diff options
Diffstat (limited to 'inc/3rdparty/site_config')
-rwxr-xr-x | inc/3rdparty/site_config/standard/zeit.de.txt | 4 |
1 files changed, 4 insertions, 0 deletions
diff --git a/inc/3rdparty/site_config/standard/zeit.de.txt b/inc/3rdparty/site_config/standard/zeit.de.txt index 9815d478..8c9c1718 100755 --- a/inc/3rdparty/site_config/standard/zeit.de.txt +++ b/inc/3rdparty/site_config/standard/zeit.de.txt | |||
@@ -1,3 +1,4 @@ | |||
1 | # 2014-10-21 [Marmo] added stripping of inline ads and appropriate test_url | ||
1 | # 2013.10.30 [rezor92] fixed single_page_link | 2 | # 2013.10.30 [rezor92] fixed single_page_link |
2 | # 2012-12-23 [carlo@...] fixed half-assed headlines in articles, removed inline author profiles, adjusted picture captions | 3 | # 2012-12-23 [carlo@...] fixed half-assed headlines in articles, removed inline author profiles, adjusted picture captions |
3 | # 2012-03-17 [dkless@...] Cut metadata parts in the beginning and the ends of the content block; copyright entries for pictures removed; Author fixed, not sure if old entries still valid (I left them); Weird problems with some pages addressed (see last section for removing hidden section) | 4 | # 2012-03-17 [dkless@...] Cut metadata parts in the beginning and the ends of the content block; copyright entries for pictures removed; Author fixed, not sure if old entries still valid (I left them); Weird problems with some pages addressed (see last section for removing hidden section) |
@@ -16,6 +17,8 @@ author: substring-after(//li[@class='source first '], 'Quelle: ') | |||
16 | 17 | ||
17 | strip_id_or_class: articleheader | 18 | strip_id_or_class: articleheader |
18 | strip: //div[@id="comments"] | //div[@class="pagination block"] | //p[@class="ressortbacklink"] | //div[@id="relatedArticles"] | // div[@class="inline portrait"] | 19 | strip: //div[@id="comments"] | //div[@class="pagination block"] | //p[@class="ressortbacklink"] | //div[@id="relatedArticles"] | // div[@class="inline portrait"] |
20 | #Remove inline ads | ||
21 | strip: //div[@class="innerad"] | ||
19 | 22 | ||
20 | #Removes author and date from the start | 23 | #Removes author and date from the start |
21 | strip: //ul[@class="tools"] | 24 | strip: //ul[@class="tools"] |
@@ -43,3 +46,4 @@ strip_id_or_class:"pagination" | |||
43 | 46 | ||
44 | footnotes: no | 47 | footnotes: no |
45 | test_url: http://www.zeit.de/kultur/film/2012-12/Kurzfilmtag | 48 | test_url: http://www.zeit.de/kultur/film/2012-12/Kurzfilmtag |
49 | test_url: http://www.zeit.de/wissen/2014-10/ebola-nigeria-who | ||