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/chronicle.com.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/chronicle.com.txt')
-rwxr-xr-x[-rw-r--r--] | inc/3rdparty/site_config/standard/chronicle.com.txt | 30 |
1 files changed, 15 insertions, 15 deletions
diff --git a/inc/3rdparty/site_config/standard/chronicle.com.txt b/inc/3rdparty/site_config/standard/chronicle.com.txt index 0c6c11ed..e86d3eca 100644..100755 --- a/inc/3rdparty/site_config/standard/chronicle.com.txt +++ b/inc/3rdparty/site_config/standard/chronicle.com.txt | |||
@@ -1,17 +1,17 @@ | |||
1 | title: //h1[contains(@class, "entry-title")] | 1 | title: //h1[contains(@class, "entry-title")] |
2 | author: //p[contains(@class, "byline")] | 2 | author: //p[contains(@class, "byline")] |
3 | 3 | ||
4 | # blog articles (chronicle.com/blogs/*) | 4 | # blog articles (chronicle.com/blogs/*) |
5 | body: //div[contains(@class, "abstract")] | 5 | body: //div[contains(@class, "abstract")] |
6 | date: //p[contains(@class, "time")] | 6 | date: //p[contains(@class, "time")] |
7 | 7 | ||
8 | # all (?) other articles | 8 | # all (?) other articles |
9 | body: //div[@id="article-body"] | 9 | body: //div[@id="article-body"] |
10 | date: //p[contains(@class, "dateline")] | 10 | date: //p[contains(@class, "dateline")] |
11 | 11 | ||
12 | # remove sidebars containing images (I assume this is desired for Instapaper) | 12 | # remove sidebars containing images (I assume this is desired for Instapaper) |
13 | strip: //div[@id="related"] | 13 | strip: //div[@id="related"] |
14 | strip: //div[contains(@class, "image")] | 14 | strip: //div[contains(@class, "image")] |
15 | 15 | ||
16 | # note that if you're not a Chronicle subscriber (personally or institutionally), you'll only see the first couple of paragraphs of the article, and Instapaper will display that with some crap above and below. thank goodness for that bookmarklet | 16 | # note that if you're not a Chronicle subscriber (personally or institutionally), you'll only see the first couple of paragraphs of the article, and Instapaper will display that with some crap above and below. thank goodness for that bookmarklet |
17 | test_url: http://chronicle.com/article/In-a-Land-of-Second-Chances/128375/ \ No newline at end of file | 17 | test_url: http://chronicle.com/article/In-a-Land-of-Second-Chances/128375/ \ No newline at end of file |