Many hyperlinks are disabled.
Use anonymous login
to enable hyperlinks.
Overview
Comment: | Transferred from Bitbucket |
---|---|
Downloads: | Tarball | ZIP archive | SQL archive |
Timelines: | family | ancestors | descendants | both | trunk |
Files: | files | file ages | folders |
SHA3-256: |
f06c0d41c45e79499bfaa4d009fa3377 |
User & Date: | Cthulhux 2019-11-17 00:42:03 |
Context
2020-04-22
| ||
07:55 | Fixed README check-in: 1b6f35c75a user: Cthulhux tags: trunk | |
2019-11-17
| ||
00:42 | Transferred from Bitbucket check-in: f06c0d41c4 user: Cthulhux tags: trunk | |
00:39 | initial empty check-in check-in: 9895f32525 user: Cthulhux tags: trunk | |
Changes
Added README.md.
> > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 | # rssparser.lisp A Web-to-RSS parser in Common Lisp. ## What does it do? This software was written because a disappointing number of websites still does not have an RSS or Atom feed so I could subscribe to their updates, e.g. the [KiTTY website](https://www.9bis.net/kitty/?action=news&zone=en). The script tries to find new *articles* on any website according to given criteria (CSS selectors) and parse them into a valid RSS feed so I can subscribe to them in my usual RSS feed reader. ## Screenshot  ## Syntax * *chmod +x rssparser.lisp*, then: * ./rssparser.lisp add *<Title> <URL> <EntrySelector> <TitleSelector> [<ContentSelector>]* * ./rssparser.lisp delete *<ID>* * ./rssparser.lisp list * ./rssparser.lisp export *<ID>* ***Run a simple web interface on port 5000:*** * ./rssparser.lisp webserver ***Cronjob or manual feed creation command:*** * ./rssparser.lisp parse Supported *selectors* are all valid [CSS selectors](http://www.w3schools.com/cssref/css_selectors.asp). If you don't specify a `ContentSelector` when adding a new feed, `rssparser.lisp` will use an empty item body. ### Example If you want to subscribe to the KiTTY website, you can either use the web interface or perform the following commands: % ./rssparser.lisp add "KiTTY" "https://www.9bis.net/kitty/?action=news&zone=en" ".news" "h1" "" Success! % ./rssparser.lisp parse % ./rssparser.lisp list 1 feed is set up: ID: 23 Title: KiTTY URL: https://www.9bis.net/kitty/?action=news&zone=en Last success: Sun, 27 Mar 2016 17:54:18 +0200 By default, the KiTTY website feed will be stored as `feeds/feed23.xml` then. ## Requirements You'll need the files from this repository and [SBCL](http://www.sbcl.org) with [Quicklisp](http://www.quicklisp.org) set up. [SQLite3](https://sqlite3.org) should be available. Also, you should create a folder where your feed files should be created (`./feeds` by default). Hard links are allowed. ### Packages Usually, Quicklisp should install the required packages for you. If you want to install them manually, `rssparser.lisp` currently requires these: * `datafly` * `hunchentoot` * `cl-who` * `parenscript` * `smackjack` * `lass` * `cl-ppcre` * `dexador` * `clss` * `plump` * `plump-sexp` * `local-time` * `xml-emitter` ### SQLite schema The `feeds.db` file has the following schema: CREATE TABLE feeds ( id integer primary key autoincrement, feedtitle text not null, url text not null, entryselector text not null, titleselector text not null, contentselector text not null, lastsuccess integer ); CREATE TABLE entries ( id integer primary key autoincrement, feedid integer, title text not null, contents blob, url text not null, timestamp integer ); ### Exporting feeds into a new database If you want to transfer one or more of your stored feeds into a new database, that's what the `export` command is for: % ./rssparser.lisp export 23 Execute this SQL command to add this feed to a new database: INSERT INTO feeds ('feedtitle', 'url', 'entryselector', 'titleselector', 'contentselector') VALUES ('KiTTy', 'https://www.9bis.net/kitty/?action=news&zone=en', '.news', 'h1', ''); ## Configuration You can set a couple of parameters in the `config.lisp` file: * `+database-file+`: The SQLite database file. (Default: `feeds.db`.) Note that this file *needs* to be accessible for the RSS parser to work! * `+feed-folder+`: The folder where the feed files should be created. (Default: `feeds/`.) The script *needs* to be able to create files there; it checks its permissions automatically and informs you if it needs some help. * `+max-items-per-feed+`: The maximum number of items per feed. (Default: `50`.) * `+feed-cleanup+`: If set to `t` (which is the default value), the `entries` table will automatically be purged from old entries (only *2 * `+max-items-per-feed+`* are kept). Set this to `nil` if you want to bloat your database. * `+remove-dead-feeds+`: If set to `t`, a website which is not reachable anymore will automatically be removed from your feed list. The parser will inform you of that so if you run `rssparser.lisp` as a cronjob, you'll see what happened in your logfiles. * `+webserver-port+`: The port to run the webserver on when `rssparser.lisp webserver` is executed. It should be available through your firewall. (Default: `5000`.) |
Added config.lisp.
> > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 | ;;; Web to RSS Parser ;;; by tux. [ http://tuxproject.de ] ;;; ;;; Licensed under the terms of the WTFPL. ;;; http://wtfpl.net/txt/copying/ (in-package #:rssparser) (defun get-args () "Returns the list of command-line parameters. Don't touch this." (or #+sbcl sb-ext:*posix-argv* #+ccl *command-line-argument-list* nil)) ;;; -------- SET YOUR OPTIONS BELOW -------- ;;; Store the script's command mode in a parameter ;;; so we won't have to fetch it again and again. ;;; Also store the arguments. (defparameter *script-mode* (cadr (get-args))) (defparameter *script-arguments* (cddr (get-args))) ;;; Store the database file name and the folder ;;; for our feed files so we can easily change ;;; them later if we want to ... (defconstant +database-file+ "/home/tux/hg/rssparser.lisp/feeds.db") (defconstant +feed-folder+ "/home/tux/hg/rssparser.lisp/feeds/") ;;; Store the maximum number of entries per feed. (defconstant +max-items-per-feed+ 50) ;;; Set up a feed cleaner: If this constant is not NIL, ;;; the feed parser will remove old entries from the ;;; database automatically. (defconstant +feed-cleanup+ t) ;;; If a website is dead, it could automatically be ;;; removed from the feed list. (defconstant +remove-dead-feeds+ t) ;; By default, the webserver listens on this port. (defconstant +webserver-port+ 5000) |
Added feeds.db.dist.
cannot compute difference between binary files
Added package.lisp.
> > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 | ;;; Web to RSS Parser ;;; by tux. [ http://tuxproject.de ] ;;; ;;; Licensed under the terms of the WTFPL. ;;; http://wtfpl.net/txt/copying/ (load "~/quicklisp/setup.lisp") (ql:quickload '(:datafly ;; for database access ;; WEB SERVER: :hunchentoot ;; for providing a web server :cl-who ;; for building the HTML output :parenscript ;; for the avoiding of the horrible JS syntax :smackjack ;; for AJAX requests :lass ;; for building the (S)CSS styles ;; WEB/RSS CLIENT: :cl-ppcre ;; for regex :dexador ;; for using the web :clss ;; for CSS selecting :plump ;; for parsing XML/DOM :plump-sexp ;; for converting DOM to S-exps :local-time ;; for time conversion :xml-emitter) ;; for creating the RSS files :silent t) (defpackage #:rssparser (:use :cl :sxql :datafly :xml-emitter :local-time :hunchentoot :cl-who :lass :smackjack :sb-int) (:import-from :parenscript :ps :chain)) |
Added rssparser.lisp.
> > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 | #!/opt/local/bin/sbcl --script ;;; Web to RSS Parser ;;; by tux. [ https://tuxproject.de ] ;;; ;;; Licensed under the terms of the WTFPL. ;;; http://wtfpl.net/txt/copying/ ;;; valid syntax: ;;; * ./rssparser add <Title> <URL> <EntrySelector> <TitleSelector> [<ContentSelector>] ;;; * ./rssparser.lisp del(ete) <ID> ;;; * ./rssparser.lisp list ;;; * ./rssparser.lisp export <ID> ;;; * ./rssparser.lisp webserver ;;; * ./rssparser.lisp parse ;;; SETUP (load (merge-pathnames "package.lisp" *load-truename*)) (load (merge-pathnames "config.lisp" *load-truename*)) (in-package #:rssparser) ;;; HELPER FUNCTIONS (defun show-syntax () "Prints the command-line syntax for the RSS parser." (format t "Syntax:~% * rssparser.lisp add <Title> <URL> <EntrySelector> <TitleSelector> [<ContentSelector>]~% * rssparser.lisp delete <ID>~% * rssparser.lisp list~% * rssparser.lisp export <ID>~% * rssparser.lisp webserver~%~%If you're a bot:~% * rssparser.lisp parse")) (defun print-feed-list (list) "Makes the feed list look nicer." (loop for feed in list do (let ((id-pair (first feed)) (title-pair (second feed)) (url-pair (third feed)) (lastsuccess-pair (fourth feed))) (format t "~%ID: ~a Title: ~a~% URL: ~a~% Last success: ~a~%" (cdr id-pair) (cdr title-pair) (cdr url-pair) (if (cdr lastsuccess-pair) (timestamp-to-rssdate (cdr lastsuccess-pair)) ;; New feeds don't have a "last success" yet: "-"))))) (clss:define-pseudo-selector external-link (node) "CLSS pseudo-selector for external links, shamelessly borrowed from the CLSS manual." (let ((href (plump:attribute node "href"))) (and href (cl-ppcre:scan "^(http|https)://" href)))) (defun extract-urls (node) "Tries to find an external href in <node>. Returns a list of all found URLs." (let ((link-list (clss:select "a:external-link" node))) (loop for found-link being the elements of link-list collect (list (plump:attribute found-link "href"))))) (defun timestamp-to-rssdate (timestamp) "Returns a readable date from a given timestamp." (format-timestring nil (unix-to-timestamp timestamp) :format +rfc-1123-format+)) ;;; WEB SERVER ;; Define a parameter to determine if a method has been called via web interface. (defparameter *is-web* nil) ;; Make Parenscript coexist with CL-WHO (setf parenscript:*js-string-delimiter* #\") ;; Set the output doctype (setf (html-mode) :html5) ;; Instantiate an AJAX listener for Smackjack (defparameter *ajax-processor* (make-instance 'ajax-processor :server-uri "/ajax")) ;; Define the routes for Hunchentoot (setq *dispatch-table* (list 'dispatch-easy-handlers (create-ajax-dispatcher *ajax-processor*))) ;; Define the HTML output when accessing the web UI (define-easy-handler (rssweb :uri "/" :default-request-type :get) ((state-variable :parameter-type 'string)) (with-html-output-to-string (s nil :indent t) (:html (:head (:title "RSSParser Web Control Center") (str (generate-prologue *ajax-processor*)) (:style :type "text/css" (str (compile-and-write '(body :margin 0 :padding 0 :font-family monospace :font-size 12px) '(h1 :margin 5px) '(input :width 335px) '(div#controls :display block :width "calc (100% - 20px)" :padding 10px :background-color lightgrey) '(div#addfeed :display none :position absolute :font-family sans-serif :top 5px :right 5px :border 1px solid darkgray :padding 8px :background-color white (b :margin-bottom 6px) (div :display inline-block) (div.label :width 100px) (div.explanation :width 440px :margin-bottom 4px :font-size 11px)) '(table :margin 10px :border-collapse collapse (tr (td :border 1px solid darkgray :padding 4px) (td.centered :text-align center))) '(div#footer :position fixed :width 100% :padding 5px :display block :bottom 0px :left 0px)))) (:script :type "text/javascript" (str (ps (defun print-response-callback (response) (alert response)) (defun add-feed () (setf (chain document (get-element-by-id "addfeed") style display) "inline-block")) (defun add-this-feed () (let ((title (chain document (get-element-by-id "TitleToAdd") value)) (url (chain document (get-element-by-id "URLToAdd") value)) (entry-selector (chain document (get-element-by-id "EntrySelectorToAdd") value)) (title-selector (chain document (get-element-by-id "TitleSelectorToAdd") value)) (content-selector (chain document (get-element-by-id "ContentSelectorToAdd") value))) (if (or (not title) (not url) (not entry-selector) (not title-selector)) (alert "You should enter valid feed data before we can process your request.") (progn (chain smackjack (ajax-add-feed (list title url entry-selector title-selector content-selector) print-response-callback)) (close-add-feed-dlg) (request-table))))) (defun close-add-feed-dlg () (loop for inputid in (list "TitleToAdd" "URLToAdd" "EntrySelectorToAdd" "TitleSelectorToAdd" "ContentSelectorToAdd") do (setf (chain document (get-element-by-id inputid) value) nil)) (setf (chain document (get-element-by-id "addfeed") style display) "none")) (defun parse-all () (chain smackjack (ajax-parse-feeds print-response-callback)) (request-table)) (defun update-table (htmltext) (setf (chain document (get-element-by-id "ajaxtable") inner-h-t-m-l) htmltext)) (defun request-table () (chain smackjack (htmltable update-table)) nil) (defun zap-feed (feedid) (chain smackjack (ajax-delete-feed feedid)) (request-table) nil))))) (:body (:h1 "RSSParser Web Control Center") (:div :id "controls" (:button :type "button" :onclick (ps (parse-all)) "Parse All Feeds") (:button :type "button" :onclick (ps (add-feed)) "Add a Feed")) (:div :id "addfeed" (:div :class "explanation" "Please type the title of the feed you'd like to add.") (:br) (:div :class "label" "Title:") (:input :type "text" :id "TitleToAdd" :placeholder "e.g. KiTTY") (:br) (:br) (:div :class "explanation" "Please type the URL of the website you want to make an RSS feed of.") (:br) (:div :class "label" "URL:") (:input :type "text" :id "URLToAdd" :placeholder "e.g. http://www.9bis.net/kitty/?action=news&zone=en") (:br) (:br) (:b "CSS Selectors:") (:a :href "http://www.w3schools.com/cssref/trysel.asp" :target "_blank" "[?]") (:br) (:div :class "explanation" (str (concatenate 'string "Please type the single entry selector of the feed. For a blog, this is usually a DIV named \"article\" or similar. RSSParser.lisp will use this selector as the container selector for the following elements."))) (:br) (:div :class "label" "Selector:") (:input :type "text" :id "EntrySelectorToAdd" :placeholder "e.g. .news") (:br) (:br) (:div :class "explanation" "Please type the title selector of the feed. This is usually the headline inside the entry selector.") (:br) (:div :class "label" "Selector:") (:input :type "text" :id "TitleSelectorToAdd" :placeholder "e.g. h1") (:br) (:br) (:div :class "explanation" (str (concatenate 'string (htm (:em "(Optional)")) " Please type the content selector of the feed. This is usually the text part of the entry selector. If this is left blank, RSSParser.lisp will use the complete entry selector for the contents of your feed items."))) (:br) (:div :class "label" "Selector:") (:input :type "text" :id "ContentSelectorToAdd" :placeholder "e.g. \"\"") (:br) (:br) (:button :type "button" :onclick (ps (add-this-feed)) "Add this feed") (:button :type "button" :onclick (ps (close-add-feed-dlg)) "Cancel")) (:div :id "ajaxtable") (:div :id "footer" (:a :href "http://bitbucket.org/tux_/rssparser.lisp" :target "_blank" "Powered by RSSParser.lisp")) (:script :type "text/javascript" (str (ps (request-table)))))))) ;; Define an AJAX handler which returns the updated feeds list (as a table) (defun-ajax htmltable () (*ajax-processor* :callback-data :response-text) (with-html-output-to-string (s nil :indent t) (:table (:tr (:th "ID") (:th "Title") (:th "Original URL") (:th "Last success") (:th "Delete")) (loop for feed in (list-all-feeds) do (let ((id-pair (first feed)) (title-pair (second feed)) (url-pair (third feed)) (lastsuccess-pair (fourth feed))) (htm (:tr (:td (str (cdr id-pair))) (:td (str (cdr title-pair))) (:td (:a :href (cdr url-pair) :target "_blank" (str (cdr url-pair)))) (:td (if (cdr lastsuccess-pair) (str (timestamp-to-rssdate (cdr lastsuccess-pair))) "-")) (:td :class "centered" (:button :type "button" :title (concatenate 'string "Delete the " (write-to-string (cdr title-pair)) " feed") :onclick (concatenate 'string "javascript:zapFeed(\"" (write-to-string (cdr id-pair)) "\")") "x"))))))))) ;;; MAIN APPLICATION ;; Force the charset to be Unicode (setf sb-impl::*default-external-format* :UTF-8) (connect-toplevel :sqlite3 :database-name +database-file+) (defun add-new-feed (params) "Adds a new feed to the database." ;; Params: Feed title, URL, entry selector, title sel., [ content sel. ] (if (and ;; URL given? (cl-ppcre:scan "^https?://" (second params)) ;; Are the necessary params given at all? (>= (list-length params) 4) (<= (list-length params) 5)) (progn (if (and ;; Everything but the title must not be a number. (not (numberp (parse-integer (second params) :junk-allowed t))) (not (numberp (parse-integer (third params) :junk-allowed t))) (not (numberp (parse-integer (fourth params) :junk-allowed t)))) (progn (let ((content (if (fifth params) (princ-to-string (fifth params)) ""))) (execute ;; all arguments are set (probably even correctly). (insert-into :feeds (set= :feedtitle (princ-to-string (first params)) :url (princ-to-string (second params)) :entryselector (princ-to-string (third params)) :titleselector (princ-to-string (fourth params)) :contentselector content)))) t) nil)) (progn ;; invalid number of arguments (show-syntax) nil))) ;; AJAX handler for feed addition: (defun-ajax ajax-add-feed (params) (*ajax-processor* :callback-data :response-text) (setf *is-web* t) (if (add-new-feed params) "We successfully added your feed. :-)" "Sorry, something went wrong. :-(") (setf *is-web* nil)) (defun delete-feed (id) "Deletes a feed and all of its references." (if (and (eql 1 (list-length id)) (numberp (parse-integer (car id) :junk-allowed t))) (let ((id-to-delete (car id))) ;; The <id-to-delete> is the number of the feed to delete. (if (retrieve-one (select :id (from :feeds) (where (:= :id id-to-delete)))) (progn ;; This feed exists. Remove it. (execute (delete-from :feeds (where (:= :id id-to-delete)))) (execute (delete-from :entries (where (:= :feedid id-to-delete)))) ;; Now that the database entry is gone, we don't ;; need the XML file anymore. (let ;; The file is probably "feeds/feed<ID>.xml". ((feed-file (probe-file (concatenate 'string +feed-folder+ "feed" id-to-delete ".xml")))) (if feed-file ;; We have an XML file. Yet. (delete-file feed-file))) t) ;; No such feed in the database nil)) (progn ;; invalid number of arguments or ID is NaN (show-syntax) nil))) (defun export-feed (id) "Exports a feed's INSERT command for transferring it into another database." (if (and (eql 1 (list-length id)) (numberp (parse-integer (car id) :junk-allowed t))) (progn (let* ((id-to-export (car id)) (feed (retrieve-one (select (:feedtitle :url :entryselector :titleselector :contentselector) (from :feeds) (where (:= :id id-to-export)))))) ;; The <id-to-export> is the number of the feed to export. (if feed (progn ;; This feed exists. Export it. (let ((feed-title (second feed)) (feed-url (fourth feed)) (feed-entries (sixth feed)) (feed-entry-titles (eighth feed)) (feed-entry-contents (tenth feed))) (concatenate 'string "INSERT INTO feeds ('feedtitle', 'url', 'entryselector', 'titleselector', 'contentselector') " "VALUES ('" feed-title "', '" feed-url "', '" feed-entries "', '" feed-entry-titles "', '" feed-entry-contents "');"))) ;; No such feed in the database nil))) (progn ;; invalid number of arguments or ID is NaN (show-syntax) nil))) ;; AJAX handler for feed deletion: (defun-ajax ajax-delete-feed (feed-id) (*ajax-processor* :callback-data :response-text) (if (delete-feed (list feed-id)) (concatenate 'string "Deleted feed " feed-id) "Failed to delete the feed, sorry.")) (defun list-all-feeds () "Lists all known feeds." (retrieve-all (select (:id :feedtitle :url :lastsuccess) (from :feeds)) :as 'trivial-types:association-list)) (defun parse-all-feeds () "Loops over the known feeds and generates the XML files." (loop for feed in (retrieve-all (select (:feedtitle :url :entryselector :titleselector :contentselector :id) (from :feeds))) do (let ((feed-title (second feed)) (feed-url (fourth feed)) (feed-entries (sixth feed)) (feed-entry-titles (eighth feed)) (feed-entry-contents (tenth feed)) (feed-id (last feed))) (handler-case (let ((the-dom (plump:parse (dex:get feed-url)))) ;; the-dom is the DOM of our feed URL now. ;; We can process it normally. (let ((box-elements (clss:select feed-entries the-dom)) (feed-file (concatenate 'string +feed-folder+ "feed" (princ-to-string (car feed-id)) ".xml"))) (with-open-file (stream feed-file :direction :output :if-exists :overwrite :if-does-not-exist :create) (with-rss2 (stream :encoding "utf-8") (rss-channel-header feed-title feed-url) (loop for feed-entry being the elements of box-elements do (let ((contents ;; If the feed has an "empty" contents selector, take the ;; whole box element's content as the entry contents (if (string= feed-entry-contents "") (list feed-entry) (clss:select feed-entry-contents feed-entry))) ;; The title elements are always stored with the feed. (titles (clss:select feed-entry-titles feed-entry))) ;; Loop over all titles/contents and add an RSS item for each of them (loop for single-title being the elements of titles for single-contents being the elements of contents do (let ;; Grab the plain text from the title: ((our-title (plump:text single-title)) ;; Try to find the entry URL: (our-url (extract-urls single-title)) ;; Serialize the contents to NIL (return a string): (our-contents (plump:serialize (plump-sexp:parse (plump-sexp:serialize single-contents)) nil))) ;; Write the data to the database: (when (and our-title our-contents ;; Only do it if we don't have this item yet :-) (not (retrieve-all (select :* (from :entries) (where (:and (:= :feedid (car feed-id)) (:= :title our-title))))))) (execute (insert-into :entries (set= :feedid (princ-to-string (car feed-id)) :title (princ-to-string our-title) :contents (princ-to-string our-contents) :url (if our-url (princ-to-string (caar our-url)) feed-url) :timestamp (timestamp-to-unix (now))))))) ;; Update the success timestamp in the database. (execute (update :feeds (set= :lastsuccess (timestamp-to-unix (now))) (where (:= :id (car feed-id)))))))) ;; Clean up if requested. (when +feed-cleanup+ (execute (delete-from :entries (where (:in :id (select :id (from :entries) (where (:= :feedid (car feed-id))) (order-by (:desc :timestamp)) (limit -1) (offset (* 2 +max-items-per-feed+)))))))) ;; We have a nicely filled database now. ;; Grab the newest entries and put them into our feed. (loop for item-list in (retrieve-all (select (:title :contents :url :timestamp) (from :entries) (where (:= :feedid (car feed-id))) (order-by (:asc :timestamp)) (limit +max-items-per-feed+)) :as 'trivial-types:association-list) do ;; Our list should look as follows now: ;; ((TITLE) (CONTENTS) (URL) (TIMESTAMP)) (let ((this-title (cdr (first item-list))) (this-contents (cdr (second item-list))) (this-url (cdr (third item-list))) (this-timestamp (cdr (fourth item-list)))) ;; Write each fetched item to the RSS file. (rss-item (princ-to-string this-title) :link this-url :description (princ-to-string this-contents) :pubDate (princ-to-string (timestamp-to-rssdate this-timestamp))))))))) (simple-file-error () ;; The feed folder is not writeable. (unless *is-web* (format t "Please fix the access rights for ~a for this script to work.~%" +feed-folder+)) (return nil)) (simple-stream-error () ;; Connection reset by peer. (format t (concatenate 'string "~%Feed " (prin1-to-string (car feed-id)) " has a website which is " "temporarily unavailable. We'll try later."))) (sb-bsd-sockets:connection-refused-error () ;; Connection refused. (format t (concatenate 'string "~%Feed " (prin1-to-string (car feed-id)) " has a website which is " "temporarily unavailable. We'll try later."))) (sb-bsd-sockets:interrupted-error () ;; Connection interrupted. (format t (concatenate 'string "~%Feed " (prin1-to-string (car feed-id)) " has a website which is " "temporarily unavailable. We'll try later."))) (dex:http-request-service-unavailable () ;; Temporary website error. Retry later. (format t (concatenate 'string "~%Feed " (prin1-to-string (car feed-id)) " has a website which is " "temporarily unavailable. We'll try later."))) (dex:http-request-forbidden () ;; Probably also temporary website error. Retry later. (format t (concatenate 'string "~%Feed " (prin1-to-string (car feed-id)) " has a website which is " "temporarily unavailable. We'll try later."))) (dex:http-request-failed (e) ;; Page not found. Assume it is gone. (if +remove-dead-feeds+ (progn ;; Remove the page from the feeds. (unless *is-web* (format t (concatenate 'string "~%Feed " (prin1-to-string (car feed-id)) " seems to have a broken website: " feed-url " could not be reached (" e "). We'll better remove it."))) (force-output nil) (delete-feed (list (write-to-string (car feed-id))))) (progn ;; Display a warning. (unless *is-web* (format t (concatenate 'string "~%Feed " (prin1-to-string (car feed-id)) " seems to have a broken website: " feed-url " could not be reached (" e ")."))) (force-output nil))))))) (setf *is-web* nil)) ;; AJAX handler for feed parsing: (defun-ajax ajax-parse-feeds () (*ajax-processor* :callback-data :response-text) (setf *is-web* t) (parse-all-feeds) "Good news: We just refreshed all of your generated RSS feeds. :-)") (defun start-webserver () "Runs the RSS parser's built-in web server." (format t "Starting the web server on port ~d. Press Ctrl+C to quit.~%~%" +webserver-port+) (force-output nil) (defparameter *server* (start (make-instance 'easy-acceptor :port +webserver-port+)))) (defun rssparser () "The main function, evaluating the command-line parameters." (cond ((string= *script-mode* "add") ;; add an entry (when (add-new-feed *script-arguments*) (format t "Success!~%"))) ((or (string= *script-mode* "delete") (string= *script-mode* "del")) ;; remove an entry (if (delete-feed *script-arguments*) (format t "Deletion successful!~%") (format t "This feed could not be deleted.~%"))) ((string= *script-mode* "list") ;; list all entries (let ((feedlist (list-all-feeds))) (if feedlist (progn ;; print a list of feeds (format t (concatenate 'string (prin1-to-string (list-length feedlist)) (if (eql 1 (list-length feedlist)) " feed is set up:~%" " feeds are set up:~%"))) (force-output nil) (print-feed-list feedlist)) (format t "You don't have any feeds yet.")))) ((string= *script-mode* "export") ;; show an SQLite command to transfer this feed elsewhere (let ((result (export-feed *script-arguments*))) (if result (format t "Execute this SQL command to add this feed to a new database:~% ~A~%~%" result) (format t "This feed could not be exported.~%")))) ((string= *script-mode* "parse") ;; the parser for existing sites (parse-all-feeds)) ((string= *script-mode* "webserver") ;; start the web server (handler-case (start-webserver) (sb-sys:interactive-interrupt () (format t "~%~%Quitting the web server. Goodbye.~%~%")))) (t ;; else ... (show-syntax)))) (rssparser) |