aboutsummaryrefslogtreecommitdiffhomepage
path: root/inc/3rdparty/site_config/standard/zeit.de.txt
diff options
context:
space:
mode:
Diffstat (limited to 'inc/3rdparty/site_config/standard/zeit.de.txt')
-rwxr-xr-x[-rw-r--r--]inc/3rdparty/site_config/standard/zeit.de.txt89
1 files changed, 45 insertions, 44 deletions
diff --git a/inc/3rdparty/site_config/standard/zeit.de.txt b/inc/3rdparty/site_config/standard/zeit.de.txt
index 66a7f1ac..9815d478 100644..100755
--- a/inc/3rdparty/site_config/standard/zeit.de.txt
+++ b/inc/3rdparty/site_config/standard/zeit.de.txt
@@ -1,44 +1,45 @@
1# 2012-12-23 [carlo@...] fixed half-assed headlines in articles, removed inline author profiles, adjusted picture captions 1# 2013.10.30 [rezor92] fixed single_page_link
2# 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) 2# 2012-12-23 [carlo@...] fixed half-assed headlines in articles, removed inline author profiles, adjusted picture captions
3# 2011-12-09 [carlo@...] Removed "related articles" block 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# 2011-08-23 [carlo@...] changed single page link to use print version: page works better, less ambiguity. Related cleanups and simplifications. 4# 2011-12-09 [carlo@...] Removed "related articles" block
5# 2011-08-20 [carlo@...] added author, fixed date 5# 2011-08-23 [carlo@...] changed single page link to use print version: page works better, less ambiguity. Related cleanups and simplifications.
6 6# 2011-08-20 [carlo@...] added author, fixed date
7 7
8single_page_link: //a[@title='Druckversion'] 8
9tidy: no 9single_page_link: //a[@title='Auf einer Seite']
10 10tidy: no
11title: //title 11
12date: substring-before( //li[@class="date"], " " ) 12title: //title
13author: //li[@class="author"]/a/text() | //li[@class="author first"]/a/text() 13date: substring-before( //li[@class="date"], " " )
14author: substring-after(//li[@class='source first '], 'Quelle: ') 14author: //li[@class="author"]/a/text() | //li[@class="author first"]/a/text()
15 15author: substring-after(//li[@class='source first '], 'Quelle: ')
16strip_id_or_class: articleheader 16
17strip: //div[@id="comments"] | //div[@class="pagination block"] | //p[@class="ressortbacklink"] | //div[@id="relatedArticles"] | // div[@class="inline portrait"] 17strip_id_or_class: articleheader
18 18strip: //div[@id="comments"] | //div[@class="pagination block"] | //p[@class="ressortbacklink"] | //div[@id="relatedArticles"] | // div[@class="inline portrait"]
19#Removes author and date from the start 19
20strip: //ul[@class="tools"] 20#Removes author and date from the start
21#Removes copyright statement - often disturb as first line of the news 21strip: //ul[@class="tools"]
22strip: //p[@class="copyright"] 22#Removes copyright statement - often disturb as first line of the news
23strip: //div[@class="copyright"] 23strip: //p[@class="copyright"]
24#Removes pagination links at the end 24strip: //div[@class="copyright"]
25strip: //div[@class="pagination"] 25#Removes pagination links at the end
26 26strip: //div[@class="pagination"]
27# Fix picture captions 27
28wrap_in(small): //p[@class="caption"]/text() 28# Fix picture captions
29 29wrap_in(small): //p[@class="caption"]/text()
30# Fix sub-headlines 30
31wrap_in(h2): //p/strong 31# Fix sub-headlines
32dissolve: //h2/strong 32wrap_in(h2): //p/strong
33 33dissolve: //h2/strong
34#Sometimes things are embedded in the print version that are not displayed on the web, but will be displayed in the mobilized versions and lead even to problems. These sections are removed here. 34
35strip_id_or_class:"informatives" 35#Sometimes things are embedded in the print version that are not displayed on the web, but will be displayed in the mobilized versions and lead even to problems. These sections are removed here.
36strip_id_or_class:"bottom" 36strip_id_or_class:"informatives"
37strip_id_or_class:"teasermosaic" 37strip_id_or_class:"bottom"
38strip_id_or_class:"comments" 38strip_id_or_class:"teasermosaic"
39strip_id_or_class:"articlefooter af" 39strip_id_or_class:"comments"
40strip_id_or_class:"relateds" 40strip_id_or_class:"articlefooter af"
41strip_id_or_class:"pagination" 41strip_id_or_class:"relateds"
42 42strip_id_or_class:"pagination"
43footnotes: no 43
44test_url: http://www.zeit.de/kultur/film/2012-12/Kurzfilmtag \ No newline at end of file 44footnotes: no
45test_url: http://www.zeit.de/kultur/film/2012-12/Kurzfilmtag