;;; nnweb.el --- retrieving articles via web search engines
-;; Copyright (C) 1996, 1997, 1998, 1999, 2000, 2001, 2002, 2003
-;; Free Software Foundation, Inc.
+;; Copyright (C) 1996,97,98 Free Software Foundation, Inc.
;; Author: Lars Magne Ingebrigtsen <larsi@gnus.org>
;; Keywords: news
;;; Commentary:
-;; Note: You need to have `w3' installed for some functions to work.
+;; Note: You need to have `url' and `w3' installed for this
+;; backend to work.
;;; Code:
(require 'message)
(require 'gnus-util)
(require 'gnus)
+(require 'w3)
+(require 'url)
(require 'nnmail)
-(require 'mm-util)
-(require 'mm-url)
-(eval-and-compile
- (ignore-errors
- (require 'url)))
-(autoload 'w3-parse-buffer "w3-parse")
+(ignore-errors
+ (require 'w3-forms))
(nnoo-declare nnweb)
(defvoo nnweb-directory (nnheader-concat gnus-directory "nnweb/")
"Where nnweb will save its files.")
-(defvoo nnweb-type 'google
+(defvoo nnweb-type 'dejanews
"What search engine type is being used.
-Valid types include `google', `dejanews', and `gmane'.")
-
-(defvar nnweb-type-definition
- '((google
- (article . ignore)
- (id . "http://groups.google.com/groups?selm=%s&output=gplain")
- (reference . identity)
- (map . nnweb-google-create-mapping)
- (search . nnweb-google-search)
- (address . "http://groups.google.com/groups")
- (identifier . nnweb-google-identity))
- (dejanews ;; alias of google
- (article . ignore)
- (id . "http://groups.google.com/groups?selm=%s&output=gplain")
- (reference . identity)
- (map . nnweb-google-create-mapping)
- (search . nnweb-google-search)
- (address . "http://groups.google.com/groups")
- (identifier . nnweb-google-identity))
- (gmane
- (article . nnweb-gmane-wash-article)
- (id . "http://gmane.org/view.php?group=%s")
- (reference . identity)
- (map . nnweb-gmane-create-mapping)
- (search . nnweb-gmane-search)
- (address . "http://gmane.org/")
- (identifier . nnweb-gmane-identity)))
+Valid types include `dejanews', `dejanewsold', `reference',
+and `altavista'.")
+
+(defvoo nnweb-type-definition
+ '((dejanews
+ (article . nnweb-dejanews-wash-article)
+ (map . nnweb-dejanews-create-mapping)
+ (search . nnweb-dejanews-search)
+ (address . "http://x8.dejanews.com/dnquery.xp")
+ (identifier . nnweb-dejanews-identity))
+ (dejanewsold
+ (article . nnweb-dejanews-wash-article)
+ (map . nnweb-dejanews-create-mapping)
+ (search . nnweb-dejanewsold-search)
+ (address . "http://x8.dejanews.com/dnquery.xp")
+ (identifier . nnweb-dejanews-identity))
+ (reference
+ (article . nnweb-reference-wash-article)
+ (map . nnweb-reference-create-mapping)
+ (search . nnweb-reference-search)
+ (address . "http://www.reference.com/cgi-bin/pn/go")
+ (identifier . identity))
+ (altavista
+ (article . nnweb-altavista-wash-article)
+ (map . nnweb-altavista-create-mapping)
+ (search . nnweb-altavista-search)
+ (address . "http://www.altavista.digital.com/cgi-bin/query")
+ (id . "/cgi-bin/news?id@%s")
+ (identifier . identity)))
"Type-definition alist.")
(defvoo nnweb-search nil
- "Search string to feed to Google.")
+ "Search string to feed to DejaNews.")
(defvoo nnweb-max-hits 999
"Maximum number of hits to display.")
(set-buffer nntp-server-buffer)
(erase-buffer)
(let (article header)
- (mm-with-unibyte-current-buffer
- (while (setq article (pop articles))
- (when (setq header (cadr (assq article nnweb-articles)))
- (nnheader-insert-nov header))))
+ (while (setq article (pop articles))
+ (when (setq header (cadr (assq article nnweb-articles)))
+ (nnheader-insert-nov header)))
'nov)))
(deffoo nnweb-request-scan (&optional group server)
(nnweb-possibly-change-server group server)
- (if nnweb-ephemeral-p
- (setq nnweb-hashtb (gnus-make-hashtable 4095)))
+ (setq nnweb-hashtb (gnus-make-hashtable 4095))
(funcall (nnweb-definition 'map))
(unless nnweb-ephemeral-p
(nnweb-write-active)
(when (and group
(not (equal group nnweb-group))
(not nnweb-ephemeral-p))
- (setq nnweb-group group
- nnweb-articles nil)
(let ((info (assoc group nnweb-group-alist)))
- (when info
- (setq nnweb-type (nth 2 info))
- (setq nnweb-search (nth 3 info))
- (unless dont-check
- (nnweb-read-overview group)))))
+ (setq nnweb-group group)
+ (setq nnweb-type (nth 2 info))
+ (setq nnweb-search (nth 3 info))
+ (unless dont-check
+ (nnweb-read-overview group))))
(cond
((not nnweb-articles)
(nnheader-report 'nnweb "No matching articles"))
(let* ((header (cadr (assq article nnweb-articles)))
(url (and header (mail-header-xref header))))
(when (or (and url
- (mm-with-unibyte-current-buffer
- (mm-url-insert url)))
+ (nnweb-fetch-url url))
(and (stringp article)
(nnweb-definition 'id t)
(let ((fetch (nnweb-definition 'id))
- art active)
+ art)
(when (string-match "^<\\(.*\\)>$" article)
(setq art (match-string 1 article)))
- (when (and fetch art)
- (setq url (format fetch art))
- (mm-with-unibyte-current-buffer
- (mm-url-insert url))
- (if (nnweb-definition 'reference t)
- (setq article
- (funcall (nnweb-definition
- 'reference) article)))))))
+ (and fetch
+ art
+ (nnweb-fetch-url
+ (format fetch article))))))
(unless nnheader-callback-function
- (funcall (nnweb-definition 'article)))
+ (funcall (nnweb-definition 'article))
+ (nnweb-decode-entities))
(nnheader-report 'nnweb "Fetched article %s" article)
- (cons group (and (numberp article) article))))))
+ t))))
(deffoo nnweb-close-server (&optional server)
(when (and (nnweb-server-opened server)
t))
(deffoo nnweb-request-update-info (group info &optional server)
- (nnweb-possibly-change-server group server))
+ (nnweb-possibly-change-server group server)
+ ;;(setcar (cddr info) nil)
+ )
(deffoo nnweb-asynchronous-p ()
- nil)
+ t)
(deffoo nnweb-request-create-group (group &optional server args)
(nnweb-possibly-change-server nil server)
(deffoo nnweb-request-delete-group (group &optional force server)
(nnweb-possibly-change-server group server)
- (gnus-pull group nnweb-group-alist t)
- (nnweb-write-active)
+ (gnus-pull group nnweb-group-alist)
(gnus-delete-file (nnweb-overview-file group))
t)
(defun nnweb-read-overview (group)
"Read the overview of GROUP and build the map."
(when (file-exists-p (nnweb-overview-file group))
- (mm-with-unibyte-buffer
+ (nnheader-temp-write nil
(nnheader-insert-file-contents (nnweb-overview-file group))
(goto-char (point-min))
(let (header)
(defun nnweb-write-overview (group)
"Write the overview file for GROUP."
- (with-temp-file (nnweb-overview-file group)
+ (nnheader-temp-write (nnweb-overview-file group)
(let ((articles nnweb-articles))
(while articles
(nnheader-insert-nov (cadr (pop articles)))))))
(defun nnweb-write-active ()
"Save the active file."
- (gnus-make-directory nnweb-directory)
- (with-temp-file (nnheader-concat nnweb-directory "active")
+ (nnheader-temp-write (nnheader-concat nnweb-directory "active")
(prin1 `(setq nnweb-group-alist ',nnweb-group-alist) (current-buffer))))
(defun nnweb-read-active ()
(nnweb-open-server server)))
(unless nnweb-group-alist
(nnweb-read-active))
- (unless nnweb-hashtb
- (setq nnweb-hashtb (gnus-make-hashtable 4095)))
(when group
(when (and (not nnweb-ephemeral-p)
- (equal group nnweb-group))
+ (not (equal group nnweb-group)))
(nnweb-request-group group nil t))))
(defun nnweb-init (server)
(unless (gnus-buffer-live-p nnweb-buffer)
(setq nnweb-buffer
(save-excursion
- (mm-with-unibyte
- (nnheader-set-temp-buffer
- (format " *nnweb %s %s %s*"
- nnweb-type nnweb-search server))
- (current-buffer))))))
+ (nnheader-set-temp-buffer
+ (format " *nnweb %s %s %s*" nnweb-type nnweb-search server))))))
+
+(defun nnweb-fetch-url (url)
+ (save-excursion
+ (if (not nnheader-callback-function)
+ (let ((buf (current-buffer)))
+ (save-excursion
+ (set-buffer nnweb-buffer)
+ (erase-buffer)
+ (url-insert-file-contents url)
+ (copy-to-buffer buf (point-min) (point-max))
+ t))
+ (nnweb-url-retrieve-asynch
+ url 'nnweb-callback (current-buffer) nnheader-callback-function)
+ t)))
+
+(defun nnweb-callback (buffer callback)
+ (when (gnus-buffer-live-p url-working-buffer)
+ (save-excursion
+ (set-buffer url-working-buffer)
+ (funcall (nnweb-definition 'article))
+ (nnweb-decode-entities)
+ (set-buffer buffer)
+ (goto-char (point-max))
+ (insert-buffer-substring url-working-buffer))
+ (funcall callback t)
+ (gnus-kill-buffer url-working-buffer)))
+
+(defun nnweb-url-retrieve-asynch (url callback &rest data)
+ (let ((url-request-method "GET")
+ (old-asynch url-be-asynchronous)
+ (url-request-data nil)
+ (url-request-extra-headers nil)
+ (url-working-buffer (generate-new-buffer-name " *nnweb*")))
+ (setq-default url-be-asynchronous t)
+ (save-excursion
+ (set-buffer (get-buffer-create url-working-buffer))
+ (setq url-current-callback-data data
+ url-be-asynchronous t
+ url-current-callback-func callback)
+ (url-retrieve url))
+ (setq-default url-be-asynchronous old-asynch)))
+
+(defun nnweb-encode-www-form-urlencoded (pairs)
+ "Return PAIRS encoded for forms."
+ (mapconcat
+ (function
+ (lambda (data)
+ (concat (w3-form-encode-xwfu (car data)) "="
+ (w3-form-encode-xwfu (cdr data)))))
+ pairs "&"))
+
+(defun nnweb-fetch-form (url pairs)
+ (let ((url-request-data (nnweb-encode-www-form-urlencoded pairs))
+ (url-request-method "POST")
+ (url-request-extra-headers
+ '(("Content-type" . "application/x-www-form-urlencoded"))))
+ (url-insert-file-contents url)
+ (setq buffer-file-name nil))
+ t)
+
+(defun nnweb-decode-entities ()
+ (goto-char (point-min))
+ (while (re-search-forward "&\\([a-z]+\\);" nil t)
+ (replace-match (char-to-string (or (cdr (assq (intern (match-string 1))
+ w3-html-entities))
+ ?#))
+ t t)))
+
+(defun nnweb-remove-markup ()
+ (goto-char (point-min))
+ (while (search-forward "<!--" nil t)
+ (delete-region (match-beginning 0)
+ (or (search-forward "-->" nil t)
+ (point-max))))
+ (goto-char (point-min))
+ (while (re-search-forward "<[^>]+>" nil t)
+ (replace-match "" t t)))
;;;
-;;; Deja bought by google.com
+;;; DejaNews functions.
;;;
-(defun nnweb-google-wash-article ()
- (let ((case-fold-search t) url)
- (goto-char (point-min))
- (re-search-forward "^<pre>" nil t)
- (narrow-to-region (point-min) (point))
- (search-backward "<table " nil t 2)
- (delete-region (point-min) (point))
- (if (re-search-forward "Search Result [0-9]+" nil t)
- (replace-match ""))
- (if (re-search-forward "View complete thread ([0-9]+ articles?)" nil t)
- (replace-match ""))
- (goto-char (point-min))
- (while (search-forward "<br>" nil t)
- (replace-match "\n"))
- (mm-url-remove-markup)
- (goto-char (point-min))
- (while (re-search-forward "^[ \t]*\n" nil t)
- (replace-match ""))
- (goto-char (point-max))
- (insert "\n")
- (widen)
- (narrow-to-region (point) (point-max))
- (search-forward "</pre>" nil t)
- (delete-region (point) (point-max))
- (mm-url-remove-markup)
- (widen)))
-
-(defun nnweb-google-parse-1 (&optional Message-ID)
- (let ((i 0)
- (case-fold-search t)
- (active (cadr (assoc nnweb-group nnweb-group-alist)))
- Subject Score Date Newsgroups From
- map url mid)
- (unless active
- (push (list nnweb-group (setq active (cons 1 0))
- nnweb-type nnweb-search)
- nnweb-group-alist))
- ;; Go through all the article hits on this page.
- (goto-char (point-min))
- (while (re-search-forward
- "a href=/groups\\(\\?[^ \">]*selm=\\([^ &\">]+\\)\\)" nil t)
- (setq mid (match-string 2)
- url (format
- "http://groups.google.com/groups?selm=%s&output=gplain" mid))
- (narrow-to-region (search-forward ">" nil t)
- (search-forward "</a>" nil t))
- (mm-url-remove-markup)
- (mm-url-decode-entities)
- (setq Subject (buffer-string))
- (goto-char (point-max))
- (widen)
- (forward-line 1)
- (when (looking-at "<br><font[^>]+>")
- (goto-char (match-end 0)))
- (if (not (looking-at "<a[^>]+>"))
- (skip-chars-forward " \t")
- (narrow-to-region (point)
- (search-forward "</a>" nil t))
- (mm-url-remove-markup)
- (mm-url-decode-entities)
- (setq Newsgroups (buffer-string))
- (goto-char (point-max))
- (widen)
- (skip-chars-forward "- \t"))
- (when (looking-at
- "\\([0-9]+\\)[/ ]\\([A-Za-z]+\\)[/ ]\\([0-9]+\\)[ \t]*by[ \t]*\\([^<]*\\) - <a")
- (setq From (match-string 4)
- Date (format "%s %s 00:00:00 %s"
- (match-string 2) (match-string 1)
- (match-string 3))))
- (forward-line 1)
- (incf i)
- (unless (nnweb-get-hashtb url)
- (push
- (list
- (incf (cdr active))
- (make-full-mail-header
- (cdr active) (if Newsgroups
- (concat "(" Newsgroups ") " Subject)
- Subject)
- From Date (or Message-ID mid)
- nil 0 0 url))
- map)
- (nnweb-set-hashtb (cadar map) (car map))))
- map))
-
-(defun nnweb-google-reference (id)
- (let ((map (nnweb-google-parse-1 id)) header)
- (setq nnweb-articles
- (nconc nnweb-articles map))
- (when (setq header (cadar map))
- (mm-with-unibyte-current-buffer
- (mm-url-insert (mail-header-xref header)))
- (caar map))))
-
-(defun nnweb-google-create-mapping ()
- "Perform the search and create a number-to-url alist."
+(defun nnweb-dejanews-create-mapping ()
+ "Perform the search and create an number-to-url alist."
(save-excursion
(set-buffer nnweb-buffer)
(erase-buffer)
(when (funcall (nnweb-definition 'search) nnweb-search)
- (let ((more t)
- (i 0))
- (while more
- (setq nnweb-articles
- (nconc nnweb-articles (nnweb-google-parse-1)))
- ;; Check if there are more articles to fetch
+ (let ((i 0)
+ (more t)
+ (case-fold-search t)
+ (active (or (cadr (assoc nnweb-group nnweb-group-alist))
+ (cons 1 0)))
+ Subject (Score "0") Date Newsgroup Author
+ map url)
+ (while more
+ ;; Go through all the article hits on this page.
+ (goto-char (point-min))
+ (nnweb-decode-entities)
+ (goto-char (point-min))
+ (while (re-search-forward "^ <P>\n" nil t)
+ (narrow-to-region
+ (point)
+ (cond ((re-search-forward "^ <P>\n" nil t)
+ (match-beginning 0))
+ ((search-forward "\n\n" nil t)
+ (point))
+ (t
+ (point-max))))
(goto-char (point-min))
- (incf i 100)
- (if (or (not (re-search-forward
- "<td nowrap><a href=\\([^>]+\\).*<span class=b>Next</span>" nil t))
- (>= i nnweb-max-hits))
- (setq more nil)
- ;; Yup, there are more articles
- (setq more (concat "http://groups.google.com" (match-string 1)))
- (when more
- (erase-buffer)
- (mm-url-insert more))))
- ;; Return the articles in the right order.
- (setq nnweb-articles
- (sort nnweb-articles 'car-less-than-car))))))
+ (looking-at ".*HREF=\"\\([^\"]+\\)\"\\(.*\\)")
+ (setq url (match-string 1))
+ (let ((begin (point)))
+ (nnweb-remove-markup)
+ (goto-char begin)
+ (while (search-forward "\t" nil t)
+ (replace-match " "))
+ (goto-char begin)
+ (end-of-line)
+ (setq Subject (buffer-substring begin (point)))
+ (if (re-search-forward
+ "^ Newsgroup: \\(.*\\)\n Posted on \\([0-9/]+\\) by \\(.*\\)$" nil t)
+ (setq Newsgroup (match-string 1)
+ Date (match-string 2)
+ Author (match-string 3))))
+ (widen)
+ (incf i)
+ (unless (nnweb-get-hashtb url)
+ (push
+ (list
+ (incf (cdr active))
+ (make-full-mail-header
+ (cdr active) Subject Author Date
+ (concat "<" (nnweb-identifier url) "@dejanews>")
+ nil 0 (string-to-int Score) url))
+ map)
+ (nnweb-set-hashtb (cadar map) (car map))))
+ ;; See whether there is a "Get next 20 hits" button here.
+ (if (or (not (re-search-forward
+ "HREF=\"\\([^\"]+\\)\"[<>b]+Next result" nil t))
+ (>= i nnweb-max-hits))
+ (setq more nil)
+ ;; Yup -- fetch it.
+ (setq more (match-string 1))
+ (erase-buffer)
+ (url-insert-file-contents more)))
+ ;; Return the articles in the right order.
+ (setq nnweb-articles
+ (sort (nconc nnweb-articles map) 'car-less-than-car))))))
-(defun nnweb-google-search (search)
- (mm-url-insert
- (concat
- (nnweb-definition 'address)
- "?"
- (mm-url-encode-www-form-urlencoded
- `(("q" . ,search)
- ("num". "100")
- ("hq" . "")
- ("hl" . "")
- ("lr" . "")
- ("safe" . "off")
- ("sites" . "groups")))))
+(defun nnweb-dejanews-wash-article ()
+ (let ((case-fold-search t))
+ (goto-char (point-min))
+ (re-search-forward "<PRE>" nil t)
+ (delete-region (point-min) (point))
+ (re-search-forward "</PRE>" nil t)
+ (delete-region (point) (point-max))
+ (nnweb-remove-markup)
+ (goto-char (point-min))
+ (while (and (looking-at " *$")
+ (not (eobp)))
+ (gnus-delete-line))
+ (while (looking-at "\\(^[^ ]+:\\) *")
+ (replace-match "\\1 " t)
+ (forward-line 1))
+ (when (re-search-forward "\n\n+" nil t)
+ (replace-match "\n" t t))
+ (goto-char (point-min))
+ (when (search-forward "[More Headers]" nil t)
+ (replace-match "" t t))))
+
+(defun nnweb-dejanews-search (search)
+ (nnweb-fetch-form
+ (nnweb-definition 'address)
+ `(("query" . ,search)
+ ("defaultOp" . "AND")
+ ("svcclass" . "dncurrent")
+ ("maxhits" . "100")
+ ("format" . "verbose2")
+ ("threaded" . "0")
+ ("showsort" . "date")
+ ("agesign" . "1")
+ ("ageweight" . "1")))
+ t)
+
+(defun nnweb-dejanewsold-search (search)
+ (nnweb-fetch-form
+ (nnweb-definition 'address)
+ `(("query" . ,search)
+ ("defaultOp" . "AND")
+ ("svcclass" . "dnold")
+ ("maxhits" . "100")
+ ("format" . "verbose2")
+ ("threaded" . "0")
+ ("showsort" . "date")
+ ("agesign" . "1")
+ ("ageweight" . "1")))
t)
-(defun nnweb-google-identity (url)
+(defun nnweb-dejanews-identity (url)
"Return an unique identifier based on URL."
- (if (string-match "selm=\\([^ &>]+\\)" url)
+ (if (string-match "recnum=\\([0-9]+\\)" url)
(match-string 1 url)
url))
;;;
-;;; gmane.org
+;;; InReference
;;;
-(defun nnweb-gmane-create-mapping ()
- "Perform the search and create a number-to-url alist."
+
+(defun nnweb-reference-create-mapping ()
+ "Perform the search and create an number-to-url alist."
(save-excursion
(set-buffer nnweb-buffer)
(erase-buffer)
(when (funcall (nnweb-definition 'search) nnweb-search)
- (let ((more t)
+ (let ((i 0)
+ (more t)
(case-fold-search t)
(active (or (cadr (assoc nnweb-group nnweb-group-alist))
(cons 1 0)))
- subject group url
- map)
- ;; Remove stuff from the beginning of results
- (goto-char (point-min))
- (search-forward "Search Results</h1><ul>" nil t)
- (delete-region (point-min) (point))
- (goto-char (point-min))
- ;; Iterate over the actual hits
- (while (re-search-forward ".*href=\"\\([^\"]+\\)\">\\(.*\\)" nil t)
- (setq url (concat "http://gmane.org/" (match-string 1)))
- (setq subject (match-string 2))
- (unless (nnweb-get-hashtb url)
- (push
- (list
- (incf (cdr active))
- (make-full-mail-header
- (cdr active) (concat "(" group ") " subject) nil nil
- nil nil 0 0 url))
- map)
- (nnweb-set-hashtb (cadar map) (car map))))
+ Subject Score Date Newsgroups From Message-ID
+ map url)
+ (while more
+ ;; Go through all the article hits on this page.
+ (goto-char (point-min))
+ (search-forward "</pre><hr>" nil t)
+ (delete-region (point-min) (point))
+ ;(nnweb-decode-entities)
+ (goto-char (point-min))
+ (while (re-search-forward "^ +[0-9]+\\." nil t)
+ (narrow-to-region
+ (point)
+ (if (re-search-forward "^$" nil t)
+ (match-beginning 0)
+ (point-max)))
+ (goto-char (point-min))
+ (when (looking-at ".*href=\"\\([^\"]+\\)\"")
+ (setq url (match-string 1)))
+ (nnweb-remove-markup)
+ (goto-char (point-min))
+ (while (search-forward "\t" nil t)
+ (replace-match " "))
+ (goto-char (point-min))
+ (while (re-search-forward "^\\([^:]+\\): \\(.*\\)$" nil t)
+ (set (intern (match-string 1)) (match-string 2)))
+ (widen)
+ (search-forward "</pre>" nil t)
+ (incf i)
+ (unless (nnweb-get-hashtb url)
+ (push
+ (list
+ (incf (cdr active))
+ (make-full-mail-header
+ (cdr active) (concat "(" Newsgroups ") " Subject) From Date
+ Message-ID
+ nil 0 (string-to-int Score) url))
+ map)
+ (nnweb-set-hashtb (cadar map) (car map))))
+ (setq more nil))
;; Return the articles in the right order.
(setq nnweb-articles
(sort (nconc nnweb-articles map) 'car-less-than-car))))))
-(defun nnweb-gmane-wash-article ()
+(defun nnweb-reference-wash-article ()
(let ((case-fold-search t))
(goto-char (point-min))
- (re-search-forward "<!--X-Head-of-Message-->" nil t)
+ (re-search-forward "^</center><hr>" nil t)
(delete-region (point-min) (point))
- (goto-char (point-min))
- (while (looking-at "^<li><em>\\([^ ]+\\)</em>.*</li>")
- (replace-match "\\1\\2" t)
- (forward-line 1))
- (mm-url-remove-markup)))
+ (search-forward "<pre>" nil t)
+ (forward-line -1)
+ (let ((body (point-marker)))
+ (search-forward "</pre>" nil t)
+ (delete-region (point) (point-max))
+ (nnweb-remove-markup)
+ (goto-char (point-min))
+ (while (looking-at " *$")
+ (gnus-delete-line))
+ (narrow-to-region (point-min) body)
+ (while (and (re-search-forward "^$" nil t)
+ (not (eobp)))
+ (gnus-delete-line))
+ (goto-char (point-min))
+ (while (looking-at "\\(^[^ ]+:\\) *")
+ (replace-match "\\1 " t)
+ (forward-line 1))
+ (goto-char (point-min))
+ (when (re-search-forward "^References:" nil t)
+ (narrow-to-region
+ (point) (if (re-search-forward "^$\\|^[^:]+:" nil t)
+ (match-beginning 0)
+ (point-max)))
+ (goto-char (point-min))
+ (while (not (eobp))
+ (unless (looking-at "References")
+ (insert "\t")
+ (forward-line 1)))
+ (goto-char (point-min))
+ (while (search-forward "," nil t)
+ (replace-match " " t t)))
+ (widen)
+ (set-marker body nil))))
-(defun nnweb-gmane-search (search)
- (mm-url-insert
+(defun nnweb-reference-search (search)
+ (url-insert-file-contents
(concat
(nnweb-definition 'address)
"?"
- (mm-url-encode-www-form-urlencoded
- `(("query" . ,search)))))
+ (nnweb-encode-www-form-urlencoded
+ `(("search" . "advanced")
+ ("querytext" . ,search)
+ ("subj" . "")
+ ("name" . "")
+ ("login" . "")
+ ("host" . "")
+ ("organization" . "")
+ ("groups" . "")
+ ("keywords" . "")
+ ("choice" . "Search")
+ ("startmonth" . "Jul")
+ ("startday" . "25")
+ ("startyear" . "1996")
+ ("endmonth" . "Aug")
+ ("endday" . "24")
+ ("endyear" . "1996")
+ ("mode" . "Quick")
+ ("verbosity" . "Verbose")
+ ("ranking" . "Relevance")
+ ("first" . "1")
+ ("last" . "25")
+ ("score" . "50")))))
(setq buffer-file-name nil)
t)
-
-(defun nnweb-gmane-identity (url)
- "Return a unique identifier based on URL."
- (if (string-match "group=\\(.+\\)" url)
- (match-string 1 url)
- url))
-
;;;
-;;; General web/w3 interface utility functions
+;;; Alta Vista
;;;
-(defun nnweb-insert-html (parse)
- "Insert HTML based on a w3 parse tree."
- (if (stringp parse)
- (insert (nnheader-string-as-multibyte parse))
- (insert "<" (symbol-name (car parse)) " ")
- (insert (mapconcat
- (lambda (param)
- (concat (symbol-name (car param)) "="
- (prin1-to-string
- (if (consp (cdr param))
- (cadr param)
- (cdr param)))))
- (nth 1 parse)
- " "))
- (insert ">\n")
- (mapcar 'nnweb-insert-html (nth 2 parse))
- (insert "</" (symbol-name (car parse)) ">\n")))
-
-(defun nnweb-parse-find (type parse &optional maxdepth)
- "Find the element of TYPE in PARSE."
- (catch 'found
- (nnweb-parse-find-1 type parse maxdepth)))
-
-(defun nnweb-parse-find-1 (type contents maxdepth)
- (when (or (null maxdepth)
- (not (zerop maxdepth)))
- (when (consp contents)
- (when (eq (car contents) type)
- (throw 'found contents))
- (when (listp (cdr contents))
- (dolist (element contents)
- (when (consp element)
- (nnweb-parse-find-1 type element
- (and maxdepth (1- maxdepth)))))))))
-
-(defun nnweb-parse-find-all (type parse)
- "Find all elements of TYPE in PARSE."
- (catch 'found
- (nnweb-parse-find-all-1 type parse)))
-
-(defun nnweb-parse-find-all-1 (type contents)
- (let (result)
- (when (consp contents)
- (if (eq (car contents) type)
- (push contents result)
- (when (listp (cdr contents))
- (dolist (element contents)
- (when (consp element)
- (setq result
- (nconc result (nnweb-parse-find-all-1 type element))))))))
- result))
-
-(defvar nnweb-text)
-(defun nnweb-text (parse)
- "Return a list of text contents in PARSE."
- (let ((nnweb-text nil))
- (nnweb-text-1 parse)
- (nreverse nnweb-text)))
-
-(defun nnweb-text-1 (contents)
- (dolist (element contents)
- (if (stringp element)
- (push element nnweb-text)
- (when (and (consp element)
- (listp (cdr element)))
- (nnweb-text-1 element)))))
+(defun nnweb-altavista-create-mapping ()
+ "Perform the search and create an number-to-url alist."
+ (save-excursion
+ (set-buffer nnweb-buffer)
+ (erase-buffer)
+ (let ((part 0))
+ (when (funcall (nnweb-definition 'search) nnweb-search part)
+ (let ((i 0)
+ (more t)
+ (case-fold-search t)
+ (active (or (cadr (assoc nnweb-group nnweb-group-alist))
+ (cons 1 0)))
+ subject date from id group
+ map url)
+ (while more
+ ;; Go through all the article hits on this page.
+ (goto-char (point-min))
+ (search-forward "<dt>" nil t)
+ (delete-region (point-min) (match-beginning 0))
+ (goto-char (point-min))
+ (while (search-forward "<dt>" nil t)
+ (replace-match "\n<blubb>"))
+ (nnweb-decode-entities)
+ (goto-char (point-min))
+ (while (re-search-forward "<blubb>.*href=\"\\([^\"]+\\)\"><strong>\\([^>]*\\)</strong></a><dd>\\([^-]+\\)- <b>\\([^<]+\\)<.*href=\"news:\\([^\"]+\\)\">.*\">\\(.+\\)</a><P>"
+ nil t)
+ (setq url (match-string 1)
+ subject (match-string 2)
+ date (match-string 3)
+ group (match-string 4)
+ id (concat "<" (match-string 5) ">")
+ from (match-string 6))
+ (incf i)
+ (unless (nnweb-get-hashtb url)
+ (push
+ (list
+ (incf (cdr active))
+ (make-full-mail-header
+ (cdr active) (concat "(" group ") " subject) from date
+ id nil 0 0 url))
+ map)
+ (nnweb-set-hashtb (cadar map) (car map))))
+ ;; See if we want more.
+ (when (or (not nnweb-articles)
+ (>= i nnweb-max-hits)
+ (not (funcall (nnweb-definition 'search)
+ nnweb-search (incf part))))
+ (setq more nil)))
+ ;; Return the articles in the right order.
+ (setq nnweb-articles
+ (sort (nconc nnweb-articles map) 'car-less-than-car)))))))
+
+(defun nnweb-altavista-wash-article ()
+ (goto-char (point-min))
+ (let ((case-fold-search t))
+ (when (re-search-forward "^<strong>" nil t)
+ (delete-region (point-min) (match-beginning 0)))
+ (goto-char (point-min))
+ (while (looking-at "<strong>\\([^ ]+\\) +</strong> +\\(.*\\)$")
+ (replace-match "\\1: \\2" t)
+ (forward-line 1))
+ (when (re-search-backward "^References:" nil t)
+ (narrow-to-region (point) (progn (forward-line 1) (point)))
+ (goto-char (point-min))
+ (while (re-search-forward "<A.*\\?id@\\([^\"]+\\)\">[0-9]+</A>" nil t)
+ (replace-match "<\\1> " t)))
+ (widen)
+ (nnweb-remove-markup)))
+
+(defun nnweb-altavista-search (search &optional part)
+ (url-insert-file-contents
+ (concat
+ (nnweb-definition 'address)
+ "?"
+ (nnweb-encode-www-form-urlencoded
+ `(("pg" . "aq")
+ ("what" . "news")
+ ,@(when part `(("stq" . ,(int-to-string (* part 30)))))
+ ("fmt" . "d")
+ ("q" . ,search)
+ ("r" . "")
+ ("d0" . "")
+ ("d1" . "")))))
+ (setq buffer-file-name nil)
+ t)
(provide 'nnweb)
projects / elisp / gnus.git- / blobdiff