Mai und Juni 2020 - aber erst 5 Termine insgesamt) + Such-Kriterium: cba:broadcastDate wenn gesetzt sonst cba:productionDate + RH: 4wöchentlich, Woche 1, Sonntag, 17:00-18:00 + +- (mz) Medienzirkus + https://cba.media/podcast/medienzirkus/feed + + Original: erster Freitag im Monat + Upload: am selben Tag, manchmal ein bis zwei Tage davor + Such-Kriterium: cba:broadcastDate wenn gesetzt sonst cba:productionDate + RH: 4wöchentlich, Woche 4, Freitag, 17:00-17:30 diff --git a/graveyard/cron.disabled b/graveyard/cron.disabled index 4de7141..e5af32f 100644 --- a/graveyard/cron.disabled +++ b/graveyard/cron.disabled @@ -60,3 +60,35 @@ 06 21,23 * * 3 autoimport /usr/bin/rhautoimport so 06 1,3,5 * * 4 autoimport /usr/bin/rhautoimport so 00 15 * * 4 autoimport /usr/bin/rhautoimport so last + +############## +Between the Lines (Sendung abgesetzt) +48 18,20,21 * * 3 autoimport /usr/bin/rhautoimport btl +48 0,2,4,6,18,20,21 * * 4-6 autoimport /usr/bin/rhautoimport btl +48 0,2,4,6,18,20 * * 7 autoimport /usr/bin/rhautoimport btl +48 21 * * 7 autoimport /usr/bin/rhautoimport btl last + +############## +# literadio on air +57 2,4,6 * * 4-7 autoimport /usr/bin/rhautoimport lr +57 8 * * 1 autoimport /usr/bin/rhautoimport lr last + +############## +# das mensch +06 2,4,6 * * 1-7 autoimport /usr/bin/rhautoimport dm +06 10 * * 2 autoimport /usr/bin/rhautoimport dm last + +############## +# barrierefrei aufgerollt (Sendung abgesetzt) +11 2,4,6 * * 1-7 autoimport /usr/bin/rhautoimport ba +11 12 * * 5 autoimport /usr/bin/rhautoimport ba last + +############## +# crossing borders (Sendung abgesetzt) +42 1,3,5 * * 1-7 autoimport /usr/bin/rhautoimport cb +42 17 * * 5 autoimport /usr/bin/rhautoimport cb last + +############## +# Medienzirkus (Sendung abgesetzt) +23 1,3,5 * * 1-7 autoimport /usr/bin/rhautoimport mz +23 11 * * 5 autoimport /usr/bin/rhautoimport mz last diff --git a/graveyard/rhautoimport-ba b/graveyard/rhautoimport-ba new file mode 100755 index 0000000..8fafe34 --- /dev/null +++ b/graveyard/rhautoimport-ba @@ -0,0 +1,212 @@ +#!/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-ba.stat"; +my $RSS_URL = "https://cba.media/podcast/barrierefrei-aufgerollt/feed"; +$XML::Feed::MULTIPLE_ENCLOSURES=1; +my $RD_GROUP = "baufgeroll"; +my $PV_ID = '774'; +my $TITLE = "barrierefrei aufgerollt"; +my $LAST_RUN = 0; +my $upload_delay_days = 3; # "we try to upload between Monday and Wednesday after the Show" + +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] = 5; +@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 > 5) { + @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], $import_date[1], 7, 1); +if(Date::Calc::Delta_Days(@broadcast_date, @import_date) <= 0) { + my @tmp_date = Date::Calc::Add_Delta_YM(@broadcast_date, 0, -1); + @broadcast_date = Date::Calc::Nth_Weekday_of_Month_Year($tmp_date[0], $tmp_date[1], 7, 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 (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.media/help#feeds'}{'broadcastDate'}; + my $format_string = "%a, %d %b %Y %H:%M:%S"; + unless (defined $entry_bdt) { + $entry_bdt = $entry->{'entry'}{'https://cba.media/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; diff --git a/graveyard/rhautoimport-btl b/graveyard/rhautoimport-btl new file mode 100755 index 0000000..6649e39 --- /dev/null +++ b/graveyard/rhautoimport-btl @@ -0,0 +1,178 @@ +#!/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-btl.stat"; +my $RSS_URL = "http://www.btlonline.org/rss/btl128.xml"; +my $RD_GROUP = "betweenlin"; +my $PV_ID = '221'; +my $TITLE="Between the Lines"; +my $LAST_RUN = 0; +my $upload_delay_days = 0; # files are usally there on the same day + +binmode(STDIN, ":utf8"); +binmode(STDOUT, ":utf8"); +binmode(STDERR, ":utf8"); + +my $curweek = RHRD::utils::get_rd_week(); +if($curweek == 2 || $curweek == 4) { + print "won't do anything in week 2 or 4!\n"; + rhautoimport::report_title_and_last($TITLE, 0); + exit 42; +} + +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 = $allowed_dbs[0]->{'SHOWTITLE'}; + +my @today = Date::Calc::Today(); +my @import_date = Date::Calc::Add_Delta_Days(@today, 7); +@import_date = Date::Calc::Standard_to_Business(@import_date); +$import_date[2] = 1; +@import_date = Date::Calc::Business_to_Standard(@import_date); + +my @broadcast_date = Date::Calc::Add_Delta_Days(@import_date, -5); + +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 "current broadcast cycle starts/started on: " . 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); +my $bdfile = ".*broadcast-affiliates?.*\.mp3"; + +print "looking for files issued on '$bd' and named like '$bdfile' in RSS Feed\n"; +print " -> $RSS_URL\n"; + +my ($result, $feed) = rhautoimport::fetch_parse_rss($RSS_URL); +unless ($result) { + print "Error fetching feed: $feed\n"; + exit 1; +} + +my $uri = ""; +my $file = ""; +my $sum_title = ""; +my $sum_text = ""; + +for my $entry ($feed->entries) { + if($entry->enclosure && ($entry->enclosure->type eq "audio/mpeg" || entry->enclosure->type eq "audio/mp3")) { + next unless $entry->enclosure->url =~ /$bdfile/; + + my $idt = DateTime::Format::Strptime::strptime("%Y-%m-%dT%H:%M:%S", $entry->issued); + next unless($broadcast_date[0] == $idt->year && $broadcast_date[1] == $idt->month && $broadcast_date[2] == $idt->day); + + $uri = new URI::URL($entry->enclosure->url); + my @path = $uri->path_components; + $file = $path[-1]; + + 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_title =~ s/ \(128 kbps\)$//; + $sum_title =~ s/ \(broadcast affiliate version\)//; + $sum_text = decode_entities($entry->content->body); + print "summary:\n" . $sum_title . "\n\n" . $sum_text . "\n"; + last; + } +} +if($uri eq "") { + print "No Entry found for " . Date::Calc::Date_to_Text(@broadcast_date) . " - "; + 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 $fhs "$file"; +close($fhs); + +exit $exit_code; diff --git a/graveyard/rhautoimport-cb b/graveyard/rhautoimport-cb new file mode 100755 index 0000000..3a8c73e --- /dev/null +++ b/graveyard/rhautoimport-cb @@ -0,0 +1,208 @@ +#!/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-cb.stat"; +my $RSS_URL = "https://cba.media/podcast/crossing-borders/feed"; +$XML::Feed::MULTIPLE_ENCLOSURES=1; +my $RD_GROUP = "crossingb"; +my $PV_ID = '809'; +my $TITLE = "Crossing Borders"; +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 == 1) { + 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] = 7; +@import_date = Date::Calc::Business_to_Standard(@import_date); + +my $dow = Date::Calc::Day_of_Week(@today); +if($curweek == 2) { + @import_date = Date::Calc::Add_Delta_Days(@import_date, 21); +} elsif($curweek == 3) { + @import_date = Date::Calc::Add_Delta_Days(@import_date, 14); +} else { + @import_date = Date::Calc::Add_Delta_Days(@import_date, 7); +} +print "day of next Radio Helsinki broadcast: " . Date::Calc::Date_to_Text(@import_date) . "\n"; + + +my @allowed_dbs = rhautoimport::get_dropboxes($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], $import_date[1], 4, 1); +if(Date::Calc::Delta_Days(@broadcast_date, @import_date) <= 0) { + my @tmp_date = Date::Calc::Add_Delta_YM(@broadcast_date, 0, -1); + @broadcast_date = Date::Calc::Nth_Weekday_of_Month_Year($tmp_date[0], $tmp_date[1], 4, 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 (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.media/help#feeds'}{'broadcastDate'}; + my $format_string = "%a, %d %b %Y %H:%M:%S"; + unless (defined $entry_bdt) { + $entry_bdt = $entry->{'entry'}{'https://cba.media/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; diff --git a/graveyard/rhautoimport-dm b/graveyard/rhautoimport-dm new file mode 100755 index 0000000..dae6ee7 --- /dev/null +++ b/graveyard/rhautoimport-dm @@ -0,0 +1,212 @@ +#!/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-dm.stat"; +my $RSS_URL = "https://cba.media/podcast/das-mensch-gender_queer-on-air/feed"; +$XML::Feed::MULTIPLE_ENCLOSURES=1; +my $RD_GROUP = "dasmensch"; +my $PV_ID = '669'; +my $TITLE = "das mensch. gender_queer on air"; +my $LAST_RUN = 0; +my $upload_delay_days = 2; # files are usally there at least 2-3 days after 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] = 2; +@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 > 2) { + @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], $import_date[1], 4, 2); +if(Date::Calc::Delta_Days(@broadcast_date, @import_date) <= 0) { + my @tmp_date = Date::Calc::Add_Delta_YM(@broadcast_date, 0, -1); + @broadcast_date = Date::Calc::Nth_Weekday_of_Month_Year($tmp_date[0], $tmp_date[1], 4, 2); +} +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.media/help#feeds'}{'broadcastDate'}; + my $format_string = "%a, %d %b %Y %H:%M:%S"; + unless (defined $entry_bdt) { + $entry_bdt = $entry->{'entry'}{'https://cba.media/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; diff --git a/graveyard/rhautoimport-lr b/graveyard/rhautoimport-lr new file mode 100755 index 0000000..14ff6f6 --- /dev/null +++ b/graveyard/rhautoimport-lr @@ -0,0 +1,226 @@ +#!/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-lr.stat"; +my $RSS_URL = "https://cba.media/podcast/aufdraht-literadio-on-air/feed"; +$XML::Feed::MULTIPLE_ENCLOSURES=1; +my $RD_GROUP = "literadio"; +my $PV_ID = '53'; +my $TITLE="literadio on air"; +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 @tmp = Date::Calc::Standard_to_Business(@today); +$tmp[2] = 2; +my @import_date = Date::Calc::Business_to_Standard(@tmp); + +my $curweek = RHRD::utils::get_rd_week(); +if($curweek == 2 && $today[2] >= 4) { + @import_date = Date::Calc::Add_Delta_Days(@import_date, 7); +} elsif($curweek == 3 && $today[2] == 1) { + @import_date = @import_date; # perl won't except an empty line here +} else { + print "File won't be available by now!\n"; + exit 42; +} +my @import_date_reb = Date::Calc::Add_Delta_Days(@import_date, 22); + +print "day of Radio Helsinki broadcast: " . Date::Calc::Date_to_Text(@import_date) . "\n"; +print "day of this show's rebroadcast: " . Date::Calc::Date_to_Text(@import_date_reb) . "\n"; + +my @reb_date_last = Date::Calc::Add_Delta_Days(@import_date_reb, -28); +print "day of last show's rebroadcast: " . Date::Calc::Date_to_Text(@reb_date_last) . "\n"; +if(Date::Calc::Delta_Days(@today, @reb_date_last) >= 0) { + print "the rebroadcast from last show has not been played yet!\n"; + exit 42; +} + +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 file for $id\n"; + exit 42; +} + +print "looking for files newer than '$current_file' 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 = $path[-1]; + + if($file eq $current_file) { + last; # no new entry + } + if(!rhautoimport::check_file_extension($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" . $sum_text . "\n"; + last; + } + } + last; # we are only intersted in the first entry +} +if($uri eq "") { + print "No new Entry found - "; + 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 $fhs "$id\n$file"; +close($fhs); + +exit $exit_code; diff --git a/graveyard/rhautoimport-mz b/graveyard/rhautoimport-mz new file mode 100755 index 0000000..60e2607 --- /dev/null +++ b/graveyard/rhautoimport-mz @@ -0,0 +1,212 @@ +#!/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-mz.stat"; +my $RSS_URL = "https://cba.media/podcast/medienzirkus/feed"; +$XML::Feed::MULTIPLE_ENCLOSURES=1; +my $RD_GROUP = "medienzi"; +my $PV_ID = '913'; +my $TITLE = "Medienzirkus"; +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 == 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] = 5; +@import_date = Date::Calc::Business_to_Standard(@import_date); + +my $dow = Date::Calc::Day_of_Week(@today); +if($curweek == 4) { + if($dow >= 5) { + @import_date = Date::Calc::Add_Delta_Days(@import_date, 28); + } +} elsif($curweek == 3) { + @import_date = Date::Calc::Add_Delta_Days(@import_date, 7); +} elsif($curweek == 2) { + @import_date = Date::Calc::Add_Delta_Days(@import_date, 14); +} else { + @import_date = Date::Calc::Add_Delta_Days(@import_date, 21); +} +print "day of next Radio Helsinki broadcast: " . Date::Calc::Date_to_Text(@import_date) . "\n"; + + +my @allowed_dbs = rhautoimport::get_dropboxes($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], $import_date[1], 5, 1); +if(Date::Calc::Delta_Days(@broadcast_date, @import_date) <= 0) { + my @tmp_date = Date::Calc::Add_Delta_YM(@broadcast_date, 0, -1); + @broadcast_date = Date::Calc::Nth_Weekday_of_Month_Year($tmp_date[0], $tmp_date[1], 5, 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 (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.media/help#feeds'}{'broadcastDate'}; + my $format_string = "%a, %d %b %Y %H:%M:%S"; + unless (defined $entry_bdt) { + $entry_bdt = $entry->{'entry'}{'https://cba.media/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; |