From 81bce8244b3d0e29918117a0fdcf40589e184ba9 Mon Sep 17 00:00:00 2001 From: Tim Groeneveld Date: Tue, 10 Mar 2015 11:50:15 +1100 Subject: Add some other missing news sites that do not always correctly work. * business.time.com * galwayindependent.com * help.fivefilters.org * ippmedia.com * mitchellrepublic.com * news.menshealth.com * planetsave.com * yourerie.com --- business.time.com.txt | 17 +++++++++++++++++ galwayindependent.com.txt | 3 +++ help.fivefilters.org.txt | 2 ++ ippmedia.com.txt | 4 ++++ mitchellrepublic.com.txt | 3 +++ news.menshealth.com.txt | 1 + planetsave.com.txt | 1 + yourerie.com.txt | 2 ++ 8 files changed, 33 insertions(+) create mode 100644 business.time.com.txt create mode 100644 galwayindependent.com.txt create mode 100644 help.fivefilters.org.txt create mode 100644 ippmedia.com.txt create mode 100644 mitchellrepublic.com.txt create mode 100644 news.menshealth.com.txt create mode 100644 planetsave.com.txt create mode 100644 yourerie.com.txt diff --git a/business.time.com.txt b/business.time.com.txt new file mode 100644 index 0000000..5502bea --- /dev/null +++ b/business.time.com.txt @@ -0,0 +1,17 @@ +# 2011-10-25 - carlo@... - Initial setup. + +single_page_link: //li[@class='print']/a/@href + +title: //h1 +author: //meta[@name="byline"]/@content +date: //meta[@name="date"]/@content + +strip: //span[@class="see"] +strip: //div[@class="byline"] +strip: //div[@id="date2"] +strip: //h1 +strip: //div[@class='post-rail-ad'] +strip: //div[@class='post-rail-content'] +strip: //aside[@class='post-rail'] + +test_url: http://www.time.com/time/specials/packages/article/0,28804,2094921_2094923_2094924,00.html diff --git a/galwayindependent.com.txt b/galwayindependent.com.txt new file mode 100644 index 0000000..d45b7ac --- /dev/null +++ b/galwayindependent.com.txt @@ -0,0 +1,3 @@ +title: //div[@class='leftCol']/h1 + +prune: no diff --git a/help.fivefilters.org.txt b/help.fivefilters.org.txt new file mode 100644 index 0000000..70a7d15 --- /dev/null +++ b/help.fivefilters.org.txt @@ -0,0 +1,2 @@ +title: //div[@class="title"]/h3 +date: substring-after(//div[@class="meta"], ": ") diff --git a/ippmedia.com.txt b/ippmedia.com.txt new file mode 100644 index 0000000..99f25dc --- /dev/null +++ b/ippmedia.com.txt @@ -0,0 +1,4 @@ +title: //div[@class="content_title"]//h2 +author: substring-after(//div[@class="byline"], "By ") +date: //div[@class="publish_date"] +strip: //div[@class="read_image_box"] diff --git a/mitchellrepublic.com.txt b/mitchellrepublic.com.txt new file mode 100644 index 0000000..fae858a --- /dev/null +++ b/mitchellrepublic.com.txt @@ -0,0 +1,3 @@ +body: //div[@class='section'] +strip_id_or_class: mediumtxt +strip: //strong[contains diff --git a/news.menshealth.com.txt b/news.menshealth.com.txt new file mode 100644 index 0000000..a07fdac --- /dev/null +++ b/news.menshealth.com.txt @@ -0,0 +1 @@ +strip: //span[@style="color: #cf1206;"] diff --git a/planetsave.com.txt b/planetsave.com.txt new file mode 100644 index 0000000..d6f34e2 --- /dev/null +++ b/planetsave.com.txt @@ -0,0 +1 @@ +strip_id_or_class: author-bio-box diff --git a/yourerie.com.txt b/yourerie.com.txt new file mode 100644 index 0000000..b46b09e --- /dev/null +++ b/yourerie.com.txt @@ -0,0 +1,2 @@ +body: //div[@class="nxFullTextData"] +test_url: http://yourerie.com/fulltext?nxd_id=306552 -- cgit v1.3.1