sb-zeit-de.el fix

[David Hansen <david.hansen@xxxxxxx>]

Hello,

2008-04-22 David Hansen <david.hansen@xxxxxxx>

        * (shimbun-zeit-de-x-face-alist): New variable.
        * (shimbun-zeit-de-content-end): Follow new page layout.
        * (shimbun-get-headers): Remove "from=rss" parameter from the URL.
        * (shimbun-clear-contents): Filter more junk.

*** sb-zeit-de.el.~1.13.~	2007-10-20 19:55:11.000000000 +0200
--- sb-zeit-de.el	2008-04-22 23:16:19.000000000 +0200
***************
*** 39,44 ****
--- 39,48 ----
      "international" "leben" "literatur" "musik" "news" "reisen"
      "schule" "sport" "studium" "wirtschaft" "wissen" "zuender"))
  
+ (defvar shimbun-zeit-de-x-face-alist
+   '(("default" . "X-Face: +@u:6eD3Nq>u{P_Ev&\"A6eW=EA{5H[OqH;|oz7H>atafNFsUS-&7\
+ %\\qo;KFS%E`=t5Z)'q~lhfl6<7rQ=]")))
+ 
  (defvar shimbun-zeit-de-content-start
    "title\">\\|<!--content starts here-->\\(?:<table[^>]+>\\)?")
  
***************
*** 46,52 ****
    (concat
     "</body>\\|</html>\\|navigation[^><]*>[^A]\\|"
     "<script language=\"JavaScript1\.2\" type=\"text/javascript\">\\|"
!    "<div[^>]+class=\"comments"))
  
  (defvar shimbun-zeit-de-from-address "DieZeit@xxxxxxx")
  
--- 50,56 ----
    (concat
     "</body>\\|</html>\\|navigation[^><]*>[^A]\\|"
     "<script language=\"JavaScript1\.2\" type=\"text/javascript\">\\|"
!    "<div[^>]+\\(class\\|id\\)=\"comments"))
  
  (defvar shimbun-zeit-de-from-address "DieZeit@xxxxxxx")
  
***************
*** 62,67 ****
--- 66,74 ----
    (mapc
     (lambda (header)
       (let ((url (shimbun-header-xref header)))
+        ;; remove the "?from=rss" parameter
+        (when (string-match "\\(.*\\)\\?from=rss$" url)
+          (setq url (match-string 1 url)))
         (cond ((string-match "\\`http://www\\.zeit\\.de" url)
  	      (shimbun-header-set-xref header (concat url "?page=all")))
  	     ((string-match "\\`/" url)
***************
*** 101,106 ****
--- 108,114 ----
  						    header)
  
    ;;  remove advertisements and 1-pixel-images aka webbugs
+   (shimbun-remove-tags "<!--START: LESERMEINUNG-->" "<!--ENDE: LESERMEINUNG-->")
    (shimbun-remove-tags "<div[^>]*class=\"?\\(?:ad\\|most_read\\)" "</div>")
    (shimbun-remove-tags "<a[^>]*doubleclick.net" "</a>")
    (shimbun-remove-tags "<IFRAME[^>]*doubleclick.net[^>]*>")