diff options
author | Nicolas LÅ“uillet <nicolas.loeuillet@smile.fr> | 2014-10-10 13:33:54 +0200 |
---|---|---|
committer | Nicolas LÅ“uillet <nicolas.loeuillet@smile.fr> | 2014-10-10 13:33:54 +0200 |
commit | 44d35257e805856b4913c63fcbed3c0acb64bae8 (patch) | |
tree | 11e9d276c34b1b287706cb61182bdc71729661e2 /inc/3rdparty/site_config/standard/theglobalmail.org.txt | |
parent | af8292c1de1886cd975d79f0f42df40e0bd1c5bd (diff) | |
parent | cf8a5e1eedbed484dbcb1ddc9f7a13fc19b7a27b (diff) | |
download | wallabag-1.8.0.tar.gz wallabag-1.8.0.tar.zst wallabag-1.8.0.zip |
Merge branch 'dev'1.8.0
Diffstat (limited to 'inc/3rdparty/site_config/standard/theglobalmail.org.txt')
-rwxr-xr-x[-rw-r--r--] | inc/3rdparty/site_config/standard/theglobalmail.org.txt | 78 |
1 files changed, 39 insertions, 39 deletions
diff --git a/inc/3rdparty/site_config/standard/theglobalmail.org.txt b/inc/3rdparty/site_config/standard/theglobalmail.org.txt index fae0fb29..da1c84f9 100644..100755 --- a/inc/3rdparty/site_config/standard/theglobalmail.org.txt +++ b/inc/3rdparty/site_config/standard/theglobalmail.org.txt | |||
@@ -1,41 +1,41 @@ | |||
1 | title: //h1[@id="headline"] | 1 | title: //h1[@id="headline"] |
2 | author: //div[contains(@class, "editorial-byline-author")]/a | 2 | author: //div[contains(@class, "editorial-byline-author")]/a |
3 | date: substring-after(//div[contains(@class, "editorial-byline-meta")], " | ") | 3 | date: substring-after(//div[contains(@class, "editorial-byline-meta")], " | ") |
4 | 4 | ||
5 | # The article body contains a mix or article and non-article elements, so lot of manual tweaks are needed | 5 | # The article body contains a mix or article and non-article elements, so lot of manual tweaks are needed |
6 | body: //div[@id="template"] | 6 | body: //div[@id="template"] |
7 | strip_id_or_class: editorial-byline-pic | 7 | strip_id_or_class: editorial-byline-pic |
8 | strip_id_or_class: editorial-byline | 8 | strip_id_or_class: editorial-byline |
9 | strip_id_or_class: headline | 9 | strip_id_or_class: headline |
10 | 10 | ||
11 | # Include the leadin paragraph in the body text, but remove quotes because they're out of context | 11 | # Include the leadin paragraph in the body text, but remove quotes because they're out of context |
12 | dissolve: //div[contains(@id, "leadin")] | 12 | dissolve: //div[contains(@id, "leadin")] |
13 | strip_id_or_class: pullquote | 13 | strip_id_or_class: pullquote |
14 | 14 | ||
15 | # Image captions removed because they're confusing in body text | 15 | # Image captions removed because they're confusing in body text |
16 | strip_id_or_class: image-caption-content | 16 | strip_id_or_class: image-caption-content |
17 | 17 | ||
18 | # Remove header and footer | 18 | # Remove header and footer |
19 | strip_id_or_class: header | 19 | strip_id_or_class: header |
20 | strip_id_or_class: footer | 20 | strip_id_or_class: footer |
21 | 21 | ||
22 | # Remove the hidden logo that seems to be used to cause Facebook to show the logo instead of a random article image | 22 | # Remove the hidden logo that seems to be used to cause Facebook to show the logo instead of a random article image |
23 | strip: /html/body/span[contains(@style, "display: none")] | 23 | strip: /html/body/span[contains(@style, "display: none")] |
24 | 24 | ||
25 | # Remove search box | 25 | # Remove search box |
26 | strip_id_or_class: searchContainer | 26 | strip_id_or_class: searchContainer |
27 | strip: //div[contains(@class, "searchInstruction")] | 27 | strip: //div[contains(@class, "searchInstruction")] |
28 | strip: //div[contains(@class, "searchResults")]/h4 | 28 | strip: //div[contains(@class, "searchResults")]/h4 |
29 | 29 | ||
30 | # Remove the 'Letters to the Editor' section | 30 | # Remove the 'Letters to the Editor' section |
31 | strip_id_or_class: letter-text | 31 | strip_id_or_class: letter-text |
32 | strip_id_or_class: letter-from | 32 | strip_id_or_class: letter-from |
33 | strip_id_or_class: letter-date | 33 | strip_id_or_class: letter-date |
34 | 34 | ||
35 | # Remove Like/Tweet links | 35 | # Remove Like/Tweet links |
36 | strip_id_or_class: social-tab | 36 | strip_id_or_class: social-tab |
37 | 37 | ||
38 | # Remove 'divider' which causes an inexplicable slash to appear in the article body | 38 | # Remove 'divider' which causes an inexplicable slash to appear in the article body |
39 | strip_id_or_class: divider | 39 | strip_id_or_class: divider |
40 | 40 | ||
41 | test_url: http://www.theglobalmail.org/feature/tiramisu-time-in-pyongyang/88/ \ No newline at end of file | 41 | test_url: http://www.theglobalmail.org/feature/tiramisu-time-in-pyongyang/88/ \ No newline at end of file |