From 41e3199b3fa8e49b362de214a51fb5ec11936410 Mon Sep 17 00:00:00 2001 From: "FiveFilters.org" Date: Mon, 13 May 2013 00:52:49 +0200 Subject: Mostly Instapaper changes --- foreignaffairs.com.txt | 34 ++++++++++++++++++++++++++++++++++ 1 file changed, 34 insertions(+) create mode 100644 foreignaffairs.com.txt (limited to 'foreignaffairs.com.txt') diff --git a/foreignaffairs.com.txt b/foreignaffairs.com.txt new file mode 100644 index 0000000..cf8b742 --- /dev/null +++ b/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 v1.3.1