diff options
Diffstat (limited to 'zeit.de.txt')
| -rw-r--r-- | zeit.de.txt | 7 |
1 files changed, 5 insertions, 2 deletions
diff --git a/zeit.de.txt b/zeit.de.txt index 9815d47..4e00894 100644 --- a/zeit.de.txt +++ b/zeit.de.txt @@ -1,3 +1,4 @@ +# 2015.07.08 [Marvin Dickhaus] fixed single_page_link # 2013.10.30 [rezor92] fixed single_page_link # 2012-12-23 [carlo@...] fixed half-assed headlines in articles, removed inline author profiles, adjusted picture captions # 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) @@ -5,8 +6,7 @@ # 2011-08-23 [carlo@...] changed single page link to use print version: page works better, less ambiguity. Related cleanups and simplifications. # 2011-08-20 [carlo@...] added author, fixed date - -single_page_link: //a[@title='Auf einer Seite'] +single_page_link: //a[contains(@href, 'komplettansicht')] tidy: no title: //title @@ -24,6 +24,8 @@ strip: //p[@class="copyright"] strip: //div[@class="copyright"] #Removes pagination links at the end strip: //div[@class="pagination"] +#Removes link to main page at the bottom of some articles (Zur Startseite) +strip: //a[@href='http://www.zeit.de'] # Fix picture captions wrap_in(small): //p[@class="caption"]/text() @@ -43,3 +45,4 @@ strip_id_or_class:"pagination" footnotes: no test_url: http://www.zeit.de/kultur/film/2012-12/Kurzfilmtag +test_url: http://www.zeit.de/kultur/2015-07/kapitalismuskritik-selbstberuhigung-armin-nassehi |