(defvoo nnweb-directory (nnheader-concat gnus-directory "nnweb/")
"Where nnweb will save its files.")
-(defvoo nnweb-type 'dejanews
+(defvoo nnweb-type 'google
"What search engine type is being used.
-Valid types include `dejanews', `dejanewsold', `reference',
+Valid types include `google', `dejanews', `dejanewsold', `reference',
and `altavista'.")
(defvar nnweb-type-definition
'(
- (dejanews ;; bought by google.com
- (article . nnweb-google-wash-article)
- (id . "http://groups.google.com/groups?as_umsgid=%s")
+ (google
+ ;;(article . nnweb-google-wash-article)
+ ;;(id . "http://groups.google.com/groups?as_umsgid=%s")
+ (article . ignore)
+ (id . "http://groups.google.com/groups?selm=%s&output=gplain")
+ ;;(reference . nnweb-google-reference)
+ (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 . nnweb-google-wash-article)
+ ;;(id . "http://groups.google.com/groups?as_umsgid=%s")
+ (article . ignore)
+ (id . "http://groups.google.com/groups?selm=%s&output=gplain")
+ ;;(reference . nnweb-google-reference)
+ (reference . identity)
(map . nnweb-google-create-mapping)
(search . nnweb-google-search)
(address . "http://groups.google.com/groups")
(deffoo nnweb-request-scan (&optional group server)
(nnweb-possibly-change-server group server)
+ (if nnweb-ephemeral-p
+ (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-group group)
(setq nnweb-type (nth 2 info))
(setq nnweb-search (nth 3 info))
(unless dont-check
(and (stringp article)
(nnweb-definition 'id t)
(let ((fetch (nnweb-definition 'id))
- art)
+ art active)
(when (string-match "^<\\(.*\\)>$" article)
(setq art (match-string 1 article)))
- (and fetch
- art
- (mm-with-unibyte-current-buffer
- (nnweb-fetch-url
- (format fetch article)))))))
+ (when (and fetch art)
+ (setq url (format fetch art))
+ (mm-with-unibyte-current-buffer
+ (nnweb-fetch-url url))
+ (if (nnweb-definition 'reference t)
+ (setq article
+ (funcall (nnweb-definition
+ 'reference) article)))))))
(unless nnheader-callback-function
- (funcall (nnweb-definition 'article))
- (nnweb-decode-entities))
+ (funcall (nnweb-definition 'article)))
(nnheader-report 'nnweb "Fetched article %s" article)
(cons group (and (numberp article) article))))))
(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)
- (not (equal group nnweb-group)))
- (setq nnweb-hashtb (gnus-make-hashtable 4095))
+ (equal group nnweb-group))
(nnweb-request-group group nil t))))
(defun nnweb-init (server)
(while (search-forward "," nil t)
(replace-match " " t t)))
(widen)
+ (nnweb-decode-entities)
(set-marker body nil))))
(defun nnweb-reference-search (search)
(while (re-search-forward "<A.*\\?id@\\([^\"]+\\)\">[0-9]+</A>" nil t)
(replace-match "<\\1> " t)))
(widen)
- (nnweb-remove-markup)))
+ (nnweb-remove-markup)
+ (nnweb-decode-entities)))
(defun nnweb-altavista-search (search &optional part)
(url-insert-file-contents
;;;
(defun nnweb-google-wash-article ()
- (let ((case-fold-search t))
+ (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)
+ (search-backward "<table " nil t 2)
(delete-region (point-min) (point))
- (if (search-forward "[view thread]" nil t)
+ (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"))
(nnweb-remove-markup)
- (nnweb-decode-entities)
+ (goto-char (point-min))
(while (re-search-forward "^[ \t]*\n" nil t)
(replace-match ""))
(goto-char (point-max))
(search-forward "</pre>" nil t)
(delete-region (point) (point-max))
(nnweb-remove-markup)
- (nnweb-decode-entities)
(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))
+ (nnweb-remove-markup)
+ (nnweb-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))
+ (nnweb-remove-markup)
+ (nnweb-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 2)
+ Date (match-string 1)))
+ (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
+ (nnweb-fetch-url (mail-header-xref header)))
+ (caar map))))
+
(defun nnweb-google-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 ((i 0)
- (more t)
- (case-fold-search t)
- (active (or (cadr (assoc nnweb-group nnweb-group-alist))
- (cons 1 0)))
- Subject Score Date Newsgroups From Message-ID
- map url)
- (while more
- ;; Go through all the article hits on this page.
- (goto-char (point-min))
- (while (re-search-forward
- "a href=/groups\\(\\?[^ \">]*seld=[0-9]+[^ \">]*\\)" nil t)
- (setq url
- (concat (nnweb-definition 'address)
- (match-string 1)))
- (narrow-to-region (search-forward ">" nil t)
- (search-forward "</a>" nil t))
- (nnweb-remove-markup)
- (nnweb-decode-entities)
- (setq Subject (buffer-string))
- (goto-char (point-max))
- (widen)
- (forward-line 2)
- (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))
- (nnweb-remove-markup)
- (nnweb-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 2)
- Date (match-string 1)))
- (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 Message-ID
- nil 0 0 url))
- map)
- (nnweb-set-hashtb (cadar map) (car map))))
- ;; FIXME: There is more.
- (setq more nil))
- ;; Return the articles in the right order.
- (setq nnweb-articles
- (sort (nconc nnweb-articles map) 'car-less-than-car))))))
+ (let ((more t))
+ (while more
+ (setq nnweb-articles
+ (nconc nnweb-articles (nnweb-google-parse-1)))
+ ;; FIXME: There is more.
+ (setq more nil))
+ ;; Return the articles in the right order.
+ (setq nnweb-articles
+ (sort nnweb-articles 'car-less-than-car))))))
(defun nnweb-google-search (search)
(nnweb-insert
(defun nnweb-google-identity (url)
"Return an unique identifier based on URL."
- (if (string-match "seld=\\([0-9]+\\)" url)
+ (if (string-match "selm=\\([^ &>]+\\)" url)
(match-string 1 url)
url))
"Insert the contents from an URL in the current buffer.
If FOLLOW-REFRESH is non-nil, redirect refresh url in META."
(let ((name buffer-file-name))
- (if follow-refresh
+ (if follow-refresh
(save-restriction
(narrow-to-region (point) (point))
(url-insert-file-contents url)
(listp (cdr element)))
(nnweb-text-1 element)))))
-(defun nnweb-replace-in-string (string match newtext)
- (while (string-match match string)
- (setq string (replace-match newtext t t string)))
- string)
-
(provide 'nnweb)
;;; nnweb.el ends here