diff options
| -rw-r--r-- | songshuhui.net.txt | 10 | ||||
| -rw-r--r-- | xfgjls.com.txt | 18 | ||||
| -rw-r--r-- | ynet.co.il.txt | 50 |
3 files changed, 39 insertions, 39 deletions
diff --git a/songshuhui.net.txt b/songshuhui.net.txt index 51a7ac7..a923359 100644 --- a/songshuhui.net.txt +++ b/songshuhui.net.txt @@ -1,7 +1,7 @@ -# This filter is tested on:
-# http://songshuhui.net/archives/65522
-# http://songshuhui.net/archives/75760
-title://h2/span/a
-date:substring-before(substring-after(//div[@class='atrctitle']/div, '发表于'),' |')
+# This filter is tested on: +# http://songshuhui.net/archives/65522 +# http://songshuhui.net/archives/75760 +title://h2/span/a +date:substring-before(substring-after(//div[@class='atrctitle']/div, '发表于'),' |') body://div[@class='entry'] test_url: http://songshuhui.net/archives/74819
\ No newline at end of file diff --git a/xfgjls.com.txt b/xfgjls.com.txt index 919d416..2dc247a 100644 --- a/xfgjls.com.txt +++ b/xfgjls.com.txt @@ -1,11 +1,11 @@ -# This filter is tested on:
-# http://www.xfgjls.com/magazine/html/?131.html
-# http://www.xfgjls.com/magazine/html/?170.html
-
-body://h3/following-sibling::div
-title: //h3
-date: substring-before(//h3/following-sibling::div/p, ' ')
-author: substring-before(substring-after(//h3/following-sibling::div/p, '作者:'), '来源')
-wrap_in(strong)://span[contains(@style, "FONT-WEIGHT: bold")]
+# This filter is tested on: +# http://www.xfgjls.com/magazine/html/?131.html +# http://www.xfgjls.com/magazine/html/?170.html + +body://h3/following-sibling::div +title: //h3 +date: substring-before(//h3/following-sibling::div/p, ' ') +author: substring-before(substring-after(//h3/following-sibling::div/p, '作者:'), '来源') +wrap_in(strong)://span[contains(@style, "FONT-WEIGHT: bold")] dissolve://span[@style="FONT-FAMILY: '宋体'; FONT-SIZE: 10.5pt; FONT-WEIGHT: bold; mso-spacerun: 'yes'"] test_url: http://www.xfgjls.com/magazine/html/?170.html
\ No newline at end of file diff --git a/ynet.co.il.txt b/ynet.co.il.txt index 195eebf..aa86566 100644 --- a/ynet.co.il.txt +++ b/ynet.co.il.txt @@ -1,26 +1,26 @@ -body: //span[@id='article_content' or @class='text16g']
-
-# ads
-strip: //div[.//div[contains(@id, 'ads.')]]
-# related content heading
-strip: //p[contains(., 'עוד בערוץ החדשות של ynet:')]
-strip: //p[contains(., 'כותרות אחרונות מהעולם בחדשות ynet:')]
-strip: //div[contains(., 'אינציקלופדיית ynet:')]
-# related content links
-strip: //a[@class='bluelink']
-# strip image bullets
-strip_image_src: ynet_manual_bullet.png
-
-prune: no
-tidy: no
-
-# prevent JS issues
-find_string: <script type='text/javascript'>
-replace_string: <div style="display:none;">
-find_string: </script>
-replace_string: </div>
-
-test_url: http://www.ynet.co.il/articles/0,7340,L-4354266,00.html
-test_url: http://www.ynet.co.il/articles/0,7340,L-4354268,00.html
-#feed
+body: //span[@id='article_content' or @class='text16g'] + +# ads +strip: //div[.//div[contains(@id, 'ads.')]] +# related content heading +strip: //p[contains(., 'עוד בערוץ החדשות של ynet:')] +strip: //p[contains(., 'כותרות אחרונות מהעולם בחדשות ynet:')] +strip: //div[contains(., 'אינציקלופדיית ynet:')] +# related content links +strip: //a[@class='bluelink'] +# strip image bullets +strip_image_src: ynet_manual_bullet.png + +prune: no +tidy: no + +# prevent JS issues +find_string: <script type='text/javascript'> +replace_string: <div style="display:none;"> +find_string: </script> +replace_string: </div> + +test_url: http://www.ynet.co.il/articles/0,7340,L-4354266,00.html +test_url: http://www.ynet.co.il/articles/0,7340,L-4354268,00.html +#feed test_url: http://www.ynet.co.il/Integration/StoryRss2.xml
\ No newline at end of file |
