From 5893b1ea08156e3edc58692b45bc5946a13709a4 Mon Sep 17 00:00:00 2001 From: Jeremy Benoist Date: Tue, 16 Feb 2016 14:57:02 +0100 Subject: Update website - remove redirected website where html structure isn't the same - remove redirected website which already have a siteconfig for the redirected url - rename website where html structure is the same as the previous one --- alt1040.com.txt | 2 -- community.service-now.com.txt | 8 -------- community.servicenow.com.txt | 8 ++++++++ guardian.co.uk.txt | 7 ------- hipertextual.com.txt | 2 ++ iceblog.free.fr.txt | 7 ------- m.guardian.co.uk.txt | 12 ------------ macformat.techradar.com.txt | 9 --------- mobile.slate.com.txt | 5 ----- neomoney.co.txt | 3 --- online.wsj.com.txt | 25 ------------------------- physicstoday.org.txt | 7 ------- red-hot-girls.com.txt | 5 ----- redtape.msnbc.msn.com.txt | 20 -------------------- retrieverweekly.com.txt | 6 ------ ritemail.blogspot.com.txt | 5 ----- ruttloff.org.txt | 3 --- simonwillison.net.txt | 5 ----- stockholmsfria.nu.txt | 7 ------- stockholmsfria.se.txt | 7 +++++++ thisismynext.com.txt | 8 -------- walrusmagazine.com.txt | 14 -------------- weblog.bignerdranch.com.txt | 5 ----- wyctim.com.txt | 3 --- zcommunications.org.txt | 7 ------- 25 files changed, 17 insertions(+), 173 deletions(-) delete mode 100755 alt1040.com.txt delete mode 100755 community.service-now.com.txt create mode 100755 community.servicenow.com.txt delete mode 100644 guardian.co.uk.txt create mode 100755 hipertextual.com.txt delete mode 100644 iceblog.free.fr.txt delete mode 100644 m.guardian.co.uk.txt delete mode 100755 macformat.techradar.com.txt delete mode 100755 mobile.slate.com.txt delete mode 100755 neomoney.co.txt delete mode 100755 online.wsj.com.txt delete mode 100755 physicstoday.org.txt delete mode 100755 red-hot-girls.com.txt delete mode 100755 redtape.msnbc.msn.com.txt delete mode 100755 retrieverweekly.com.txt delete mode 100755 ritemail.blogspot.com.txt delete mode 100755 ruttloff.org.txt delete mode 100755 simonwillison.net.txt delete mode 100755 stockholmsfria.nu.txt create mode 100755 stockholmsfria.se.txt delete mode 100755 thisismynext.com.txt delete mode 100755 walrusmagazine.com.txt delete mode 100755 weblog.bignerdranch.com.txt delete mode 100755 wyctim.com.txt delete mode 100755 zcommunications.org.txt diff --git a/alt1040.com.txt b/alt1040.com.txt deleted file mode 100755 index 4fd4571..0000000 --- a/alt1040.com.txt +++ /dev/null @@ -1,2 +0,0 @@ -body: //*[(@class = "historia")] -test_url: http://alt1040.com/2011/09/banda-ancha-en-america-latina-insignificante \ No newline at end of file diff --git a/community.service-now.com.txt b/community.service-now.com.txt deleted file mode 100755 index c9854b4..0000000 --- a/community.service-now.com.txt +++ /dev/null @@ -1,8 +0,0 @@ -body: //div[@id="center"]//div[@class="node"] -title: //div[@id="center"]//h2 -author: substring-after(//div[@id="center"]//div[@class="node"]//span[@class="submitted"], "—") -date: substring-before(//div[@id="center"]//div[@class="node"]//span[@class="submitted"], "—") -strip: //div[@id="center"]//h2[1] -strip: //span[@class="submitted"][1] -move_into(//div[@class="node"])://div[@class="breadcrumb"] -test_url: http://community.service-now.com/blog/lawrenceeng/seasons-greetings-servicenow-team \ No newline at end of file diff --git a/community.servicenow.com.txt b/community.servicenow.com.txt new file mode 100755 index 0000000..98fb688 --- /dev/null +++ b/community.servicenow.com.txt @@ -0,0 +1,8 @@ +body: //div[@id="center"]//div[@class="node"] +title: //div[@id="center"]//h2 +author: substring-after(//div[@id="center"]//div[@class="node"]//span[@class="submitted"], "—") +date: substring-before(//div[@id="center"]//div[@class="node"]//span[@class="submitted"], "—") +strip: //div[@id="center"]//h2[1] +strip: //span[@class="submitted"][1] +move_into(//div[@class="node"])://div[@class="breadcrumb"] +test_url: http://community.servicenow.com/blog/lawrenceeng/seasons-greetings-servicenow-team diff --git a/guardian.co.uk.txt b/guardian.co.uk.txt deleted file mode 100644 index 299d71c..0000000 --- a/guardian.co.uk.txt +++ /dev/null @@ -1,7 +0,0 @@ -title: //div[@id='main-article-info']//h1 -body: //div[@id='article-wrapper'] -date: //li[@class='publication']//time[@pubdate] | //li[@class='publication']//data[@pubdate] -author: //li[@class='byline'] -prune: no -tidy: no -test_url: http://www.guardian.co.uk/business/2011/oct/06/quantitative-easing-75bn-bank-of-england \ No newline at end of file diff --git a/hipertextual.com.txt b/hipertextual.com.txt new file mode 100755 index 0000000..2cb7ca5 --- /dev/null +++ b/hipertextual.com.txt @@ -0,0 +1,2 @@ +body: //*[(@class = "historia")] +test_url: http://hipertextual.com/2011/09/banda-ancha-en-america-latina-insignificante diff --git a/iceblog.free.fr.txt b/iceblog.free.fr.txt deleted file mode 100644 index 9d1ce21..0000000 --- a/iceblog.free.fr.txt +++ /dev/null @@ -1,7 +0,0 @@ - -# Generated by FiveFilters.org's web-based selection tool -# Place this file inside your site_config/custom/ folder -# Source: http://siteconfig.fivefilters.org/grab.php?url=http%3A%2F%2Ficeblog.free.fr%2Findex.php%3Farticle102%2Fweb-histoire-geek-4 - -body: //article//section -test_url: http://iceblog.free.fr/index.php?article102/web-histoire-geek-4 diff --git a/m.guardian.co.uk.txt b/m.guardian.co.uk.txt deleted file mode 100644 index cce0271..0000000 --- a/m.guardian.co.uk.txt +++ /dev/null @@ -1,12 +0,0 @@ -title: //p[@class="txhead"] -author: //div[@class='txb'] -wrap_in(p): //div[@class='para'] -date: //div[@class='txb']/following-sibling::p/text()[substring(., 14)] -strip: //table[@class="tlogo"] -strip: //div[@class="cookieText"] -strip: //*[@class="sltb"] -strip: //*[@class="ijobs-x-link"] -strip: //*[@class="sponscolour"] -strip: //*[@class="sponsouter"] -strip: //div[@id="bottom-nav-block"]/following::* -test_url: http://m.guardian.co.uk/ms/p/gnm/op/s3OOwgO3yIhGuj41C1_S3Xg/view.m?id=15&gid=world/2012/jul/26/arctic-climate-change&cat=top-stories \ No newline at end of file diff --git a/macformat.techradar.com.txt b/macformat.techradar.com.txt deleted file mode 100755 index 522efb4..0000000 --- a/macformat.techradar.com.txt +++ /dev/null @@ -1,9 +0,0 @@ -# Remove news feed -strip: //div[@id='news_feed_front'] - -# Remove pull quote -strip: //div[@class='field field-type-text field-field-pull-quote'] - -# Remove login -strip: //div[@class='right_bar_login'] -test_url: http://macformat.techradar.com/blog/solid-state-storage-bringing-parity-back-mac-29-10-10&article=89189666 \ No newline at end of file diff --git a/mobile.slate.com.txt b/mobile.slate.com.txt deleted file mode 100755 index 6ffcd18..0000000 --- a/mobile.slate.com.txt +++ /dev/null @@ -1,5 +0,0 @@ -title: //h2[@class="article_title"] -strip: //a[@class="houseAdLink"] -strip: //h1 -strip: //div[@class="more_articles"] -test_url: http://mobile.slate.com/rss.jsp?rssid=411&item=http%3a%2f%2fwww.slate.com%2fdefault.aspx%3fdisplaymode%3d201%26id%3d2293749%26device%3drss \ No newline at end of file diff --git a/neomoney.co.txt b/neomoney.co.txt deleted file mode 100755 index 2089fc3..0000000 --- a/neomoney.co.txt +++ /dev/null @@ -1,3 +0,0 @@ -title: //*[@class="header_title"]/h1 -body: //div[contains(@class, 'content')] -test_url: http://neomoney.co/personal/expatriate-and-migrant-loans/expatriate-loans/ \ No newline at end of file diff --git a/online.wsj.com.txt b/online.wsj.com.txt deleted file mode 100755 index 448bb7e..0000000 --- a/online.wsj.com.txt +++ /dev/null @@ -1,25 +0,0 @@ -title: //meta[@property="og:title"]/@content -body: //div[@id='article_story_body'] - -author: //h3[@class='byline']/a -# for slide show content -body: //ul[@id='imageSlide']//li[@class='firstSlide']//img | (//div[@class='txt_body']//p)[1] -date: //li[@class='dateStamp']/small - -strip_id_or_class: insetFullBracket -strip_id_or_class: insettipBox -#strip_id_or_class: legacyInset -strip_id_or_class: recipeACShopAndBuyText - -strip: //div[contains(@class, 'insetContent')]//cite -strip: //*[contains(@style, 'visibility: hidden;')] -strip: //div[contains(@class, 'insetContent') and not(contains(@class, 'image'))] -strip: //div[contains(@class, 'carousel')] - -prune: no -tidy: no - -test_url: http://online.wsj.com/news/articles/SB10001424052702304626304579509100018004342 -test_url: http://online.wsj.com/article/SB10001424052970203363504577185322849515102.html -# slide show -test_url: http://online.wsj.com/article/SB10001424052970204791104577110550376458164.html diff --git a/physicstoday.org.txt b/physicstoday.org.txt deleted file mode 100755 index 624055b..0000000 --- a/physicstoday.org.txt +++ /dev/null @@ -1,7 +0,0 @@ -title: //div[@class='abstitle']//h1 -author: //div[@class='authorList'] -body: //div[@id='fulltext_body'] - -prune: no - -test_url: http://www.physicstoday.org/resource/1/phtoad/v64/i10/p48_s1?bypassSSO=1 \ No newline at end of file diff --git a/red-hot-girls.com.txt b/red-hot-girls.com.txt deleted file mode 100755 index 0403ee8..0000000 --- a/red-hot-girls.com.txt +++ /dev/null @@ -1,5 +0,0 @@ -body: //div[@class='short-text' or starts-with(@id, 'news-id-')] -prune: no -tidy: no - -test_url: http://red-hot-girls.com/2011/06/10/the_red_hot_natalia_maria_53_pics.html \ No newline at end of file diff --git a/redtape.msnbc.msn.com.txt b/redtape.msnbc.msn.com.txt deleted file mode 100755 index 8541a0d..0000000 --- a/redtape.msnbc.msn.com.txt +++ /dev/null @@ -1,20 +0,0 @@ -# Think there might be something up with your parser that it strips out 'print' from the title :) - -title: //meta[@name='title']/@content -author: //meta[@name='author']/@content -date: //meta[@name='date']/@content - -body: //div[@class='articleText'] - -strip: //div[contains(@class, 'day')] -strip: //div[contains(@class, 'month')] -strip: //div[contains(@class, 'year')] -strip: //div[contains(@class, 'time')] -strip: //h1[@class='gl_headline'] -strip: //div[@class='byline'] -strip: //div[@id='left_ear'] -strip: //div[@id='right_ear'] -strip: //div[contains(@class, 'PopularPosts')] -strip ://div[@class='discuss_page_break'] -strip ://div[contains(@class, 'p-content_TagList')] -test_url: http://redtape.msnbc.msn.com/_news/2011/09/28/8020661-sprint-raises-fee-but-wont-free-users-from-two-year-contracts?preview=true \ No newline at end of file diff --git a/retrieverweekly.com.txt b/retrieverweekly.com.txt deleted file mode 100755 index a0a2394..0000000 --- a/retrieverweekly.com.txt +++ /dev/null @@ -1,6 +0,0 @@ -single_page_link://a[contains(@href, 'print')] - -# Grab metadata from the "printer-friendly" page, after specifying single_page_link -title://h2 -date://cite -test_url: http://www.retrieverweekly.com/?cmd=displaystory&story_id=7548&format=html \ No newline at end of file diff --git a/ritemail.blogspot.com.txt b/ritemail.blogspot.com.txt deleted file mode 100755 index ed72915..0000000 --- a/ritemail.blogspot.com.txt +++ /dev/null @@ -1,5 +0,0 @@ -body: //div[@class='post-body entry-content'] -strip: //div[@id='lws_0'] -prune: no - -test_url: http://ritemail.blogspot.com/2011/06/hayden-panettiere-candids-in-los.html \ No newline at end of file diff --git a/ruttloff.org.txt b/ruttloff.org.txt deleted file mode 100755 index 43e130a..0000000 --- a/ruttloff.org.txt +++ /dev/null @@ -1,3 +0,0 @@ -author: //a[@class='author'] -tidy: no -test_url: http://ruttloff.org/2012/06/13/intervention \ No newline at end of file diff --git a/simonwillison.net.txt b/simonwillison.net.txt deleted file mode 100755 index 6999969..0000000 --- a/simonwillison.net.txt +++ /dev/null @@ -1,5 +0,0 @@ -body: //div[contains(@class, "entry")] - -date: //div[contains(@class, "entryFooter")]/a - -test_url: http://simonwillison.net/2009/Oct/22/redis/ \ No newline at end of file diff --git a/stockholmsfria.nu.txt b/stockholmsfria.nu.txt deleted file mode 100755 index cc8c28b..0000000 --- a/stockholmsfria.nu.txt +++ /dev/null @@ -1,7 +0,0 @@ -body: //div[contains(@class, 'layout__inner')]//div[contains(@class, 'file-image') or contains(@class, 'node__content')] -author: //article//div[contains(@class, 'field-byline')] -strip_id_or_class: rekommenderade -strip_id_or_class: disqus -strip_id_or_class: annonser - -test_url: http://www.stockholmsfria.nu/artikel/112068 \ No newline at end of file diff --git a/stockholmsfria.se.txt b/stockholmsfria.se.txt new file mode 100755 index 0000000..ee87483 --- /dev/null +++ b/stockholmsfria.se.txt @@ -0,0 +1,7 @@ +body: //div[contains(@class, 'layout__inner')]//div[contains(@class, 'file-image') or contains(@class, 'node__content')] +author: //article//div[contains(@class, 'field-byline')] +strip_id_or_class: rekommenderade +strip_id_or_class: disqus +strip_id_or_class: annonser + +test_url: http://www.stockholmsfria.se/artikel/112068 diff --git a/thisismynext.com.txt b/thisismynext.com.txt deleted file mode 100755 index 70b5399..0000000 --- a/thisismynext.com.txt +++ /dev/null @@ -1,8 +0,0 @@ -author: //div[@class='meta clearfix']/a -body: //div[@class='post'] - -strip: //div[@class='metaCat'] -strip: //div[@class='post']/h1 -strip: //div[@class='post']/div[@class='meta clearfix'] -strip: //div[@class='post']/div[@class='social-bar clearfix'] -test_url: http://thisismynext.com/2011/10/18/galaxy-nexus-android-ice-cream-sandwich-pictures-video-hands-on/ \ No newline at end of file diff --git a/walrusmagazine.com.txt b/walrusmagazine.com.txt deleted file mode 100755 index c53eb0d..0000000 --- a/walrusmagazine.com.txt +++ /dev/null @@ -1,14 +0,0 @@ -title: //div[@id='pr']/h3 -author: //div[@class='dateline']//a[contains(@href, '/author/')] - -# print page -body: //div[@id='prbody'] -# standard page -body: //div[@id='pgbody'] - -# for multi-page articles -single_page_link: //div[@class='tipjar']//a[contains(@href, '/printerFriendly.php?')] - -prune: no - -test_url: http://www.walrusmagazine.com/articles/2011.12-memoir-kidnapped \ No newline at end of file diff --git a/weblog.bignerdranch.com.txt b/weblog.bignerdranch.com.txt deleted file mode 100755 index 578ba52..0000000 --- a/weblog.bignerdranch.com.txt +++ /dev/null @@ -1,5 +0,0 @@ -title://div[@class="post"]/h2 -author://p[@class="postinfo"]/a -date:substring-before(substring-after(//p[@class="postinfo"],' on '),' under ') -body://div[@class="contenttext"] -test_url: http://weblog.bignerdranch.com/?p=304 \ No newline at end of file diff --git a/wyctim.com.txt b/wyctim.com.txt deleted file mode 100755 index bd7ecf2..0000000 --- a/wyctim.com.txt +++ /dev/null @@ -1,3 +0,0 @@ -body: //div[@class='article-body'] -title: //h1 -test_url: http://wyctim.com/icloud-sync-regebbi-rendszereken/ \ No newline at end of file diff --git a/zcommunications.org.txt b/zcommunications.org.txt deleted file mode 100755 index 4deb49b..0000000 --- a/zcommunications.org.txt +++ /dev/null @@ -1,7 +0,0 @@ -title: //h1[@id='view_title'] -author: //div[contains(@class, 'content_authors')]//a -body: //div[@id='view_body'] - -prune: no - -test_url: http://www.zcommunications.org/orwellian-language-update-by-edward-s-herman.html \ No newline at end of file -- cgit v1.3.1