diff options
author | Nicolas LÅ“uillet <nicolas@loeuillet.org> | 2014-07-13 10:15:40 +0200 |
---|---|---|
committer | Nicolas LÅ“uillet <nicolas@loeuillet.org> | 2014-07-13 10:15:40 +0200 |
commit | 4e067ceabd705201a16b4c92cf4b23f3b990326c (patch) | |
tree | 939f3a8e5ff3ab9ee414a57a895d3e78e1d46ce3 /inc/3rdparty/site_config/standard/zeit.de.txt | |
parent | 58dbe103889148def78b0fc8744d3f94c56a1561 (diff) | |
download | wallabag-4e067ceabd705201a16b4c92cf4b23f3b990326c.tar.gz wallabag-4e067ceabd705201a16b4c92cf4b23f3b990326c.tar.zst wallabag-4e067ceabd705201a16b4c92cf4b23f3b990326c.zip |
updated specific configuration for parsing
Diffstat (limited to 'inc/3rdparty/site_config/standard/zeit.de.txt')
-rwxr-xr-x[-rw-r--r--] | inc/3rdparty/site_config/standard/zeit.de.txt | 89 |
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 | ||
8 | single_page_link: //a[@title='Druckversion'] | 8 | |
9 | tidy: no | 9 | single_page_link: //a[@title='Auf einer Seite'] |
10 | 10 | tidy: no | |
11 | title: //title | 11 | |
12 | date: substring-before( //li[@class="date"], " " ) | 12 | title: //title |
13 | author: //li[@class="author"]/a/text() | //li[@class="author first"]/a/text() | 13 | date: substring-before( //li[@class="date"], " " ) |
14 | author: substring-after(//li[@class='source first '], 'Quelle: ') | 14 | author: //li[@class="author"]/a/text() | //li[@class="author first"]/a/text() |
15 | 15 | author: substring-after(//li[@class='source first '], 'Quelle: ') | |
16 | strip_id_or_class: articleheader | 16 | |
17 | strip: //div[@id="comments"] | //div[@class="pagination block"] | //p[@class="ressortbacklink"] | //div[@id="relatedArticles"] | // div[@class="inline portrait"] | 17 | strip_id_or_class: articleheader |
18 | 18 | strip: //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 | |
20 | strip: //ul[@class="tools"] | 20 | #Removes author and date from the start |
21 | #Removes copyright statement - often disturb as first line of the news | 21 | strip: //ul[@class="tools"] |
22 | strip: //p[@class="copyright"] | 22 | #Removes copyright statement - often disturb as first line of the news |
23 | strip: //div[@class="copyright"] | 23 | strip: //p[@class="copyright"] |
24 | #Removes pagination links at the end | 24 | strip: //div[@class="copyright"] |
25 | strip: //div[@class="pagination"] | 25 | #Removes pagination links at the end |
26 | 26 | strip: //div[@class="pagination"] | |
27 | # Fix picture captions | 27 | |
28 | wrap_in(small): //p[@class="caption"]/text() | 28 | # Fix picture captions |
29 | 29 | wrap_in(small): //p[@class="caption"]/text() | |
30 | # Fix sub-headlines | 30 | |
31 | wrap_in(h2): //p/strong | 31 | # Fix sub-headlines |
32 | dissolve: //h2/strong | 32 | wrap_in(h2): //p/strong |
33 | 33 | dissolve: //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 | |
35 | strip_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. |
36 | strip_id_or_class:"bottom" | 36 | strip_id_or_class:"informatives" |
37 | strip_id_or_class:"teasermosaic" | 37 | strip_id_or_class:"bottom" |
38 | strip_id_or_class:"comments" | 38 | strip_id_or_class:"teasermosaic" |
39 | strip_id_or_class:"articlefooter af" | 39 | strip_id_or_class:"comments" |
40 | strip_id_or_class:"relateds" | 40 | strip_id_or_class:"articlefooter af" |
41 | strip_id_or_class:"pagination" | 41 | strip_id_or_class:"relateds" |
42 | 42 | strip_id_or_class:"pagination" | |
43 | footnotes: no | 43 | |
44 | test_url: http://www.zeit.de/kultur/film/2012-12/Kurzfilmtag \ No newline at end of file | 44 | footnotes: no |
45 | test_url: http://www.zeit.de/kultur/film/2012-12/Kurzfilmtag | ||