| 1 | =head1 NAME | ||
| 2 | |||
| 3 | StreamFinder::SermonAudio - Fetch actual raw streamable URLs on sermonaudio.com. | ||
| 4 | |||
| 5 | =head1 AUTHOR | ||
| 6 | |||
| 7 | This module is Copyright (C) 2021-2026 by | ||
| 8 | |||
| 9 | Jim Turner, C<< <turnerjw784 at yahoo.com> >> | ||
| 10 | |||
| 11 | Email: turnerjw784@yahoo.com | ||
| 12 | |||
| 13 | All rights reserved. | ||
| 14 | |||
| 15 | You may distribute this module under the terms of either the GNU General | ||
| 16 | Public License or the Artistic License, as specified in the Perl README | ||
| 17 | file. | ||
| 18 | |||
| 19 | =head1 SYNOPSIS | ||
| 20 | |||
| 21 | #!/usr/bin/perl | ||
| 22 | |||
| 23 | use strict; | ||
| 24 | |||
| 25 | use StreamFinder::SermonAudio; | ||
| 26 | |||
| 27 | die "..usage: $0 ID|URL\n" unless ($ARGV[0]); | ||
| 28 | |||
| 29 | my $podcast = new StreamFinder::SermonAudio($ARGV[0]); | ||
| 30 | |||
| 31 | die "Invalid URL or no streams found!\n" unless ($podcast); | ||
| 32 | |||
| 33 | my $firstStream = $podcast->get(); | ||
| 34 | |||
| 35 | print "First Stream URL=$firstStream\n"; | ||
| 36 | |||
| 37 | my $url = $podcast->getURL(); | ||
| 38 | |||
| 39 | print "Stream URL=$url\n"; | ||
| 40 | |||
| 41 | my $podcastTitle = $podcast->getTitle(); | ||
| 42 | |||
| 43 | print "Title=$podcastTitle\n"; | ||
| 44 | |||
| 45 | my $podcastDescription = $podcast->getTitle('desc'); | ||
| 46 | |||
| 47 | print "Description=$podcastDescription\n"; | ||
| 48 | |||
| 49 | my $podcastID = $podcast->getID(); | ||
| 50 | |||
| 51 | print "Podcast ID=$podcastID\n"; | ||
| 52 | |||
| 53 | my $icon_url = $podcast->getIconURL(); | ||
| 54 | |||
| 55 | if ($icon_url) { #SAVE THE ICON TO A TEMP. FILE: | ||
| 56 | |||
| 57 | print "Icon URL=$icon_url=\n"; | ||
| 58 | |||
| 59 | my ($image_ext, $icon_image) = $podcast->getIconData(); | ||
| 60 | |||
| 61 | if ($icon_image && open IMGOUT, ">/tmp/${podcastID}.$image_ext") { | ||
| 62 | |||
| 63 | binmode IMGOUT; | ||
| 64 | |||
| 65 | print IMGOUT $icon_image; | ||
| 66 | |||
| 67 | close IMGOUT; | ||
| 68 | |||
| 69 | print "...Icon image downloaded to (/tmp/${podcastID}.$image_ext)\n"; | ||
| 70 | |||
| 71 | } | ||
| 72 | |||
| 73 | } | ||
| 74 | |||
| 75 | my $stream_count = $podcast->count(); | ||
| 76 | |||
| 77 | print "--Stream count=$stream_count=\n"; | ||
| 78 | |||
| 79 | my @streams = $podcast->get(); | ||
| 80 | |||
| 81 | foreach my $s (@streams) { | ||
| 82 | |||
| 83 | print "------ stream URL=$s=\n"; | ||
| 84 | |||
| 85 | } | ||
| 86 | |||
| 87 | =head1 DESCRIPTION | ||
| 88 | |||
| 89 | StreamFinder::SermonAudio accepts a valid podcast (sermon) ID or URL on | ||
| 90 | SermonAudio.com and returns the actual stream URL(s), title, and cover art | ||
| 91 | icon. The purpose is that one needs one of these URLs in order to have the | ||
| 92 | option to stream the podcast in one's own choice of media player software | ||
| 93 | rather than using their web browser and accepting any / all flash, ads, | ||
| 94 | javascript, cookies, trackers, web-bugs, and other crapware that can come with | ||
| 95 | that method of play. The author uses his own custom all-purpose media player | ||
| 96 | called "fauxdacious" (his custom hacked version of the open-source "audacious" | ||
| 97 | audio player). "fauxdacious" can incorporate this module to decode and play | ||
| 98 | SermonAudio.com streams. | ||
| 99 | |||
| 100 | One or more stream URLs can be returned for each podcast. | ||
| 101 | |||
| 102 | =head1 SUBROUTINES/METHODS | ||
| 103 | |||
| 104 | =over 4 | ||
| 105 | |||
| 106 | =item B<new>(I<ID>|I<url> [, I<-quality> => audio|any ] | ||
| 107 | [, I<-speakericon> [ => 0|1 ]] [, I<-secure> [ => 0|1 ]] | ||
| 108 | [, I<-notrim> [ => 0|1 ]] [, I<-nowebp> [ => 0|1 ]] | ||
| 109 | [, I<-debug> [ => 0|1|2 ]]) | ||
| 110 | |||
| 111 | Accepts a www.sermonaudio.com podcast (sermon) ID or URL and creates and | ||
| 112 | returns a a new podcast object, or I<undef> if the URL is not a valid podcast, | ||
| 113 | or no streams are found. The URL can be the full URL, ie. | ||
| 114 | https://www.sermonaudio.com/sermons/B<sermon-id>, | ||
| 115 | https://www.sermonaudio.com/speakers/B<speaker-id>, | ||
| 116 | https://www.sermonaudio.com/broadcasters/B<church-id>, | ||
| 117 | https://www.sermonaudio.com/series/B<series-id>, | ||
| 118 | https://www.sermonaudio.com/sermoninfo.asp?SID=B<id>, | ||
| 119 | https://www.sermonaudio.com/source_detail.asp?sourceid=B<source-id>, | ||
| 120 | or just I<sermon-id> (>8 digits), I<speaker-id> (5 digits), | ||
| 121 | I<series-id> (6 digits), or I<church-id> (alphanumeric). | ||
| 122 | |||
| 123 | The optional I<-quality> argument, can be set to either "audio", | ||
| 124 | or "any". "audio" means only accept audio streams, "any" or "all" | ||
| 125 | (any other value) means accept both video and audio streams found | ||
| 126 | (subject to the I<-secure> argument, if specified). Unless "audio" is | ||
| 127 | specified, and any video stream is accepted (subject to the above limitations), | ||
| 128 | then the "best" stream returned will be video (video streams are by default | ||
| 129 | favored over audio). Note: "high" and "low" are no longer used in v2.41+, | ||
| 130 | as now only a single video stream is returned in HLS format (users should | ||
| 131 | use "hls_bitrate" config file option to limit video stream bandwidth. | ||
| 132 | |||
| 133 | DEFAULT I<-quality> is "I<any>": (accept both video and audio streams). | ||
| 134 | |||
| 135 | The optional I<-speakericon> argument can be set to reverse the artist | ||
| 136 | (channel) icon and artist image, usually resulting in the artist icon being a | ||
| 137 | photo of the preacher, instead of his church's thumbnail icon. | ||
| 138 | |||
| 139 | DEFAULT I<-speakericon> is 0 (I<false>): Don't reverse the artist icon and image. | ||
| 140 | |||
| 141 | The optional I<-secure> argument can be either 0 or 1 (I<false> or I<true>). | ||
| 142 | If 1 then only secure ("https://") streams will be returned. | ||
| 143 | |||
| 144 | DEFAULT I<-secure> is 0 (false) - return all streams (http and https). | ||
| 145 | |||
| 146 | The optional I<-notrim> argument can be either 0 or 1 (I<false> or I<true>). | ||
| 147 | If 0 (I<false>) then stream URLs are trimmed of excess "ad" parameters | ||
| 148 | (everything after the first "?" character, ie. "?ads.cust_params=premium" is | ||
| 149 | removed, including the "?". Otherwise, the stream URLs are returned as-is. | ||
| 150 | |||
| 151 | DEFAULT I<-notrim> is 0 (I<false>) and URLs are trimmed. If | ||
| 152 | I<-notrim> is specified without argument, the default is 1 (I<true>). Try | ||
| 153 | using I<-notrim> if stream will not play without the extra arguments. | ||
| 154 | |||
| 155 | Note: -notrim = 0 will not trim the "webp=true" portion of icon / image URLs | ||
| 156 | unless -nowebp is set to 1. | ||
| 157 | |||
| 158 | The optional I<-nowebp> argument can be either 0 or 1 (I<false> or I<true>). | ||
| 159 | If 1 then image files specified as "img.{png|jpg|jpeg|gif}?webp=true" are | ||
| 160 | stripped of the "?webp=true" part which causes them to be downloaded in | ||
| 161 | their native format instead of webp. This is needed by the GTK versions | ||
| 162 | of Fauxdacious. | ||
| 163 | |||
| 164 | DEFAULT I<-nowebp> is 0 (I<false>): Download webp images as webp. | ||
| 165 | |||
| 166 | Additional options: | ||
| 167 | |||
| 168 | I<-log> => "I<logfile>" | ||
| 169 | |||
| 170 | Specify path to a log file. If a valid and writable file is specified, A line | ||
| 171 | will be appended to this file every time one or more streams is successfully | ||
| 172 | fetched for a url. | ||
| 173 | |||
| 174 | DEFAULT I<-none-> (no logging). | ||
| 175 | |||
| 176 | I<-logfmt> specifies a format string for lines written to the log file. | ||
| 177 | |||
| 178 | DEFAULT "I<[time] [url] - [site]: [title] ([total])>". | ||
| 179 | |||
| 180 | The valid field I<[variables]> are: [stream]: The url of the first/best stream | ||
| 181 | found. [site]: The site name (SermonAudio). [url]: The url searched for | ||
| 182 | streams. [time]: Perl timestamp when the line was logged. [title], [artist], | ||
| 183 | [album], [description], [year], [genre], [total], [albumartist]: | ||
| 184 | The corresponding field data returned (or "I<-na->", if no value). | ||
| 185 | |||
| 186 | =item $podcast->B<get>() | ||
| 187 | |||
| 188 | Returns an array of strings representing all stream URLs found. | ||
| 189 | |||
| 190 | =item $podcast->B<getURL>([I<options>]) | ||
| 191 | |||
| 192 | Similar to B<get>() except it only returns a single stream representing | ||
| 193 | the first valid stream found. There currently are no valid I<options>. | ||
| 194 | |||
| 195 | =item $podcast->B<count>() | ||
| 196 | |||
| 197 | Returns the number of streams found for the podcast. | ||
| 198 | |||
| 199 | =item $podcast->B<getID>() | ||
| 200 | |||
| 201 | Returns the podcast's SermonAudio ID (default). For podcasts, the SermonAudio | ||
| 202 | ID is a single value. For individual podcast episodes it's two values | ||
| 203 | separated by a slash ("/"). | ||
| 204 | |||
| 205 | =item $podcast->B<getTitle>(['desc']) | ||
| 206 | |||
| 207 | Returns the podcast's title, or (long description). Podcasts | ||
| 208 | on SermonAudio can have separate descriptions, but for podcasts, | ||
| 209 | it is always the podcast's title. | ||
| 210 | |||
| 211 | =item $podcast->B<getIconURL>(['artist']) | ||
| 212 | |||
| 213 | Returns the URL for the podcast's "cover art" icon image, if any. | ||
| 214 | |||
| 215 | If B<'artist'> is specified, the channel artist's icon url is returned, | ||
| 216 | if any. | ||
| 217 | |||
| 218 | =item $podcast->B<getIconData>(['artist']) | ||
| 219 | |||
| 220 | Returns a two-element array consisting of the extension (ie. "png", | ||
| 221 | "gif", "jpeg", etc.) and the actual icon image (binary data), if any. | ||
| 222 | |||
| 223 | If B<'artist'> is specified, the channel artist's icon data is returned, | ||
| 224 | if any. | ||
| 225 | |||
| 226 | =item $podcast->B<getImageURL>(['artist']) | ||
| 227 | |||
| 228 | Returns the URL for the podcast's "cover art" (usually larger) | ||
| 229 | banner image. | ||
| 230 | |||
| 231 | If B<'artist'> is specified, the channel artist's image url is returned, | ||
| 232 | if any. | ||
| 233 | |||
| 234 | Note: SermonAudio sermons (unlike most other podcast sites) often have both | ||
| 235 | an artist icon (for the church) AND an artist image for that artist/channel | ||
| 236 | (preacher), and the artist's image is usually slightly larger and is a photo | ||
| 237 | of the specific preacher. See also the B<-speakericon> option. | ||
| 238 | |||
| 239 | =item $podcast->B<getImageData>(['artist']) | ||
| 240 | |||
| 241 | Returns a two-element array consisting of the extension (ie. "png", | ||
| 242 | "gif", "jpeg", etc.) and the actual podcast's banner image (binary data). | ||
| 243 | |||
| 244 | If B<'artist'> is specified, the channel artist's icon data is returned, | ||
| 245 | if any. | ||
| 246 | |||
| 247 | =item $podcast->B<getType>() | ||
| 248 | |||
| 249 | Returns the podcast's type ("SermonAudio"). | ||
| 250 | |||
| 251 | =back | ||
| 252 | |||
| 253 | =head1 CONFIGURATION FILES | ||
| 254 | |||
| 255 | The default root location directory for StreamFinder configuration files | ||
| 256 | is "~/.config/StreamFinder". To use an alternate location directory, | ||
| 257 | specify it in the "I<STREAMFINDER>" environment variable, ie.: | ||
| 258 | B<$ENV{STREAMFINDER} = "/etc/StreamFinder">. | ||
| 259 | |||
| 260 | =over 4 | ||
| 261 | |||
| 262 | =item ~/.config/StreamFinder/SermonAudio/config | ||
| 263 | |||
| 264 | Optional text file for specifying various configuration options | ||
| 265 | for a specific site (submodule). Each option is specified on a | ||
| 266 | separate line in the format below: | ||
| 267 | NOTE: Do not follow the lines with a semicolon, comma, or any other | ||
| 268 | separator. Non-numeric I<values> should be surrounded with quotes, either | ||
| 269 | single or double. Blank lines and lines beginning with a "#" sign as | ||
| 270 | their first non-blank character are ignored as comments. | ||
| 271 | |||
| 272 | 'option' => 'value' [,] | ||
| 273 | |||
| 274 | and the options are loaded into a hash used only by the specific | ||
| 275 | (submodule) specified. Valid options include | ||
| 276 | I<-debug> => [0|1|2] and most of the L<LWP::UserAgent> options. | ||
| 277 | |||
| 278 | Options specified here override any specified in | ||
| 279 | I<~/.config/StreamFinder/config>. | ||
| 280 | |||
| 281 | =item ~/.config/StreamFinder/config | ||
| 282 | |||
| 283 | Optional text file for specifying various configuration options. | ||
| 284 | Each option is specified on a separate line in the format below: | ||
| 285 | |||
| 286 | 'option' => 'value' [,] | ||
| 287 | |||
| 288 | and the options are loaded into a hash used by all sites | ||
| 289 | (submodules) that support them. Valid options include | ||
| 290 | I<-debug> => [0|1|2] and most of the L<LWP::UserAgent> options. | ||
| 291 | |||
| 292 | =back | ||
| 293 | |||
| 294 | NOTE: Options specified in the options parameter list of the I<new()> | ||
| 295 | function will override those corresponding options specified in these files. | ||
| 296 | |||
| 297 | =head1 KEYWORDS | ||
| 298 | |||
| 299 | sermonaudio | ||
| 300 | |||
| 301 | =head1 DEPENDENCIES | ||
| 302 | |||
| 303 | L<URI::Escape>, L<HTML::Entities>, L<LWP::UserAgent> | ||
| 304 | |||
| 305 | =head1 RECCOMENDS | ||
| 306 | |||
| 307 | wget | ||
| 308 | |||
| 309 | =head1 BUGS | ||
| 310 | |||
| 311 | Please report any bugs or feature requests to C<bug-streamFinder-iheartradio at rt.cpan.org>, or through | ||
| 312 | the web interface at L<http://rt.cpan.org/NoAuth/ReportBug.html?Queue=StreamFinder-SermonAudio>. I will be notified, and then you'll | ||
| 313 | automatically be notified of progress on your bug as I make changes. | ||
| 314 | |||
| 315 | =head1 SUPPORT | ||
| 316 | |||
| 317 | You can find documentation for this module with the perldoc command. | ||
| 318 | |||
| 319 | perldoc StreamFinder::SermonAudio | ||
| 320 | |||
| 321 | You can also look for information at: | ||
| 322 | |||
| 323 | =over 4 | ||
| 324 | |||
| 325 | =item * RT: CPAN's request tracker (report bugs here) | ||
| 326 | |||
| 327 | L<http://rt.cpan.org/NoAuth/Bugs.html?Dist=StreamFinder-SermonAudio> | ||
| 328 | |||
| 329 | =item * AnnoCPAN: Annotated CPAN documentation | ||
| 330 | |||
| 331 | L<http://annocpan.org/dist/StreamFinder-SermonAudio> | ||
| 332 | |||
| 333 | =item * Search CPAN | ||
| 334 | |||
| 335 | L<http://search.cpan.org/dist/StreamFinder-SermonAudio/> | ||
| 336 | |||
| 337 | =back | ||
| 338 | |||
| 339 | =head1 LICENSE AND COPYRIGHT | ||
| 340 | |||
| 341 | Copyright 2021-2026 Jim Turner. | ||
| 342 | |||
| 343 | This program is free software; you can redistribute it and/or modify it | ||
| 344 | under the terms of the the Artistic License (2.0). You may obtain a | ||
| 345 | copy of the full license at: | ||
| 346 | |||
| 347 | L<http://www.perlfoundation.org/artistic_license_2_0> | ||
| 348 | |||
| 349 | Any use, modification, and distribution of the Standard or Modified | ||
| 350 | Versions is governed by this Artistic License. By using, modifying or | ||
| 351 | distributing the Package, you accept this license. Do not use, modify, | ||
| 352 | or distribute the Package, if you do not accept this license. | ||
| 353 | |||
| 354 | If your Modified Version has been derived from a Modified Version made | ||
| 355 | by someone other than you, you are nevertheless required to ensure that | ||
| 356 | your Modified Version complies with the requirements of this license. | ||
| 357 | |||
| 358 | This license does not grant you the right to use any trademark, service | ||
| 359 | mark, tradename, or logo of the Copyright Holder. | ||
| 360 | |||
| 361 | This license includes the non-exclusive, worldwide, free-of-charge | ||
| 362 | patent license to make, have made, use, offer to sell, sell, import and | ||
| 363 | otherwise transfer the Package with respect to any patent claims | ||
| 364 | licensable by the Copyright Holder that are necessarily infringed by the | ||
| 365 | Package. If you institute patent litigation (including a cross-claim or | ||
| 366 | counterclaim) against any party alleging that the Package constitutes | ||
| 367 | direct or contributory patent infringement, then this Artistic License | ||
| 368 | to you shall terminate on the date that such litigation is filed. | ||
| 369 | |||
| 370 | Disclaimer of Warranty: THE PACKAGE IS PROVIDED BY THE COPYRIGHT HOLDER | ||
| 371 | AND CONTRIBUTORS "AS IS' AND WITHOUT ANY EXPRESS OR IMPLIED WARRANTIES. | ||
| 372 | THE IMPLIED WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR | ||
| 373 | PURPOSE, OR NON-INFRINGEMENT ARE DISCLAIMED TO THE EXTENT PERMITTED BY | ||
| 374 | YOUR LOCAL LAW. UNLESS REQUIRED BY LAW, NO COPYRIGHT HOLDER OR | ||
| 375 | CONTRIBUTOR WILL BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, OR | ||
| 376 | CONSEQUENTIAL DAMAGES ARISING IN ANY WAY OUT OF THE USE OF THE PACKAGE, | ||
| 377 | EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. | ||
| 378 | |||
| 379 | =cut | ||
| 380 | |||
| 381 | package StreamFinder::SermonAudio; | ||
| 382 | |||
| 383 | use strict; | ||
| 384 | use warnings; | ||
| 385 | use URI::Escape; | ||
| 386 | use HTML::Entities (); | ||
| 387 | use LWP::UserAgent (); | ||
| 388 | use parent 'StreamFinder::_Class'; | ||
| 389 | |||
| 390 | my $DEBUG = 0; | ||
| 391 | |||
| 392 | sub new | ||
| 393 | { | ||
| 394 | my $class = shift; | ||
| 395 | my $url = shift; | ||
| 396 | |||
| 397 | return undef unless ($url); | ||
| 398 | |||
| 399 | my $self = $class->SUPER::new('SermonAudio', @_); | ||
| 400 | $DEBUG = $self->{'debug'} if (defined $self->{'debug'}); | ||
| 401 | |||
| 402 | while (@_) { | ||
| 403 | if ($_[0] =~ /^\-?debug$/o) { | ||
| 404 | shift; | ||
| 405 | $DEBUG = (defined($_[0]) && $_[0] =~/^[0-9]$/) ? shift : 1; | ||
| 406 | } elsif ($_[0] =~ /^\-?secure$/o) { | ||
| 407 | shift; | ||
| 408 | $self->{'secure'} = (defined $_[0]) ? shift : 1; | ||
| 409 | } elsif ($_[0] =~ /^\-?quality$/o) { | ||
| 410 | shift; | ||
| 411 | $self->{'quality'} = (defined $_[0]) ? shift : 'any'; | ||
| 412 | } elsif ($_[0] =~ /^\-?speakericon$/o) { | ||
| 413 | shift; | ||
| 414 | $self->{'speakericon'} = (defined $_[0]) ? shift : 1; | ||
| 415 | } elsif ($_[0] =~ /^\-?notrim$/o) { | ||
| 416 | shift; | ||
| 417 | $self->{'notrim'} = (defined $_[0]) ? shift : 1; | ||
| 418 | } elsif ($_[0] =~ /^\-?nowebp$/o) { | ||
| 419 | shift; | ||
| 420 | $self->{'nowebp'} = (defined $_[0]) ? shift : 1; | ||
| 421 | } else { | ||
| 422 | shift; | ||
| 423 | } | ||
| 424 | } | ||
| 425 | $self->{'quality'} = 'any' unless (defined $self->{'quality'}); | ||
| 426 | $self->{'speakericon'} = 0 unless (defined $self->{'speakericon'}); | ||
| 427 | $self->{'notrim'} = 0 unless (defined $self->{'notrim'}); | ||
| 428 | $self->{'nowebp'} = 0 unless (defined $self->{'nowebp'}); | ||
| 429 | |||
| 430 | my $isEpisode = 1; | ||
| 431 | $url =~ s#\\##g; | ||
| 432 | (my $url2fetch = $url); | ||
| 433 | $url2fetch =~ s#\?.*$## unless ($self->{'notrim'}); | ||
| 434 | if ($url =~ /^https?\:/) { #FULL URL: | ||
| 435 | $self->{'id'} = $1 if ($url2fetch =~ m#\?SID\=([\d]+)#); | ||
| 436 | unless ($self->{'id'}) { #WE'RE ONE OF SERMONAUDIO'S ALTERNATE URLS: | ||
| 437 | $self->{'id'} = $1 if ($url2fetch =~ /sermonaudio/i && $url2fetch =~ m#([\d]+)\/?$#); | ||
| 438 | if ($url2fetch =~ m#\/speakers?\/#) { | ||
| 439 | $isEpisode = 0; #ASSUME WE'RE AN AUTHOR/PREACHER PAGE. | ||
| 440 | } elsif ($url2fetch =~ m#\/series\/#) { | ||
| 441 | $isEpisode = 0; #ASSUME WE'RE A SERIES (SERMON GROUP) PAGE. | ||
| 442 | } elsif ($url2fetch =~ m#\/broadcasters?\/([a-zA-Z0-9]+)#) { | ||
| 443 | $self->{'id'} = $1; | ||
| 444 | $isEpisode = 0; #ASSUME WE'RE A CHURCH PAGE. | ||
| 445 | } elsif ($self->{'id'}) { | ||
| 446 | $url2fetch = 'https://www.sermonaudio.com/sermoninfo.asp?SID='.$self->{'id'}; | ||
| 447 | } elsif ($url2fetch =~ m#\bsourceid\=([^\?\&]+)$#) { | ||
| 448 | $self->{'id'} = $1; | ||
| 449 | $isEpisode = 0; #ASSUME WE'RE NOT AN EPISODE PAGE. | ||
| 450 | } elsif ($url2fetch =~ m#https://www.sermonaudio.com\/[a-z]+\/([^\?\&]+)$#) { | ||
| 451 | $self->{'id'} = $1; | ||
| 452 | $isEpisode = 0; #ASSUME WE'RE AN AUTHOR/PREACHER PAGE. | ||
| 453 | } else { | ||
| 454 | $self->{'id'} = 'sermonaudio'; | ||
| 455 | $isEpisode = 0; #ASSUME WE'RE A SEARCH/FOUND PAGE. | ||
| 456 | } | ||
| 457 | } | ||
| 458 | } elsif ($url =~ /^\d\d\d\d\d\d\d\d+$/) { #(URL=###########) | ||
| 459 | $self->{'id'} = $url; | ||
| 460 | $url2fetch = "https://www.sermonaudio.com/sermoninfo.asp?SID=$url"; | ||
| 461 | } elsif ($url =~ /^\d\d\d\d\d$/) { #5-DIGIT ID (AUTHOR/PREACHER PAGE) | ||
| 462 | $self->{'id'} = $url; | ||
| 463 | $isEpisode = 0; #WE'RE AN AUTHOR/PREACHER PAGE. | ||
| 464 | $url2fetch = "https://www.sermonaudio.com/speakers/$url"; | ||
| 465 | } elsif ($url =~ /^\d\d\d\d\d\d$/) { #6-DIGIT ID (SERIES PAGE) | ||
| 466 | $self->{'id'} = $url; | ||
| 467 | $url2fetch = "https://www.sermonaudio.com/series/$url"; | ||
| 468 | } elsif ($url =~ /^[a-z]+$/i) { #ALPHANUMERIC ID (CHURCH PAGE) | ||
| 469 | $self->{'id'} = $url; | ||
| 470 | $url2fetch = "https://www.sermonaudio.com/broadcasters/$url"; | ||
| 471 | $isEpisode = 0; | ||
| 472 | } elsif ($url =~ m#\/#) { #KEYWORD/ID | ||
| 473 | $self->{'id'} = $url; | ||
| 474 | $url2fetch = "https://www.sermonaudio.com/$url"; | ||
| 475 | $isEpisode = 0; | ||
| 476 | } | ||
| 477 | return undef unless ($self->{'id'}); | ||
| 478 | |||
| 479 | my $html = ''; | ||
| 480 | my $ua = LWP::UserAgent->new(@{$self->{'_userAgentOps'}}); | ||
| 481 | $ua->timeout($self->{'timeout'}); | ||
| 482 | $ua->cookie_jar({}); | ||
| 483 | $ua->env_proxy; | ||
| 484 | my $response; | ||
| 485 | my $tried = 0; | ||
| 486 | |||
| 487 | TRYIT: | ||
| 488 | print STDERR "-${tried}(SermonAudio): FETCHING URL=$url2fetch= ID=".$self->{'id'}."=\n" if ($DEBUG); | ||
| 489 | |||
| 490 | $response = $ua->get($url2fetch); | ||
| 491 | if ($response->is_success) { | ||
| 492 | $html = $response->decoded_content; | ||
| 493 | } else { | ||
| 494 | print STDERR $response->status_line if ($DEBUG); | ||
| 495 | } | ||
| 496 | print STDERR "-1: html=$html=\n" if ($DEBUG > 1); | ||
| 497 | print STDERR "---ID=".$self->{'id'}."= isEpisode=$isEpisode=\n" if ($DEBUG); | ||
| 498 | return undef unless ($self->{'id'} && $html); | ||
| 499 | |||
| 500 | my $baseURL = ($html =~ m#\bhostname\:\"([^\"]+)#) ? $1 : 'https://www.sermonaudio.com'; | ||
| 501 | $baseURL =~ s#^\/##; | ||
| 502 | $baseURL = 'https://' . $baseURL unless ($baseURL =~ m#^http#); | ||
| 503 | if ($isEpisode) { | ||
| 504 | print STDERR "-1: html=$html=\n" if ($DEBUG > 1); | ||
| 505 | return undef unless ($html && $self->{'id'}); #STEP 1 FAILED, INVALID PODCAST URL, PUNT! | ||
| 506 | |||
| 507 | $self->{'genre'} = 'Sermon'; | ||
| 508 | $self->{'albumartist'} = $url2fetch; | ||
| 509 | if ($self->{'quality'} !~ /audio/i && $html =~ s#\<video.+?src\=\"([^\"]+)##s) { | ||
| 510 | my $mediaurl = $1; | ||
| 511 | unless ($self->{'secure'} && $mediaurl !~ /^https/o) { | ||
| 512 | $mediaurl =~ s#\?.*$## unless ($self->{'notrim'}); #STRIP OFF ANY EXTRA ARGS | ||
| 513 | push @{$self->{'streams'}}, $mediaurl; | ||
| 514 | print STDERR "--stream found=$mediaurl=\n" if ($DEBUG); | ||
| 515 | $self->{'cnt'}++; | ||
| 516 | } | ||
| 517 | } | ||
| 518 | if ($html =~ s#\<audio.+?src\=\"([^\"]+)##s) { | ||
| 519 | my $audiourl = $1; | ||
| 520 | unless ($self->{'secure'} && $audiourl !~ /^https/o) { | ||
| 521 | $audiourl =~ s#\?.*$## unless ($self->{'notrim'}); #STRIP OFF ANY EXTRA ARGS | ||
| 522 | push @{$self->{'streams'}}, $audiourl; | ||
| 523 | print STDERR "--stream found=$audiourl=\n" if ($DEBUG); | ||
| 524 | $self->{'cnt'}++; | ||
| 525 | } | ||
| 526 | } | ||
| 527 | $self->{'total'} = $self->{'cnt'}; | ||
| 528 | # return undef unless ($self->{'cnt'} > 0); | ||
| 529 | |||
| 530 | $html =~ s/\\\"/\"\;/gs; | ||
| 531 | $self->{'title'} = $1 if ($html =~ m#\<title\>\s*([^\|\<]+)#si); | ||
| 532 | $self->{'title'} ||= $1 if ($html =~ m#\"(?:og|twitter)\:title\"\s+content\=\"([^\"]+)#s); | ||
| 533 | $self->{'description'} = $1 if ($html =~ m#subtitle\:\w\,moreInfoText\:\"([^\"]+)#s); | ||
| 534 | $self->{'description'} ||= $1 if ($html =~ m#\-\-md\-spacing\:1em\;\"\>\<p\>(.+?)\<\/p\>#is); | ||
| 535 | $self->{'description'} ||= $self->{'title'}; | ||
| 536 | $self->{'genre'} = $1 if ($html =~ m#\>\s*Category\s*\<\/td\>\s*\<td[^\>]*\>(.+?)\<\/td\>#s); | ||
| 537 | $self->{'genre'} =~ s/\<[^\>]+\>//gs; | ||
| 538 | $self->{'genre'} =~ s/^\s+//s; | ||
| 539 | $self->{'genre'} =~ s/\s+$//s; | ||
| 540 | if ($html =~ m#(?:\"uploadDate\"\:|\<time\s+datetime\=)\"([^\"]+)# | ||
| 541 | || $html =~ m#\>Date\<\/td\>\s*\<td[^\>]*\>(.+?)\<\/td\>#s) { | ||
| 542 | $self->{'created'} = $1; | ||
| 543 | $self->{'year'} = $1 if ($self->{'created'} =~ /(\d\d\d\d)/); | ||
| 544 | } | ||
| 545 | foreach my $field (qw(title description)) { | ||
| 546 | $self->{$field} = HTML::Entities::decode_entities($self->{$field}); | ||
| 547 | $self->{$field} = uri_unescape($self->{$field}); | ||
| 548 | $self->{$field} =~ s/(?:\%|\\?u?00)([0-9A-Fa-f]{2})/chr(hex($1))/eg; | ||
| 549 | } | ||
| 550 | $self->{'iconurl'} = $1 if ($html =~ m#\"(?:og|twitter)\:image\:secure_url\"\s+content\=\"([^\"]+)#s); | ||
| 551 | $self->{'iconurl'} ||= $1 if ($html =~ m#\"(?:og|twitter)\:image(?:\:url)?\"\s+content\=\"([^\"]+)#s); | ||
| 552 | if ($html =~ s#\<div\s+class\=\"absolute-fill\s+bg\-black(.+?)\<\/div\>##s) { | ||
| 553 | my $data = $1; | ||
| 554 | $self->{'imageurl'} = $1 if ($data =~ m#\"background\-image\:url\((http[^\)]+)#s); | ||
| 555 | } | ||
| 556 | |||
| 557 | #BEGIN LIKELY-DEPRECIATED: | ||
| 558 | if ($html =~ m#\<span\s+class\=\"bg\-cover.+?style\=\"background\-image\:url\((http[^\)]+)#s) { | ||
| 559 | $self->{'articonurl'} = $1; | ||
| 560 | } elsif ($html =~ s#<div class="bg-cover[^\"]+\"\s+style\=\"background\-image\:url\((http[^\)]+)\)##s) { | ||
| 561 | $self->{'articonurl'} = $1; | ||
| 562 | } | ||
| 563 | $self->{'iconurl'} ||= $1 if ($html =~ s#\<img\s+src\=\"(http[^\"]+)##s); | ||
| 564 | $self->{'artimageurl'} = $1 if ($html =~ s#\<img\s+src\=\"(http[^\"]+)##s); | ||
| 565 | $self->{'imageurl'} ||= $self->{'iconurl'}; | ||
| 566 | $self->{'artimageurl'} = 'https:' . $self->{'artimageurl'} if ($self->{'artimageurl'} =~ m#^\/\/#); | ||
| 567 | $self->{'articonurl'} ||= $self->{'artimageurl'}; | ||
| 568 | |||
| 569 | if ($html =~ s#\<a\s+href\=\"([^\"]*?\/broadcasters?\/[^\/]+\/)\"\s+class\=\"link\"[^\>]*\>([^\<]+)##s) { | ||
| 570 | my ($one, $two) = ($1, $2); | ||
| 571 | $one = $baseURL . $one if ($one =~ m#^\/broadcaster#); | ||
| 572 | $self->{'albumartist'} = "$two - $one"; | ||
| 573 | } | ||
| 574 | if ($html =~ s#\<a\s+href\=\"([^\"]*?\/speakers?\/\d+\/)\"\s+class\=\"link\"[^\>]*\>([^\<]+)##s) { | ||
| 575 | my ($one, $two) = ($1, $2); | ||
| 576 | $one = $baseURL . $one if ($one =~ m#^\/speaker#); | ||
| 577 | $self->{'artist'} = $two; | ||
| 578 | unless ($self->{'albumartist'} && $self->{'albumartist'} !~ m#$one#) { | ||
| 579 | $self->{'albumartist'} ||= $one; | ||
| 580 | } | ||
| 581 | } | ||
| 582 | if (!$self->{'artist'} && $html =~ m#\<meta\s+name\=\"description\"\s+content\=\"([^\"]+)"#s) { | ||
| 583 | ($self->{'artist'} = $1) =~ s/\s+\|.*$//; | ||
| 584 | } | ||
| 585 | #END LIKELY-DEPRECIATED | ||
| 586 | |||
| 587 | #NEWER? JASON TAKES PRECEDENCE FOR ARTIST & ALBUMARTIST DATA: | ||
| 588 | if ($html =~ s#\{"\@type":"Person",([^\}]+)\}##s) { | ||
| 589 | my $artistStuff = $1; | ||
| 590 | my $artistURL = ($artistStuff =~ m#\"\@id\"\:\"([^\"]+)#) ? $1 : ''; | ||
| 591 | $artistURL ||= $1 if ($artistStuff =~ m#\"url\"\:\"([^\"]+)#); | ||
| 592 | $self->{'artist'} = $1 if ($artistStuff =~ m#\"name\"\:\"([^\"]+)#); | ||
| 593 | if ($artistURL) { | ||
| 594 | $self->{'artist'} .= ' - ' if ($self->{'artist'}); | ||
| 595 | $self->{'artist'} .= $artistURL; | ||
| 596 | } | ||
| 597 | $self->{'artimageurl'} ||= $1 if ($artistStuff =~ m#\"image\"\:\"([^\"]+)#); | ||
| 598 | } | ||
| 599 | if ($html =~ s#\{"\@type":"Organization",([^\}]+)\}##s) { | ||
| 600 | my $channelStuff = $1; | ||
| 601 | $self->{'albumartist'} = ($channelStuff =~ m#\"\@id\"\:\"([^\"]+)#) ? $1 : ''; | ||
| 602 | $self->{'album'} = $1 if ($channelStuff =~ m#\"name\"\:\"([^\"]+)#); | ||
| 603 | $self->{'articonurl'} = $1 if ($channelStuff =~ m#\"image\"\:\"([^\"]+)#); | ||
| 604 | } | ||
| 605 | |||
| 606 | if ($self->{'speakericon'} && $self->{'artimageurl'}) { #USE PREACHER'S THUMBNAIL (REVERSE articon AND artimage): | ||
| 607 | my $x = $self->{'artimageurl'}; | ||
| 608 | $self->{'artimageurl'} = $self->{'articonurl'}; | ||
| 609 | $self->{'articonurl'} = ($html =~ s#\<\/i\>\s+\<img\s+src\=\"(http[^\"]+)##s) | ||
| 610 | ? $1 : $x; | ||
| 611 | } | ||
| 612 | $self->{'album'} = $1 if ($html =~ m#\<meta\s+name\=\"description\"\s+content\=\"([^\"]+)#s); | ||
| 613 | $self->{'album'} ||= $1 if ($html =~ m#\<meta\s+property\=\"og\:description\"\s+content\=\"([^\"]+)#s); | ||
| 614 | $self->{'album'} =~ s#$self->{'artist'}\s*\|\s*## if ($self->{'artist'}); | ||
| 615 | $self->{'albumartist'} ||= $1 if ($html =~ m#href\=\"([^\"]+)\"\>Web\<\/a\>#s); | ||
| 616 | $self->{'articonurl'} ||= $self->{'artimageurl'}; | ||
| 617 | $self->{'Url'} = ($self->{'total'} > 0) ? $self->{'streams'}->[0] : ''; | ||
| 618 | |||
| 619 | if ($self->{'notrim'}) { | ||
| 620 | if ($self->{'nowebp'}) { | ||
| 621 | foreach my $field (qw(iconurl imageurl articonurl artimageurl)) { | ||
| 622 | $self->{$field} =~ s#[\&\?]webp\=[a-z]+##; | ||
| 623 | $self->{$field} =~ s#\.(png|jpe?g|gif)\&#\.$1\?#; | ||
| 624 | } | ||
| 625 | } | ||
| 626 | } else { | ||
| 627 | foreach my $field (qw(iconurl imageurl articonurl artimageurl)) { | ||
| 628 | my $webp = ($self->{$field} =~ /[\&\?](webp\=[a-z]+)/) ? $1 : 0; | ||
| 629 | $self->{$field} =~ s#\.(png|jpe?g|gif)[\&\?].*$#\.$1#; | ||
| 630 | $self->{$field} .= "?$webp" if ($webp && !$self->{'nowebp'}); | ||
| 631 | } | ||
| 632 | } | ||
| 633 | } else { | ||
| 634 | print STDERR "--NOT EPISODE, tried=$tried=\n" if ($DEBUG); | ||
| 635 | if ($tried < 2) { #WE'RE A PODCAST PAGE!: | ||
| 636 | #NOTE: SERMONAUDIO PODCAST PAGES DO NOT HAVE STREAMS, ONLY EPISODE-IDS+TITLES, SO | ||
| 637 | #WE CAN'T CONSTRUCT A PLAYLIST, BUT ONLY GRAB THE 1ST EPISODE AND TRY AND FETCH THAT: :( | ||
| 638 | ++$tried; | ||
| 639 | $html =~ s#^.+?\<div\s+class\=\"wrapper\-element\s##s; | ||
| 640 | if ($html =~ s#\<a\s+href\=\"([^\"]*?\/sermons?\/)(\d+)\/?\"##s) { | ||
| 641 | my $one = $1; | ||
| 642 | $self->{'id'} = $2; | ||
| 643 | $one = $baseURL . $one if ($one =~ m#^\/sermon#); | ||
| 644 | $isEpisode = 1; | ||
| 645 | $url2fetch = $one . $self->{'id'}; | ||
| 646 | print STDERR "-!!!!- RETRY w/1ST EPISODE ID=$url2fetch= TITLE=".$self->{'title'}."=\n" if ($DEBUG); | ||
| 647 | goto TRYIT; | ||
| 648 | } elsif ($html =~ s#\<a\s+href\=\"([^\"]*?\/series\/)(\d+)\/?\"##s) { | ||
| 649 | my $one = $1; | ||
| 650 | $self->{'id'} = $2; | ||
| 651 | $one = $baseURL . $one if ($one =~ m#^\/series#); | ||
| 652 | $isEpisode = 0; | ||
| 653 | $url2fetch = $one . $self->{'id'}; | ||
| 654 | print STDERR "-!!!!- RETRY w/1ST SERIES ID=$url2fetch= TITLE=".$self->{'title'}."=\n" if ($DEBUG); | ||
| 655 | goto TRYIT; | ||
| 656 | } | ||
| 657 | } | ||
| 658 | return undef unless ($self->{'total'} > 0); #NO VALID PAGE FOUND! | ||
| 659 | } | ||
| 660 | |||
| 661 | if ($DEBUG) { | ||
| 662 | foreach my $i (sort keys %{$self}) { | ||
| 663 | print STDERR "--KEY=$i= VAL=".$self->{$i}."=\n"; | ||
| 664 | } | ||
| 665 | print STDERR "--SUCCESS: 1st stream=".$self->{'Url'}."= total=".$self->{'total'}."=\n" | ||
| 666 | if ($self->{'cnt'} > 0); | ||
| 667 | } | ||
| 668 | |||
| 669 | $self->_log($url); | ||
| 670 | |||
| 671 | bless $self, $class; #BLESS IT! | ||
| 672 | |||
| 673 | return $self; | ||
| 674 | } | ||
| 675 | |||
| 676 | 1 |