From 4e067ceabd705201a16b4c92cf4b23f3b990326c Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Nicolas=20L=C5=93uillet?= Date: Sun, 13 Jul 2014 10:15:40 +0200 Subject: updated specific configuration for parsing --- .../site_config/standard/foreignaffairs.com.txt | 34 ++++++++++++++++++++++ 1 file changed, 34 insertions(+) create mode 100755 inc/3rdparty/site_config/standard/foreignaffairs.com.txt (limited to 'inc/3rdparty/site_config/standard/foreignaffairs.com.txt') diff --git a/inc/3rdparty/site_config/standard/foreignaffairs.com.txt b/inc/3rdparty/site_config/standard/foreignaffairs.com.txt new file mode 100755 index 00000000..cf8b742f --- /dev/null +++ b/inc/3rdparty/site_config/standard/foreignaffairs.com.txt @@ -0,0 +1,34 @@ +# TIDY +#tidy: no +# PRUNE +#prune: no + +# SINGLE PAGE +single_page_link: //div[@class='showlinks']/a + +# TITLE +title: //h1[@class="title"] + +# AUTHOR +author: //div[contains(@class,"field-field-article-display-authors")]/div/div/a/text() + +# DATE +date: //div[contains(@class,"field-field-article-issue")]/div/div/a/text() | //span[@class="date-display-single"] + +# BODY +body: //div[contains(@class,"content-resize")] + +# Remove clutter +strip: //div[@class="article-sidebar"] +strip: //div[@class="showlinks"] +strip: //div[contains(@class,"premium-box")] +strip: //div[contains(@class,"premium-box")] +strip: //table[contains(@border,"2")] + +# Fix picture captions +wrap_in(small): //p/img/following-sibling::em +wrap_in(small): //p[img]/text() + +# Fix sub-headlines +wrap_in(h3): //div[contains(@class,"field-field-article-subtitle")]/div/div/text() +test_url: http://www.foreignaffairs.com/articles/138810/pierre-n-leval/the-long-arm-of-international-law \ No newline at end of file -- cgit v1.2.3