updated specific configuration for parsing

This commit is contained in:
Nicolas Lœuillet 2014-07-13 10:15:40 +02:00
parent 58dbe10388
commit 4e067ceabd
952 changed files with 7585 additions and 5682 deletions

8
inc/3rdparty/site_config/standard/24ways.org.txt vendored Normal file → Executable file
View File

@ -1,6 +1,6 @@
title: //div[@class='meta']/h2/a
author: //div[@class='meta']/h2/following-sibling::p/a/text()
date://div[@class='meta']/h2/strong
body: //div[@id='article']
title: //div[@class='meta']/h2/a
author: //div[@class='meta']/h2/following-sibling::p/a/text()
date://div[@class='meta']/h2/strong
body: //div[@id='article']
strip: //div[@class='domore']
test_url: http://24ways.org/2011/composing-the-new-canon

View File

@ -0,0 +1,8 @@
title: //h1[contains(@class, 'entry-title')]
date: //meta[@name='weibo: article:create_at']/@content
body: //div[contains(@class, 'mainContent')]
strip_id_or_class: related_topics
prune: no
test_url: http://www.36kr.com/p/207879.html

8
inc/3rdparty/site_config/standard/37signals.com.txt vendored Normal file → Executable file
View File

@ -1,6 +1,6 @@
title: //div[@class='post_header']//h2/a
author: //span[@class='author']
date: //span[@class='date']
body: //div[@id='Content']
title: //div[@class='post_header']//h2/a
author: //span[@class='author']
date: //span[@class='date']
body: //div[@id='Content']
test_url: http://37signals.com/svn/posts/2785-the-end-of-the-it-department

16
inc/3rdparty/site_config/standard/3quarksdaily.com.txt vendored Normal file → Executable file
View File

@ -1,9 +1,9 @@
body: //div[@class='content']
date: //div[@class='content']/h2
strip: //div[@class='content']/h2
title: //div[@class='content']/h3
strip: //div[@id='postmenu']
strip: //div[@class='trackback']
tidy: no
body: //div[@class='content']
date: //div[@class='content']/h2
strip: //div[@class='content']/h2
title: //div[@class='content']/h3
strip: //div[@id='postmenu']
strip: //div[@class='trackback']
tidy: no
test_url: http://www.3quarksdaily.com/3quarksdaily/2012/01/martin-luther-king-i-have-a-dream.html

0
inc/3rdparty/site_config/standard/3voor12.vpro.nl.txt vendored Normal file → Executable file
View File

4
inc/3rdparty/site_config/standard/43folders.com.txt vendored Normal file → Executable file
View File

@ -1,4 +1,4 @@
body: //*[@class = 'content']
author: //*[@class = 'submitted']/a
body: //*[@class = 'content']
author: //*[@class = 'submitted']/a
date: substring-after(//*[@class = 'submitted']/text(), '|')
test_url: http://www.43folders.com/2011/04/22/cranking

50
inc/3rdparty/site_config/standard/500px.com.txt vendored Normal file → Executable file
View File

@ -1,27 +1,27 @@
# very loose setup for both 500px.com/photo/* and 500px.com/blog/*
# photo page example: http://500px.com/photo/4181666
# blog page example: http://500px.com/blog/110
# avoid "no text" error
tidy:no
prune:no
# reorganize photo page elements
#body://div[contains(@class,'container')]
move_into(body)://div[contains(@id,'thephoto')]
move_into(body)://div[contains(@id,'description')]
move_into(body)://div[contains(@id,'tags')]
move_into(body)://div[contains(@id,'photo-info')]
# clean photo page info
strip://span[contains(@id,'copyright')]
strip://*[contains(@id,'store')]
strip://*[contains(@id,'user-info')]
strip://*[contains(@id,'photo-stats')]
strip://*[contains(@id,'voting_controls_container')]
strip://*[contains(@id,'more-photos')]
strip://*[contains(@id,'embed-photo')]
# clean blog page side bar
# very loose setup for both 500px.com/photo/* and 500px.com/blog/*
# photo page example: http://500px.com/photo/4181666
# blog page example: http://500px.com/blog/110
# avoid "no text" error
tidy:no
prune:no
# reorganize photo page elements
#body://div[contains(@class,'container')]
move_into(body)://div[contains(@id,'thephoto')]
move_into(body)://div[contains(@id,'description')]
move_into(body)://div[contains(@id,'tags')]
move_into(body)://div[contains(@id,'photo-info')]
# clean photo page info
strip://span[contains(@id,'copyright')]
strip://*[contains(@id,'store')]
strip://*[contains(@id,'user-info')]
strip://*[contains(@id,'photo-stats')]
strip://*[contains(@id,'voting_controls_container')]
strip://*[contains(@id,'more-photos')]
strip://*[contains(@id,'embed-photo')]
# clean blog page side bar
strip://*[contains(@class,'col d3 clearafter')]
test_url: http://500px.com/photo/3641041?from=editors

0
inc/3rdparty/site_config/standard/512pixels.net.txt vendored Normal file → Executable file
View File

14
inc/3rdparty/site_config/standard/5by5.tv.txt vendored Normal file → Executable file
View File

@ -1,9 +1,9 @@
body: //*[@id="episode"]
prune: no
tidy: no
autodetect_next_page: no
strip_id_or_class: player
body: //*[@id="episode"]
prune: no
tidy: no
autodetect_next_page: no
strip_id_or_class: player
strip://*[@id="header"]
test_url: http://5by5.tv/buildanalyze/60

View File

@ -0,0 +1,7 @@
title: //*[@id='sstitle']
body: //div[@id='sstory']
strip_id_or_class: newsoptions
prune: no
test_url: http://www.7newsbelize.com/sstory.php?nid=25654
test_url: http://www.7newsbelize.com/7news.xml

14
inc/3rdparty/site_config/standard/944.com.txt vendored Normal file → Executable file
View File

@ -1,9 +1,9 @@
title: //h2[@class='border']
body: //div[@class='padding']
convert_double_br_tags: yes
strip: //div[@id='social_sharing']
strip: //div[@class='socialLinks']
title: //h2[@class='border']
body: //div[@class='padding']
convert_double_br_tags: yes
strip: //div[@id='social_sharing']
strip: //div[@class='socialLinks']
test_url: http://www.944.com/articles/mild-obsessions-frock-la-get-to-know-victoria-tik-s-haute-sustainable-fashion-line/

38
inc/3rdparty/site_config/standard/README.md vendored Executable file
View File

@ -0,0 +1,38 @@
Full-Text RSS site config files
================
[Full-Text RSS](http://fivefilters.org/content-only/), our article extraction tool, makes use of site-specific extraction rules to improve results. Each time a URL is processed, it checks to see if there are extraction rules for the site being processed. If there are no site patterns, it tries to detect the content block automatically.
This repository contains the site config files we use in Full-Text RSS.
### Contributing changes
We chose GitHub for this set of files because they offer one feature which we hope will make contributing changes easier: [file editing](https://github.com/blog/844-forking-with-the-edit-button) through the web interface.
You can now make changes to any of our site config files and request that your changes be pulled into the main set we maintain. This is what GitHub calls the Fork and Pull model:
> The Fork & Pull Model lets anyone fork an existing repository and push changes to their personal fork without requiring access be granted to the source repository. The changes must then be pulled into the source repository by the project maintainer. This model reduces the amount of friction for new contributors and is popular with open source projects because it allows people to work independently without upfront coordination.
When we receive a pull request we'll review the changes and if everything's okay we'll update our copy.
If a site is not in our set, you can create a file for it in the same way. See [Creating files on GitHub](https://github.com/blog/1327-creating-files-on-github).
### How to write a site config file
The quickest and simplest way is to use our [point-and-click interface](http://siteconfig.fivefilters.org). It's a simple tool only intended to create a rule to extract the correct content block.
For further refinements, e.g. selecting the title, stripping elements, dealing with multi-page articles, please see our [help page](http://help.fivefilters.org/customer/portal/articles/223153-site-patterns).
### Instapaper
When we introduced site patterns, we chose to adopt the [same format](http://blog.instapaper.com/post/730281947) used by Instapaper. This allows us to make use of the existing extraction rules contributed by Instapaper users.
Marco, Instapaper's creator, graciously opened up the database of contributions to everyone:
> And, recognizing that your efforts could be useful to a wide range of other tools and services, I'll make the list of all of these site-specific configurations available to the public, free, with no strings attached.
Most of the extraction rules in our set are borrowed from Instapaper. You can see the list maintained by Instapaper at [instapaper.com/bodytext/](http://instapaper.com/bodytext/) (login required).
### Testing site config files
Currently you will have to have a copy of Full-Text RSS to test changes to the site config files. In the future we will try to make this process easier.

18
inc/3rdparty/site_config/standard/aachener-nachrichten.de.txt vendored Normal file → Executable file
View File

@ -1,10 +1,10 @@
title: //meta[@property='og:title']/@content
body: //*[@class='fliesstext_detail' or @class='detail_fliesstext'] | //img[@itemprop="image" and starts-with(@src, "/sixcms/media.php/")]
strip_id_or_class: socialshareprivacy1
strip_id_or_class: zvaFacebookButton
tidy: no
prune: no
title: //meta[@property='og:title']/@content
body: //*[@class='fliesstext_detail' or @class='detail_fliesstext'] | //img[@itemprop="image" and starts-with(@src, "/sixcms/media.php/")]
strip_id_or_class: socialshareprivacy1
strip_id_or_class: zvaFacebookButton
tidy: no
prune: no
test_url: http://www.aachener-nachrichten.de/lokales/aachen-detail-an/2517757

18
inc/3rdparty/site_config/standard/aachener-zeitung.de.txt vendored Normal file → Executable file
View File

@ -1,10 +1,10 @@
title: //meta[@property='og:title']/@content
body: //*[@class='fliesstext_detail' or @class='detail_fliesstext'] | //img[@itemprop="image" and starts-with(@src, "/sixcms/media.php/")]
strip_id_or_class: socialshareprivacy1
strip_id_or_class: zvaFacebookButton
tidy: no
prune: no
title: //meta[@property='og:title']/@content
body: //*[@class='fliesstext_detail' or @class='detail_fliesstext'] | //img[@itemprop="image" and starts-with(@src, "/sixcms/media.php/")]
strip_id_or_class: socialshareprivacy1
strip_id_or_class: zvaFacebookButton
tidy: no
prune: no
test_url: http://www.aachener-zeitung.de/sixcms/detail.php?template=az_detail&id=2552718

10
inc/3rdparty/site_config/standard/abc.es.txt vendored Normal file → Executable file
View File

@ -1,7 +1,7 @@
title: //meta[@property='og:title']/@content
body: //div[@class='datosi' or @class='date' or @class='photo-alt1' or @class='text']
strip_id_or_class: colB
prune: no
title: //meta[@property='og:title']/@content
body: //div[@class='datosi' or @class='date' or @class='photo-alt1' or @class='text' or @itemprop='articleBody']
strip_id_or_class: colB
prune: no
test_url: http://www.abc.es/20120209/tv-series/abci-house-ultima-temporada-201202090936.html

26
inc/3rdparty/site_config/standard/abc.net.au.txt vendored Normal file → Executable file
View File

@ -1,10 +1,18 @@
title: //h1
author: //div[@class="byline"]/a
date: //span[@class="timestamp"]
strip: //p[@class="topics"]
strip: //h1
strip: //div[@class="byline"]
strip: //p[@class="published"]
title: //div[@class='article section']//h1
author: //div[@class="byline"]/a
date: //span[@class="timestamp"]
body: //div[@class="page section"]
strip: //a[@class="inline-caption"]
strip: //p[@class="ticker section noprint"]
strip: //p[@class="topics"]
strip: //h1
strip: //div[@class="byline"]
strip: //p[@class="published"]
strip: //div[contains(@class,"featured-scroller")]
test_url: http://www.abc.net.au/news/2011-11-08/crabb-carbon-legislation-abbott-demolition/3652544
strip_id_or_class: footer
tidy: no
test_url: http://www.abc.net.au/news/2013-03-27/open-speed-highways-change-clp-giles/4597892
test_url: http://www.abc.net.au/news/2013-04-30/credit-growth-remains-subdued/4660054?section=business

52
inc/3rdparty/site_config/standard/abcnews.go.com.txt vendored Normal file → Executable file
View File

@ -1,27 +1,27 @@
title: //h1[@class='headline']
body: //div[@id='storyText']
# for video entries
body: //img[@id='ff-img'] | //div[@id='meta']//div[contains(@class, 'overview')]
author: //div[@class='byline']
date: //div[@class='date']
strip: //*[@id='date_partner']
strip: //div[@class='breadcrumb']
strip: //div[contains(@class,'show_tools')]
strip: //div[@id='sponsoredByAd']
strip: //div[contains(@class,'rel_container')]
strip: //p[a[starts-with(@href, 'http://www.twitter.com')]]
strip: //p[a[starts-with(@href, 'http://www.facebook.com')]]
strip: //p[contains(., 'Click here to return to')]
#strip_id_or_class: media
strip_id_or_class: mediaplayer
replace_string(<link rel="image_src" href="http): <img id="ff-img" src="http
prune: no
single_page_link: concat(//li[@class='pager']//a/@href, '&singlePage=true')
test_url: http://abcnews.go.com/Politics/newt-gingrich-rocky-rollout-presidential-campaign-recover/story?id=13632744
# multi-page
title: //h1[@class='headline']
body: //div[@id='storyText']
# for video entries
body: //img[@id='ff-img'] | //div[@id='meta']//div[contains(@class, 'overview')]
author: //div[@class='byline']
date: //div[@class='date']
strip: //*[@id='date_partner']
strip: //div[@class='breadcrumb']
strip: //div[contains(@class,'show_tools')]
strip: //div[@id='sponsoredByAd']
strip: //div[contains(@class,'rel_container')]
strip: //p[a[starts-with(@href, 'http://www.twitter.com')]]
strip: //p[a[starts-with(@href, 'http://www.facebook.com')]]
strip: //p[contains(., 'Click here to return to')]
#strip_id_or_class: media
strip_id_or_class: mediaplayer
replace_string(<link rel="image_src" href="http): <img id="ff-img" src="http
prune: no
single_page_link: concat(//li[@class='pager']//a/@href, '&singlePage=true')
test_url: http://abcnews.go.com/Politics/newt-gingrich-rocky-rollout-presidential-campaign-recover/story?id=13632744
# multi-page
test_url: http://abcnews.go.com/Blotter/family-freed-american-hostage-somalia-seals-obama/story?id=15439544

16
inc/3rdparty/site_config/standard/accesstoinsight.org.txt vendored Normal file → Executable file
View File

@ -1,9 +1,9 @@
title: //div[@id='H_docTitle']
body: //div[@id='H_meta' or @id='H_content' or @id='F_footer']
strip_id_or_class: F_toenail
prune: no
title: //div[@id='H_docTitle']
body: //div[@id='H_meta' or @id='H_content' or @id='F_footer']
strip_id_or_class: F_toenail
prune: no
test_url: http://www.accesstoinsight.org/lib/authors/nyanaponika/wheel026.html

4
inc/3rdparty/site_config/standard/acidcow.com.txt vendored Normal file → Executable file
View File

@ -1,3 +1,3 @@
body: //div[starts-with(@id, 'news-id-')]
body: //div[starts-with(@id, 'news-id-')]
test_url: http://acidcow.com/fun/20933-acid-picdump-83-pics.html

14
inc/3rdparty/site_config/standard/acquia.com.txt vendored Normal file → Executable file
View File

@ -1,9 +1,9 @@
title://h1[@class="title"]
author://div[@class="submitted"]/span/a
date://div[@class="submitted"]/span
body://div[@class="content-wrapper"]
strip://div[@id="skip-link"]
strip://div[@id="region-content-3-3"]
title://h1[@class="title"]
author://div[@class="submitted"]/span/a
date://div[@class="submitted"]/span
body://div[@class="content-wrapper"]
strip://div[@id="skip-link"]
strip://div[@id="region-content-3-3"]
strip://div[@id="section-footer"]
test_url: https://www.acquia.com/blog/drupals-long-warmth-toward-third-party-code

6
inc/3rdparty/site_config/standard/acroswing.fr.txt vendored Normal file → Executable file
View File

@ -1,5 +1,5 @@
tidy:no
date: //time[@class='updated']
dissolve: //ul[@class='video-gallery']/li
tidy:no
date: //time[@class='updated']
dissolve: //ul[@class='video-gallery']/li
dissolve: //ul[@class='video-gallery']
test_url: http://www.acroswing.fr/actualites/competition_rock/selectif_bellegarde_sur_valserine__2012-02-26.php

View File

@ -0,0 +1,5 @@
title: //h1[@class='articleTitle ']
body: //div[@class='bodyText widget storyContent']
strip: //p/span[@class='quote']/..
strip_id_or_class: 'pull1'
test_url: https://www.aftenposten.no/meninger/spaltister/Portrett-av-scenekunstneren-som-ung-mann-7167959.html

View File

@ -0,0 +1,13 @@
author: //article//address[contains(@class, 'author')]
body: //article[.//div[contains(@class, 'abBodyText')]]//*[contains(@class, 'abLeadText') or contains(@class, 'abBodyText') or contains(@class, 'abImageBlock') or contains(@class, 'abIGSatellite')]
strip: //address//img
strip: //footer
strip_id_or_class: abSticky
prune: no
test_url: http://www.aftonbladet.se/sportbladet/hockey/sverige/allsvenskan/article17498194.ab
test_url: http://www.aftonbladet.se/debatt/article16207536.ab
test_url: http://www.aftonbladet.se/debatt/debattamnen/politik/article17483377.ab
test_url: http://www.aftonbladet.se/rss.xml

26
inc/3rdparty/site_config/standard/aht.seriouseats.com.txt vendored Normal file → Executable file
View File

@ -1,15 +1,15 @@
body: //div[@id='content']
# clean up recipe pages
strip: //h2[@class='fn'] | //h2[@class='double-lined'] | //h3 | //div[@id='threeColumn2'] | //div[@id='threeColumn3']
#recipe pages
strip_id_or_class: "recipe-feedback"
strip_id_or_class: "comments"
strip_id_or_class: "procedure-number"
strip_id_or_class: "more-with-author"
#slice
strip_id_or_class: "inner"
body: //div[@id='content']
# clean up recipe pages
strip: //h2[@class='fn'] | //h2[@class='double-lined'] | //h3 | //div[@id='threeColumn2'] | //div[@id='threeColumn3']
#recipe pages
strip_id_or_class: "recipe-feedback"
strip_id_or_class: "comments"
strip_id_or_class: "procedure-number"
strip_id_or_class: "more-with-author"
#slice
strip_id_or_class: "inner"
test_url: http://aht.seriouseats.com/archives/2009/12/the-burger-lab-salting-ground-beef.html

View File

@ -0,0 +1,6 @@
body: //div[@id='main-column']//div[@class='content']
prune: no
test_url: http://www.albayan.ae/across-the-uae/education/2013-08-29-1.1949645
test_url: http://www.albayan.ae/1.448?ot=ot.AjaxPageLayout

0
inc/3rdparty/site_config/standard/alex.mullr.net.txt vendored Normal file → Executable file
View File

View File

@ -0,0 +1,4 @@
body: //section[@class='content']
date: //span[1]
author: //h1[@id='sitetitle']
test_url: https://alexduner.com/blog/2013/1/something-i-learned-today

View File

@ -0,0 +1,4 @@
body: //section[@class='content']
date: //span[1]
author: //h1[@id='sitetitle']
test_url: https://alexduner.squarespace.com/blog/2013/1/tech-culture-from-the-outside-looking-in

20
inc/3rdparty/site_config/standard/alistapart.com.txt vendored Normal file → Executable file
View File

@ -1,12 +1,12 @@
title: //h1[@class='title']
author: //h3[@class='byline']/a
date: //div[@class='ishinfo']
body: //*[@id='articletext']
strip_id_or_class: 'ishinfo'
strip_id_or_class: 'metastuff'
strip_id_or_class: 'learnmore'
strip_id_or_class: 'discuss'
title: //h1[@class='title']
author: //h3[@class='byline']/a
date: //div[@class='ishinfo']
body: //*[@id='articletext']
strip_id_or_class: 'ishinfo'
strip_id_or_class: 'metastuff'
strip_id_or_class: 'learnmore'
strip_id_or_class: 'discuss'
prune: no
test_url: http://www.alistapart.com/articles/organizing-mobile/

14
inc/3rdparty/site_config/standard/aljazeera.com.txt vendored Normal file → Executable file
View File

@ -1,8 +1,8 @@
title: //span[@id='DetailedTitle']
body: //td[@id='tdTextContent']
strip_id_or_class: Skyscrapper_Body
date: //span[@id='ctl00_cphBody_lblDate']
author: //div[@id="dvAuthorInfo"]//a/text()
strip: //table[ tbody/tr/td/object ]
prune: no
title: //span[@id='DetailedTitle']
body: //td[@id='tdTextContent']
strip_id_or_class: Skyscrapper_Body
date: //span[@id='ctl00_cphBody_lblDate']
author: //div[@id="dvAuthorInfo"]//a/text()
strip: //table[ tbody/tr/td/object ]
prune: no
test_url: http://www.aljazeera.com/indepth/opinion/2012/01/2012114121925380575.html

24
inc/3rdparty/site_config/standard/allrecipes.com.txt vendored Normal file → Executable file
View File

@ -1,14 +1,14 @@
title: //h1[@id='itemTitle']
body: //img[@id="ctl00_CenterColumnPlaceHolder_recipe_photoStuff_imgPhoto"] | //div[@id='ctl00_CenterColumnPlaceHolder_recipe_divSubmitter'] | //div[contains(@class, 'recipe-details-content')]
strip: //div[@class='top-left' or @class='top-right' or @class='bot-left' or @class='bot-right']
strip: //div[contains(@class, 'rightcoltoolsdiv')]
strip: //div[contains(@class, 'servings-form')]
strip: //p[@class='nutritional-information']
strip: //a[contains(@class, 'nutritional-information') or contains(@class, 'nutritionanchor')]
strip: //div[@id='nutri-info']/div[contains(@class, 'title')]
strip: //img[@id='ctl00_CenterColumnPlaceHolder_recipe_imgSubmitter']
strip_id_or_class: eshaAttribute
strip_id_or_class: eshaParagraph
prune: no
title: //h1[@id='itemTitle']
body: //img[@id="ctl00_CenterColumnPlaceHolder_recipe_photoStuff_imgPhoto"] | //div[@id='ctl00_CenterColumnPlaceHolder_recipe_divSubmitter'] | //div[contains(@class, 'recipe-details-content')]
strip: //div[@class='top-left' or @class='top-right' or @class='bot-left' or @class='bot-right']
strip: //div[contains(@class, 'rightcoltoolsdiv')]
strip: //div[contains(@class, 'servings-form')]
strip: //p[@class='nutritional-information']
strip: //a[contains(@class, 'nutritional-information') or contains(@class, 'nutritionanchor')]
strip: //div[@id='nutri-info']/div[contains(@class, 'title')]
strip: //img[@id='ctl00_CenterColumnPlaceHolder_recipe_imgSubmitter']
strip_id_or_class: eshaAttribute
strip_id_or_class: eshaParagraph
prune: no
test_url: http://allrecipes.com/Recipe/Taco-Pie/Detail.aspx?src=rotd

21
inc/3rdparty/site_config/standard/allthingsd.com.txt vendored Normal file → Executable file
View File

@ -1,10 +1,13 @@
title://div[@class="article-title"]/h1[@class="title"]
date: //p[@class="article-date"]
body://*[@class="article-body article-text"]
# Trim out related posts at bottom of article
strip://blockquote[@class="memo"]
# Yup, no idea why author won't work...
author://div[@class="page-header article-header clearfix"]/p[@class="title"]
title://div[@class="article-title"]/h1[@class="title"]
date: //p[@class="article-date"]
body://div[contains(@class, "article-body")]
# Trim out related posts at bottom of article
strip://blockquote[@class="memo"]
tidy: no
# Yup, no idea why author won't work...
author://div[@class="page-header article-header clearfix"]/p[@class="title"]
# [Marco:] Author won't work here because the page defines the "home" link under the author's name as rel="author", which always gets priority if the page has defined it.
test_url: http://allthingsd.com/20120513/exclusive-yahoos-thompson-out-levinsohn-in-board-settlement-with-loeb-nears-completion/
test_url: http://allthingsd.com/20120513/exclusive-yahoos-thompson-out-levinsohn-in-board-settlement-with-loeb-nears-completion/
test_url: http://allthingsd.com/20131010/google-cio-ben-fried-on-how-google-works/

12
inc/3rdparty/site_config/standard/allyou.com.txt vendored Normal file → Executable file
View File

@ -1,8 +1,8 @@
title: //div[@id='pageHdr']//h1
body: //div[@id='pageHdr']/*[@class='dek'] | //div[@id='printArticle' or @id='slideShowPrint']
strip: //div[contains(@class, 'infoBox') or @id='infoBox']
single_page_link: //li[@id='print']/a
title: //div[@id='pageHdr']//h1
body: //div[@id='pageHdr']/*[@class='dek'] | //div[@id='printArticle' or @id='slideShowPrint']
strip: //div[contains(@class, 'infoBox') or @id='infoBox']
single_page_link: //li[@id='print']/a
prune: no
test_url: http://www.allyou.com/budget-home/money-shopping/freebies-online-00400000066392/

18
inc/3rdparty/site_config/standard/alphabeta.argaam.com.txt vendored Normal file → Executable file
View File

@ -1,11 +1,11 @@
body: //div[@class = 'entry']
date: substring-after(//p[@class="date"],'بتاريخ ')
strip_id_or_class: date
strip_id_or_class: follow-single
strip_id_or_class: ratingblock
strip_id_or_class: newRatingHolder
strip_id_or_class: postmetadata
strip_id_or_class: addthis_toolbox
strip_id_or_class: addthis_default_style
body: //div[@class = 'entry']
date: substring-after(//p[@class="date"],'بتاريخ ')
strip_id_or_class: date
strip_id_or_class: follow-single
strip_id_or_class: ratingblock
strip_id_or_class: newRatingHolder
strip_id_or_class: postmetadata
strip_id_or_class: addthis_toolbox
strip_id_or_class: addthis_default_style
strip_id_or_class: size-full
test_url: http://alphabeta.argaam.com/?p=35657

16
inc/3rdparty/site_config/standard/alriyadh.com.txt vendored Normal file → Executable file
View File

@ -1,9 +1,9 @@
body: //div[@id = "article-view"]
body: //div[contains(@class, 'article')]//div[contains(@class, 'photo_bg')]
author: //p[@class = "author"]
strip: //h1
strip: //h2
strip_id_or_class: author
prune: no
test_url: http://www.alriyadh.com/2011/10/10/article674357.html
body: //div[@id = "article-view"]
body: //div[contains(@class, 'article')]//div[contains(@class, 'photo_bg')]
author: //p[@class = "author"]
strip: //h1
strip: //h2
strip_id_or_class: author
prune: no
test_url: http://www.alriyadh.com/2011/10/10/article674357.html
test_url: http://www.alriyadh.com/net/article/780935

0
inc/3rdparty/site_config/standard/alseraj.net.txt vendored Normal file → Executable file
View File

0
inc/3rdparty/site_config/standard/alt1040.com.txt vendored Normal file → Executable file
View File

View File

@ -0,0 +1,4 @@
single_page_link: //div[contains(@class, 'story_tools')]//a[contains(@href, '/print/')]
test_url: http://www.alternet.org/civil-liberties/noam-chomsky-surveillance-state-beyond-imagination-being-created-one-freest
test_url: http://feeds.feedblitz.com/alternet

0
inc/3rdparty/site_config/standard/altfoto.com.txt vendored Normal file → Executable file
View File

16
inc/3rdparty/site_config/standard/alumni.stanford.edu.txt vendored Normal file → Executable file
View File

@ -1,10 +1,10 @@
title: //h1
author: substring-after(//div[@class="enableBullets"]/preceding-sibling::p[1], "By ")
date: //div/a[contains (@href, "issue")]
move_into(//div[@class="enableBullets"]/p): (//div[@id="content"]//img)[1]
title: //h1
author: substring-after(//div[@class="enableBullets"]/preceding-sibling::p[1], "By ")
date: //div/a[contains (@href, "issue")]
move_into(//div[@class="enableBullets"]/p): (//div[@id="content"]//img)[1]
body: //div[@class="enableBullets"]
test_url: http://alumni.stanford.edu/get/page/magazine/article/?article_id=54819

View File

@ -0,0 +1,6 @@
body: //div[@id='content']//div[contains(@class, 'content')]
strip_id_or_class: widget
strip: //a[contains(@href, 'upm_export=')]
test_url: http://amandala.com.bz/news/feed/
test_url: http://amandala.com.bz/news/poor-pse-results-30-raise/

36
inc/3rdparty/site_config/standard/amazon.com.txt vendored Normal file → Executable file
View File

@ -1,19 +1,19 @@
title: //span[@id = 'btAsinTitle']
body: (//*[@id='prodImageCell']//a)[1] | //div[@id = 'ps-content'] | //span[@id='actualPriceValue'] | //h2[.='Product Details']/following-sibling::div | //div[@class='h2' and .='Product Description']/following-sibling::div
#strip_id_or_class: quantityDropdownDiv
#strip_id_or_class: addToCartSpan
#strip_id_or_class: oneClickDiv
strip_id_or_class: nocontent
strip_id_or_class: masDynamicConten
strip_id_or_class: dynamic-content
prune: no
find_string: <span id="actualPriceValue">
replace_string: <span id="actualPriceValue"><br />Price:
strip_id_or_class: collapsePS
strip_id_or_class: expandPS
strip_id_or_class: psPlaceHolde
strip: //li[contains(., 'update product info') or contains(., 'give feedback on images')]
title: //span[@id = 'btAsinTitle']
body: (//*[@id='prodImageCell']//a)[1] | //div[@id = 'ps-content'] | //span[@id='actualPriceValue'] | //h2[.='Product Details']/following-sibling::div | //div[@class='h2' and .='Product Description']/following-sibling::div
#strip_id_or_class: quantityDropdownDiv
#strip_id_or_class: addToCartSpan
#strip_id_or_class: oneClickDiv
strip_id_or_class: nocontent
strip_id_or_class: masDynamicConten
strip_id_or_class: dynamic-content
prune: no
find_string: <span id="actualPriceValue">
replace_string: <span id="actualPriceValue"><br />Price:
strip_id_or_class: collapsePS
strip_id_or_class: expandPS
strip_id_or_class: psPlaceHolde
strip: //li[contains(., 'update product info') or contains(., 'give feedback on images')]
test_url: http://www.amazon.com/Common-Sense-Forestry-Living-Mother/dp/1931498210/

8
inc/3rdparty/site_config/standard/americandrink.net.txt vendored Normal file → Executable file
View File

@ -1,6 +1,6 @@
title: //div[@class='head']/h2/a
author: //div[@class='head']/a
date: //div[@class='head']/p[@class='date']/a
body: //div[@class='copy']
title: //div[@class='head']/h2/a
author: //div[@class='head']/a
date: //div[@class='head']/p[@class='date']/a
body: //div[@class='copy']
strip: //p[@class='meta']
test_url: http://americandrink.net/post/10567188712/free-the-hooch

18
inc/3rdparty/site_config/standard/americascup.com.txt vendored Normal file → Executable file
View File

@ -1,10 +1,10 @@
title: //div[@class="editorial-content"]/h3
body: //div[@class="hero-image" or @class="editorial-content"]
strip: //ul[@class="hero-caption"]
strip_id_or_class: footer
prune: no
tidy: no
title: //div[@class="editorial-content"]/h3
body: //div[@class="hero-image" or @class="editorial-content"]
strip: //ul[@class="hero-caption"]
strip_id_or_class: footer
prune: no
tidy: no
test_url: http://www.americascup.com/en/Latest/News/2012/3/Coutts-and-Peyron-tell-transformative-tale-at-Global-Sports-Forum/

6
inc/3rdparty/site_config/standard/americastestkitchenfeed.com.txt vendored Normal file → Executable file
View File

@ -1,5 +1,5 @@
title: //h1[@class="post-title"]
author: //span[@class="author"]/a
date: //span[@class="date"]
title: //h1[@class="post-title"]
author: //span[@class="author"]/a
date: //span[@class="date"]
body: //div[@class="post-content main"]
test_url: http://www.americastestkitchenfeed.com/gadgets-and-gear/2012/07/chill-out-with-tovolos-king-cube-silicone-ice-cube-tray/

View File

@ -0,0 +1,8 @@
title: //title
body: //div[@class="entry-content"]
author: //span[@class="author vcard"]
date: //span[@class="entry-date"]
test_url: http://www.amptoons.com/blog/2013/03/14/open-thread-and-link-farm-i-hate-being-sick-edition/

20
inc/3rdparty/site_config/standard/anandtech.com.txt vendored Normal file → Executable file
View File

@ -1,11 +1,11 @@
author: //a[@class='b'][1]
date: substring-after(substring-before(//div, 'Posted in'), ' on ')
strip_image_src: /content/images/globals/
strip: //h2[. = 'Page 1']/preceding::p
strip: //h2
prune: no
single_page_link: concat('http://www.anandtech.com/print/', substring-after(//meta[@property='og:url']/@content, '/show/'))
author: //a[@class='b'][1]
date: substring-after(substring-before(//div, 'Posted in'), ' on ')
strip_image_src: /content/images/globals/
strip: //h2[. = 'Page 1']/preceding::p
strip: //h2
prune: no
single_page_link: concat('http://www.anandtech.com/print/', substring-after(//meta[@property='og:url']/@content, '/show/'))
test_url: http://www.anandtech.com/show/5812/eurocom-monster-10-clevos-little-monster/

View File

@ -0,0 +1,5 @@
body: //div[@class='post_content']
date: //div[@class='date_day'] | div[@class='date_month']
test_url: http://www.androidpolice.com/2014/03/30/music-boss-for-pebble-can-now-control-playback-and-volume-on-chromecast-content-from-your-smartwatch/

16
inc/3rdparty/site_config/standard/andyrutledge.com.txt vendored Normal file → Executable file
View File

@ -1,9 +1,9 @@
title: //h2
author: string('Andy Rutledge')
date: //div[@class='articledate']
body: //div[@class='copybody']
strip: //*[@class='space']
strip: //*[@class='articleFoot']
title: //h2
author: string('Andy Rutledge')
date: //div[@class='articledate']
body: //div[@class='copybody']
strip: //*[@class='space']
strip: //*[@class='articleFoot']
test_url: http://www.andyrutledge.com/hungry-for-a-better-menu.php

14
inc/3rdparty/site_config/standard/annatravelling.wordpress.com.txt vendored Normal file → Executable file
View File

@ -1,9 +1,9 @@
title: //h1[@class="title"]
author: ("Anna Manasova")
# is ignored, unfortunately
date: //p[@class="date"]
title: //h1[@class="title"]
author: ("Anna Manasova")
# is ignored, unfortunately
date: //p[@class="date"]
body: //div[@class="entry"]
test_url: http://annatravelling.wordpress.com/2011/11/07/a-day-of-cooking-thai/

34
inc/3rdparty/site_config/standard/applature.com.txt vendored Normal file → Executable file
View File

@ -1,18 +1,18 @@
title: //h1[contains(@class, 'title')#
body: //div[@id='mainContent']//div[contains(@class, 'section_content')] | //ul[@class='section_footer']
date: //div[@class='date']
strip_id_or_class: sharethis
strip_id_or_class: stats
strip_id_or_class: apply_form
strip_id_or_class: job_map
strip_id_or_class: respond
strip: //h1//span[@class='type']
strip: //li[@class='print' or @class='map']
replace_string(<ul class="section_footer" style="display): <ul class="section_footer" style="display-bla
prune: no
tidy: no
title: //h1[contains(@class, 'title')#
body: //div[@id='mainContent']//div[contains(@class, 'section_content')] | //ul[@class='section_footer']
date: //div[@class='date']
strip_id_or_class: sharethis
strip_id_or_class: stats
strip_id_or_class: apply_form
strip_id_or_class: job_map
strip_id_or_class: respond
strip: //h1//span[@class='type']
strip: //li[@class='print' or @class='map']
replace_string(<ul class="section_footer" style="display): <ul class="section_footer" style="display-bla
prune: no
tidy: no
test_url: http://applature.com/mining-jobs/jobs/nickel-west-leinster-analytical-laboratory-technician/

12
inc/3rdparty/site_config/standard/apple.com.txt vendored Normal file → Executable file
View File

@ -1,7 +1,7 @@
strip: //p[@class='sosumi']
# Aren't they witty?
# I can't work out what causes the  before the title.
title: //h1[@class='title']
strip: //h1[@class='title']
strip: //p[@class='sosumi']
# Aren't they witty?
# I can't work out what causes the  before the title.
title: //h1[@class='title']
strip: //h1[@class='title']
test_url: http://www.apple.com/pr/library/2011/02/15appstore.html

View File

@ -0,0 +1,4 @@
body: //div[contains(@class, 'articulum')]
test_url: http://www.appledaily.com.tw/realtimenews/article/new/20140120/330479
test_url: http://www.appledaily.com.tw/rss/create/kind/rnews/type/new/

34
inc/3rdparty/site_config/standard/appleinsider.com.txt vendored Normal file → Executable file
View File

@ -1,11 +1,23 @@
title: //p[@class='title']
author: //p[text() = 'By ']/a/text()
strip: //p[text() = 'By ']
body: //td[@class='bod']
strip_id_or_class: title
strip_id_or_class: minor
strip_id_or_class: multipagefooter
test_url: http://www.appleinsider.com/articles/12/02/29/inside_os_x_108_mountain_lion_safari_52_gets_a_simplified_user_interface_with_new_sharing_features.html
title: //h1[@class="art-head"]
author: //p[contains(@class, 'byline')]/a
#author: //p[text() = 'By ']/a/text()
#strip: //p[text() = 'By ']
date: //p[contains(@class, 'date-header')]
body: //div[@class="article"]
strip_id_or_class: lazy
#strip_id_or_class: minor
strip_id_or_class: multipagefooter
strip_id_or_class: date-header
strip_id_or_class: byline
find_string: <noscript>
replace_string: <div>
find_string: </noscript>
replace_string: </div>
test_url: http://www.appleinsider.com/articles/12/02/29/inside_os_x_108_mountain_lion_safari_52_gets_a_simplified_user_interface_with_new_sharing_features.html
test_url: http://appleinsider.com/articles/13/10/03/goldee-companion-app-for-philips-hue-bulbs-offers-shifting-dynamic-light-scenes
test_url: http://appleinsider.com/appleinsider.rss

0
inc/3rdparty/site_config/standard/appleweblog.com.txt vendored Normal file → Executable file
View File

6
inc/3rdparty/site_config/standard/archdaily.com.txt vendored Normal file → Executable file
View File

@ -1,5 +1,5 @@
date: //div[@class='post_date']
body: //div[@class='post_content']
date: //div[@class='post_date']
body: //div[@class='post_content']
test_url: http://www.archdaily.com/185325/p10-mixed-use-building-studio-up

38
inc/3rdparty/site_config/standard/archiveofourown.org.txt vendored Normal file → Executable file
View File

@ -1,18 +1,22 @@
# Description: Fix XPaths to include ALL chapters on 'view_full_work' pages.
# Include: work meta, summary, chapter information, and notes which Instapaper strips out on default.
# Exclude: header, footer, navigation, comments.
# Notes: User is a newbie with XPaths.
title: //h2[@class='title']
author: //h3[@class='byline']
author: //a[@class='login author']
strip_id_or_class:header
strip_id_or_class:navigation
strip_id_or_class:feedback
strip_id_or_class:kudos
strip_id_or_class:add_comment_placeholder
strip_id_or_class:add_comment
strip_id_or_class:globalize
# Description: Fix XPaths to include ALL chapters on 'view_full_work' pages.
# Include: work meta, summary, chapter information, and notes which Instapaper strips out on default.
# Exclude: header, footer, navigation, comments.
# Notes: User is a newbie with XPaths.
title: //h2[@class='title']
author: //h3[@class='byline']
author: //a[@class='login author']
strip_id_or_class:header
strip_id_or_class:navigation
strip_id_or_class:feedback
strip_id_or_class:kudos
strip_id_or_class:add_comment_placeholder
strip_id_or_class:add_comment
strip_id_or_class:globalize
strip_id_or_class:footer
test_url: http://archiveofourown.org/works/229402?view_full_work=true
single_page_link: //div[@id='main']//a[contains(@href, 'view_adult=true')]
test_url: http://archiveofourown.org/works/229402?view_full_work=true
test_url: http://archiveofourown.org/works/750111/chapters/1399929

33
inc/3rdparty/site_config/standard/arstechnica.com.txt vendored Normal file → Executable file
View File

@ -1,16 +1,17 @@
author: //p[@class='byline']/a
body: //div[contains(@class,'article-content')]
strip: //h2[@class='title']
strip_id_or_class: byline
prune: no
date: //div[@class='byline']/span[@class='posted']//abbr/@original-title
date: //div[@class='byline']/span[@class='posted']//abbr
title: //div[@id='story']//h2[@class='title']
strip: //div[@class='pager']
next_page_link: //nav//a[span/@class='next']/@href
test_url: http://arstechnica.com/tech-policy/news/2012/02/gigabit-internet-for-80-the-unlikely-success-of-californias-sonicnet.ars
test_url: http://arstechnica.com/apple/2005/04/macosx-10-4/
author: //p[@class='byline']/a
body: //div[contains(@class,'article-content')]
strip: //h2[@class='title']
strip_id_or_class: byline
strip_id_or_class: story-sidebar
prune: no
date: //div[@class='byline']/span[@class='posted']//abbr/@original-title
date: //div[@class='byline']/span[@class='posted']//abbr
title: //div[@id='story']//h2[@class='title']
strip: //div[@class='pager']
next_page_link: //nav//a[span/@class='next']/@href
test_url: http://arstechnica.com/tech-policy/news/2012/02/gigabit-internet-for-80-the-unlikely-success-of-californias-sonicnet.ars
test_url: http://arstechnica.com/apple/2005/04/macosx-10-4/

8
inc/3rdparty/site_config/standard/articles.boston.com.txt vendored Normal file → Executable file
View File

@ -1,6 +1,6 @@
title: //div[@class="mod-bostonarticleheader mod-articleheader"]/h1
author: substring-after(//div[@class="mod-bostonarticlebyline mod-articlebyline"]/span[3],"By ")
date: //div[@class="mod-bostonarticlebyline mod-articlebyline"]/span[@class="pubdate"]
title: //div[@class="mod-bostonarticleheader mod-articleheader"]/h1
author: substring-after(//div[@class="mod-bostonarticlebyline mod-articlebyline"]/span[3],"By ")
date: //div[@class="mod-bostonarticlebyline mod-articlebyline"]/span[@class="pubdate"]
strip_id_or_class: mod-pagination
test_url: http://articles.boston.com/2011-10-23/news/30313691_1_bigfoot-free-speech-monadnock-state-park

18
inc/3rdparty/site_config/standard/articles.courant.com.txt vendored Normal file → Executable file
View File

@ -1,11 +1,11 @@
title: //div[@class="mod-courantarticleheader mod-articleheader"]/h1
date: //div[@class="mod-courantarticlebyline mod-articlebyline"]/span[@class="pubdate"]
author: //div[@class="mod-courantarticlebyline mod-articlebyline"]/span[3]
strip_id_or_class: mod-article-byline
strip_id_or_class: mod-article-header
strip_id_or_class: mod-article-subtitle
#This leaves some crud after the article, but it's better than nothing.
#It would be ideal if we could set the body to every element matching //div[contains(@class, "mod-articletext")]/p, but it seems like body only takes the first matching element.
title: //div[@class="mod-courantarticleheader mod-articleheader"]/h1
date: //div[@class="mod-courantarticlebyline mod-articlebyline"]/span[@class="pubdate"]
author: //div[@class="mod-courantarticlebyline mod-articlebyline"]/span[3]
strip_id_or_class: mod-article-byline
strip_id_or_class: mod-article-header
strip_id_or_class: mod-article-subtitle
#This leaves some crud after the article, but it's better than nothing.
#It would be ideal if we could set the body to every element matching //div[contains(@class, "mod-articletext")]/p, but it seems like body only takes the first matching element.
test_url: http://articles.courant.com/2011-10-22/news/hc-green-drugsearch--1022-20111022_1_drugs-in-student-lockers-police-dogs-lockdown

View File

@ -0,0 +1,11 @@
body: //div[contains(@class, "article_body")]
# print view
body: //div[@id='print_facet']//div[@id='body']
tidy: no
prune: no
single_page_link: concat(substring-before(//div[@id="echo_container_a"]/@guid, '_story.html'), '_print.html')
test_url: http://articles.washingtonpost.com/2011-10-22/world/35279694_1_germany-acts-german-leaders-chancellor-angela-merkel
test_url: http://articles.washingtonpost.com/2013-05-31/opinions/39658000_1_chemical-weapons-mass-destruction-cartels

2
inc/3rdparty/site_config/standard/asahi.com.txt vendored Normal file → Executable file
View File

@ -1,3 +1,3 @@
body: //div[@id='HeadLine']
body: //div[@id='HeadLine']
strip: //div[@id='utility_right']
test_url: http://www.asahi.com/culture/update/0520/TKY201105200321.html

6
inc/3rdparty/site_config/standard/ascarter.net.txt vendored Normal file → Executable file
View File

@ -1,5 +1,5 @@
title: //h1[@class='article_title']
author: //span[@class='author']
date: //h2[@class='dateline']
title: //h1[@class='article_title']
author: //span[@class='author']
date: //h2[@class='dateline']
body: //div[@class='article_body']
test_url: http://ascarter.net/2012/02/20/enough-is-enough.html

10
inc/3rdparty/site_config/standard/astronews.com.txt vendored Normal file → Executable file
View File

@ -1,7 +1,7 @@
title: //span[@class='titel']
author: //span[@class='metadaten_C']/a//span[@class='metadaten_C']
date: substring-after(//span[@class='metadaten_C'],'astronews.com')
strip: //span[@class='bu']
strip_image_src: '/_images/'
title: //span[@class='titel']
author: //span[@class='metadaten_C']/a//span[@class='metadaten_C']
date: substring-after(//span[@class='metadaten_C'],'astronews.com')
strip: //span[@class='bu']
strip_image_src: '/_images/'
test_url: http://www.astronews.com/news/artikel/2011/10/1110-021.shtml

12
inc/3rdparty/site_config/standard/asymco.com.txt vendored Normal file → Executable file
View File

@ -1,8 +1,8 @@
# Johannes Stühler
title://h2
author://span[@class='meta-content']
date://abbr[@class='date published']/@title
body://div[@class='entry-content']
# Johannes Stühler
title://h2
author://span[@class='meta-content']
date://abbr[@class='date published']/@title
body://div[@class='entry-content']
test_url: http://www.asymco.com/2011/01/14/is-android-more-efficient-than-ios-at-generating-search-revenue/

8
inc/3rdparty/site_config/standard/autoblog.com.txt vendored Normal file → Executable file
View File

@ -1,6 +1,6 @@
prune: no
body: //div[@class='post-body']
author: //p[@class='byline']//a
date: substring-after(//div[@class='about']/p[2], 'Posted')
prune: no
body: //div[@class='post-body']
author: //p[@class='byline']//a
date: substring-after(//div[@class='about']/p[2], 'Posted')
strip: //div[@class='body']/div[@class='meta']
test_url: http://www.autoblog.com/2012/01/17/next-gen-bmw-x5-caught-again/

4
inc/3rdparty/site_config/standard/avclub.com.txt vendored Normal file → Executable file
View File

@ -1,4 +1,4 @@
author: //*[@id="article_wrapper"]/div[1]/a[1]
body: //*[@id="article_wrapper"]/div[2]
author: //*[@id="article_wrapper"]/div[1]/a[1]
body: //*[@id="article_wrapper"]/div[2]
date: //*[@id="article_wrapper"]/div[1]/text()[2]
test_url: http://www.avclub.com/articles/forgetmenot,70904

20
inc/3rdparty/site_config/standard/baltimoresun.com.txt vendored Normal file → Executable file
View File

@ -1,12 +1,12 @@
single_page_link: //div[@class='toppaginate']//a[@rel='nofollow']
convert_double_br_tags: yes
title: //div[@class="story"]/h1
body: //div[@id="story-body-text"]
author: //span[@class="byline"]
date: //p[@class="date"]
strip: //*[@class='all']
strip: //*[@class='articlerail']
single_page_link: //div[@class='toppaginate']//a[@rel='nofollow']
convert_double_br_tags: yes
title: //div[@class="story"]/h1
body: //div[@id="story-body-text"]
author: //span[@class="byline"]
date: //p[@class="date"]
strip: //*[@class='all']
strip: //*[@class='articlerail']
test_url: http://www.baltimoresun.com/news/maryland/bs-md-omalley-budget-2-20120116,0,5340585.story

View File

@ -0,0 +1,13 @@
title: //h1[@class='title']
author: //p[@class="author"]/a[1]
body: //div[@class="article"]
date: //p[@class="date"]
# remove user tools
strip: //div[@class='tools']
strip: //h1
strip: //h2[@class='subtitle']
strip: //p[@class='author']
strip: //p[@class='date']
test_url: http://www.baseballprospectus.com/article.php?articleid=18463

10
inc/3rdparty/site_config/standard/basicthinking.de.txt vendored Normal file → Executable file
View File

@ -1,7 +1,7 @@
title: //h2
date: //span[@class='date']
body: //div[@class='entry']
strip: //div[@class='zusatz']
title: //h2
date: //span[@class='date']
body: //div[@class='entry']
strip: //div[@class='zusatz']
test_url: http://www.basicthinking.de/blog/2011/12/13/sagt-social-networks-adieu-begrust-private-networks/

22
inc/3rdparty/site_config/standard/bb.is.txt vendored Normal file → Executable file
View File

@ -1,13 +1,13 @@
author: substring(//h3[@class='headlines']/span[@class='dates'],0,string-length(//h3[@class='headlines']/span[@class='dates'])-20)
date: substring((//h3[@class='headlines']/span[@class='dates']),string-length(//h3[@class='headlines']/span[@class='dates'])-18,12)
body: //div[@class='first-article-big']
strip: //table[@class='newsimagecontainer']
strip: //h3[@class='headlines']
strip: //iframe[@class='headlines']
strip: //a[@class='newslink']
author: substring(//h3[@class='headlines']/span[@class='dates'],0,string-length(//h3[@class='headlines']/span[@class='dates'])-20)
date: substring((//h3[@class='headlines']/span[@class='dates']),string-length(//h3[@class='headlines']/span[@class='dates'])-18,12)
body: //div[@class='first-article-big']
strip: //table[@class='newsimagecontainer']
strip: //h3[@class='headlines']
strip: //iframe[@class='headlines']
strip: //a[@class='newslink']
convert_double_br_tags: yes
test_url: http://bb.is/Pages/82?NewsID=174119

74
inc/3rdparty/site_config/standard/bbc.co.uk.txt vendored Normal file → Executable file
View File

@ -1,32 +1,42 @@
body: //div[@class="story-body"]
title: //h1[@class="story-header"]
date: //span[@class="story-date"]/span[@class='date']
# recipes, e.g. http://www.bbc.co.uk/food/recipes/mymincepies_71055
body: //div[contains(@class, 'hrecipe')]//div[@id='subcolumn-1']
#strip: //div[@class="story-feature narrow"]
#strip: //div[@class="story-feature wide"]
#strip: //div[@class="story-feature dslideshow-enclosure"]
strip: //div[contains(@class, "story-feature")]
strip: //span[@class="story-date"]
#strip: //div[@class="caption body-narrow-width"]
strip: //div[@class="warning"]//p
strip: //div[@id='page-bookmark-links-head']
strip: //object
strip: //div[contains(@class, "bbccom_advert_placeholder")]
strip: //div[contains(@class, "embedded-hyper")]
strip: //div[contains(@class, 'market-data')]
strip: //a[contains(@class, 'hidden')]
strip: //div[contains(@class, 'hypertabs')]
strip: //div[contains(@class, 'related')]
strip: //form[@id='comment-form']
strip: //div[contains(@class, 'comment-introduction')]
replace_string(<noscript>): <div>
replace_string(</noscript>): </div>
prune: no
dissolve: //h2
test_url: http://www.bbc.co.uk/news/business-15060862
body: //div[@class="story-body"]
# for video entries
body: //div[contains(@class, "videoInStory") or @id="meta-information"]
title: //h1[@class="story-header"]
date: //span[@class="story-date"]/span[@class='date']
# for sport site
date: //meta[@name='DCTERMS.created']/@content
author: //div[@id='headline']//span[@class='byline-name']
# recipes, e.g. http://www.bbc.co.uk/food/recipes/mymincepies_71055
body: //div[contains(@class, 'hrecipe')]//div[@id='subcolumn-1']
#strip: //div[@class="story-feature narrow"]
#strip: //div[@class="story-feature wide"]
#strip: //div[@class="story-feature dslideshow-enclosure"]
strip: //div[contains(@class, "story-feature")]
strip: //span[@class="story-date"]
#strip: //div[@class="caption body-narrow-width"]
strip: //div[@class="warning"]//p
strip: //div[@id='page-bookmark-links-head']
strip: //object
strip: //div[contains(@class, "bbccom_advert_placeholder")]
strip: //div[contains(@class, "embedded-hyper")]
strip: //div[contains(@class, 'market-data')]
strip: //a[contains(@class, 'hidden')]
strip: //div[contains(@class, 'hypertabs')]
strip: //div[contains(@class, 'related')]
strip: //form[@id='comment-form']
strip: //div[contains(@class, 'comment-introduction')]
strip: //div[contains(@class, 'share-tools')]
strip: //div[@id='also-related-links']
replace_string(<noscript>): <div>
replace_string(</noscript>): </div>
prune: no
dissolve: //h2
test_url: http://www.bbc.co.uk/sport/0/football/23224017
test_url: http://www.bbc.co.uk/news/business-15060862
# video entry
test_url: http://www.bbc.co.uk/news/world-asia-22056933

View File

@ -0,0 +1,16 @@
title: //header//h1
#body: //article[contains(@class, 'node-full')]
body: //div[contains(@class, 'recipe-details') or contains(@class, 'tips-carousel')] | //section[@id='recipe-ingredients' or @id='recipe-method']
strip_id_or_class: recipe-rating-wrapper
strip_id_or_class: magazine-subcribe-header
strip_id_or_class: hide
strip_id_or_class: recipe-actions
strip_id_or_class: buy-ingredients
strip_id_or_class: related-content
strip_id_or_class: recipe-magazine-ad
strip_id_or_class: copy-right
prune: no
test_url: http://www.bbcgoodfood.com/recipes/1131634/minced-beef-wellington

28
inc/3rdparty/site_config/standard/benoitmaison.org.txt vendored Normal file → Executable file
View File

@ -1,16 +1,16 @@
body: //div[@class="entry-content"]
# Remove text &lsquo;Tweet&rsquo;
strip: //div[@class="entry-content"]/div[last()]
title: h1[@class="entry-title"]
# If the Instapaper text parser worked with HTML5 tags, we would use:
date: //time[@class="entry-date"]
# But since it does not, use this more complicated rule:
date: //div[@class="entry-meta"]/a[@rel="bookmark"]
# Unfortunately, the following rule is overridden by the automatically found author.
body: //div[@class="entry-content"]
# Remove text &lsquo;Tweet&rsquo;
strip: //div[@class="entry-content"]/div[last()]
title: h1[@class="entry-title"]
# If the Instapaper text parser worked with HTML5 tags, we would use:
date: //time[@class="entry-date"]
# But since it does not, use this more complicated rule:
date: //div[@class="entry-meta"]/a[@rel="bookmark"]
# Unfortunately, the following rule is overridden by the automatically found author.
author: ("Benoit Maison")
test_url: http://www.benoitmaison.org/2011/12/06/why-siri-had-to-start-in-beta/

2
inc/3rdparty/site_config/standard/berlingske.dk.txt vendored Normal file → Executable file
View File

@ -1,3 +1,3 @@
title: //h1[@class='headline']
title: //h1[@class='headline']
body: //div[contains(@class, 'article-wrapper')]
test_url: http://www.berlingske.dk/danmark/festen-er-flyttet-nordpaa

View File

@ -0,0 +1,5 @@
body: //div[contains(@class, "NewsText"]
prune: no
test_url: http://www.bernama.com/bernama/v7/rss/english.php
test_url: http://www.bernama.com/bernama/v7/newsindex.php?id=943513

0
inc/3rdparty/site_config/standard/betabeat.com.txt vendored Normal file → Executable file
View File

10
inc/3rdparty/site_config/standard/betanews.com.txt vendored Normal file → Executable file
View File

@ -1,7 +1,7 @@
# some articles at this site like this one doesn't
# seem to pick up the article body via normal
# processing, other articles come through fine
# http://www.betanews.com/joewilcox/article
# /Google-is-a-marketing-sensation/1309708375
# some articles at this site like this one doesn't
# seem to pick up the article body via normal
# processing, other articles come through fine
# http://www.betanews.com/joewilcox/article
# /Google-is-a-marketing-sensation/1309708375
body: //*[@id="article"]
test_url: http://www.betanews.com/joewilcox/article/Google-is-a-marketing-sensation/1309708375

12
inc/3rdparty/site_config/standard/biography.com.txt vendored Normal file → Executable file
View File

@ -1,8 +1,8 @@
title: //div[contains(@class, 'main-content')]//h1
body: //div[@class='summary-column'] | //div[contains(@class, 'main-content')]
prune: no
single_page_link: //div[@id='biography-action-links']//a[contains(@href, '/print/')]
title: //div[contains(@class, 'main-content')]//h1
body: //div[@class='summary-column'] | //div[contains(@class, 'main-content')]
prune: no
single_page_link: //div[@id='biography-action-links']//a[contains(@href, '/print/')]
test_url: http://www.biography.com/print/profile/martin-luther-9389283

0
inc/3rdparty/site_config/standard/bitelia.com.txt vendored Normal file → Executable file
View File

View File

@ -0,0 +1,13 @@
date: //meta[@name='publish-date']/@content
body: //div[contains(@class, 'articleContentWrapper')]
prune: no
strip: //div[contains(@class, 'staff_info')]//dd[contains(., 'Twitter')]
strip_id_or_class: related_content
strip_id_or_class: enlarge
strip_id_or_class: photoBy
strip_id_or_class: older
test_url: http://www.bizjournals.com/cincinnati/news/2013/10/03/harris-teeter-shareholders-vote-on.html
test_url: http://feeds.bizjournals.com/industry_20?format=xml

10
inc/3rdparty/site_config/standard/bjango.com.txt vendored Normal file → Executable file
View File

@ -1,7 +1,7 @@
title: //h1[@class='articlehead']
body: //div[@class='column']
strip: //h1
strip: //div[@class='help']
title: //h1[@class='articlehead']
body: //div[@class='column']
strip: //h1
strip: //div[@class='help']
#no author or date/time provided in current layout
test_url: http://bjango.com/articles/actions/

12
inc/3rdparty/site_config/standard/blog.arsln.org.txt vendored Normal file → Executable file
View File

@ -1,8 +1,8 @@
tidy: no
prune: no
date: //article/header/h6/time
title: //article/header/h3
author: //meta[@name='author']/@content
body: //article//post
tidy: no
prune: no
date: //article/header/h6/time
title: //article/header/h3
author: //meta[@name='author']/@content
body: //article//post
test_url: http://blog.arsln.org/aska-ayip-oluyor/

10
inc/3rdparty/site_config/standard/blog.asmartbear.com.txt vendored Normal file → Executable file
View File

@ -1,7 +1,7 @@
title: //title
author: //span[@class='author vcard']/a
date: //p[@class='headline_meta']/abbr[@class='published']
body: //div[@class='format_text entry-content']
title: //title
author: //span[@class='author vcard']/a
date: //p[@class='headline_meta']/abbr[@class='published']
body: //div[@class='format_text entry-content']
strip: //div[@id='dd_ajax_float']
test_url: http://blog.asmartbear.com/how-to-get-quality-freelance-graphics-design-work-on-a-budget.html

14
inc/3rdparty/site_config/standard/blog.cloudflare.com.txt vendored Normal file → Executable file
View File

@ -1,9 +1,9 @@
# Instapaper gets this back to front and only gets the blog title instead of the article title.
title: substring-before(//title, '-')
author: //a[ contains(@href, '/people') ]
body: //div[ @class='post' ]
# Instapaper gets this back to front and only gets the blog title instead of the article title.
title: substring-before(//title, '-')
author: //a[ contains(@href, '/people') ]
body: //div[ @class='post' ]
# Date is impossible to retrieve since they use those stupid "fuzzy" dates, inserted through javascript, at posterous.
test_url: http://blog.cloudflare.com/understanding-analytics-when-is-a-page-view-n

6
inc/3rdparty/site_config/standard/blog.fefe.de.txt vendored Normal file → Executable file
View File

@ -1,5 +1,5 @@
title: //h2
date: //h3
body: //ul
title: //h2
date: //h3
body: //ul
test_url: http://blog.fefe.de/?ts=b063bf55

18
inc/3rdparty/site_config/standard/blog.instagram.com.txt vendored Normal file → Executable file
View File

@ -1,11 +1,11 @@
# clean Instagram blog a little bit
tidy:no
prune:no
body://div[contains(@id,'content')]
strip_id_or_class:meta
strip_id_or_class:notes
# clean Instagram blog a little bit
tidy:no
prune:no
body://div[contains(@id,'content')]
strip_id_or_class:meta
strip_id_or_class:notes
strip_id_or_class:pagination
test_url: http://blog.instagram.com/post/8757832007/fromwhereistand

View File

@ -0,0 +1,9 @@
author: //a[@href="http://www.marco.org/about"]
date: //span[@class="date"]
# Remove the date from article body.
strip: //span[@class="date"]
# Remove pagination links from article body.
strip: //div[@id="pagination"]
test_url: http://blog.instapaper.com/post/31303984531

4
inc/3rdparty/site_config/standard/blog.jaysalvat.com.txt vendored Normal file → Executable file
View File

@ -1,4 +1,4 @@
date: //span[contains(@class, 'date-links')]
author: //span[contains(@class, 'author-links')]
date: //span[contains(@class, 'date-links')]
author: //span[contains(@class, 'author-links')]
body: //div[contains(@class, 'entry-content')]
test_url: http://blog.jaysalvat.com/article/celui-qui-avait-refait-son-site-web

6
inc/3rdparty/site_config/standard/blog.kaelig.fr.txt vendored Normal file → Executable file
View File

@ -1,5 +1,5 @@
body: //*[contains(@class, 'post_content')]
author: string('Kaelig Deloumeau-Prigent')
title: //h1[@class='title']
body: //*[contains(@class, 'post_content')]
author: string('Kaelig Deloumeau-Prigent')
title: //h1[@class='title']
date: //span[@class='date']
test_url: http://blog.kaelig.fr/post/24877648508/preprocesseurs-css-renoncer-par-choix-ou-par

8
inc/3rdparty/site_config/standard/blog.naver.com.txt vendored Normal file → Executable file
View File

@ -1,6 +1,6 @@
title: //span[@class='pcol1 itemSubjectBoldfont']
body: //div[@id='postListBody']
date: //p[@class='date fil5 pcol2']
single_page_link: /html/frameset/frame[1]/attribute::src
title: //span[@class='pcol1 itemSubjectBoldfont']
body: //div[@id='postListBody']
date: //p[@class='date fil5 pcol2']
single_page_link: /html/frameset/frame[1]/attribute::src
strip: //div[@class='post-btn']
test_url: http://blog.naver.com/how2invest/110135068757

20
inc/3rdparty/site_config/standard/blog.pchome.net.txt vendored Normal file → Executable file
View File

@ -1,12 +1,12 @@
# PCHOME blog, a popular Chinese blog host
# Oct 15, 2011
#
title://*[contains(@class,'imp')]/h2
date://*[contains(@class,'imp')]/span
body://div[contains(@id,'blog_content')]
# PCHOME blog, a popular Chinese blog host
# Oct 15, 2011
#
title://*[contains(@class,'imp')]/h2
date://*[contains(@class,'imp')]/span
body://div[contains(@id,'blog_content')]
test_url: http://blog.pchome.net/article/462502.html

8
inc/3rdparty/site_config/standard/blog.pinboard.in.txt vendored Normal file → Executable file
View File

@ -1,6 +1,6 @@
title: //a[@class="blog_title"]
date: //p[@class="when"]/a
body: //div[@class="blog_entry"]
strip_id_or_class:blog_title
title: //a[@class="blog_title"]
date: //p[@class="when"]/a
body: //div[@class="blog_entry"]
strip_id_or_class:blog_title
strip_id_or_class:when
test_url: http://blog.pinboard.in/2011/11/the_social_graph_is_neither/

View File

@ -0,0 +1,11 @@
# This filter is tested on:
# http://blog.renren.com/share/224959024/14260739544
# http://blog.renren.com/share/231323504/14261768898
# http://blog.renren.com/share/230305019/1502806705
title://h1[contains(@class, 'title-article')]
author://span[contains(@class, 'name')]
body://div[contains(@class, 'content-body')]
convert_double_br_tags:yes
test_url: http://blog.renren.com/share/230305019/1502806705

50
inc/3rdparty/site_config/standard/blog.sina.com.cn.txt vendored Normal file → Executable file
View File

@ -1,26 +1,26 @@
# Sina blog, the most popular blog host in China.
# Its source code is horrible.
#
# Issue:
# Only the first image in the article is displayed.
# The rest images are replace by a 1x1 transparent gif by sina blog host.
#
title://*[contains(@class,'titName SG_txta')]
author://*[contains(@id,'ownernick')]
date://*[contains(@class,'time SG_txtc')]
body://div[contains(@class,'articalContent')]
# Remove redundant content which has span class start with "MASS"
# Example <span class="MASSf21674ffeef7"></span>
strip://span[contains(@class,'MASS')]
# Remove comment
strip://div[contains(@class,'allComm')]
# Remove hiden text and link
strip://ins
tidy:no
convert_double_br_tags:yes
# Sina blog, the most popular blog host in China.
# Its source code is horrible.
#
# Issue:
# Only the first image in the article is displayed.
# The rest images are replace by a 1x1 transparent gif by sina blog host.
#
title://*[contains(@class,'titName SG_txta')]
author://*[contains(@id,'ownernick')]
date://*[contains(@class,'time SG_txtc')]
body://div[contains(@class,'articalContent')]
# Remove redundant content which has span class start with "MASS"
# Example <span class="MASSf21674ffeef7"></span>
strip://span[contains(@class,'MASS')]
# Remove comment
strip://div[contains(@class,'allComm')]
# Remove hiden text and link
strip://ins
tidy:no
convert_double_br_tags:yes
test_url: http://blog.sina.com.cn/s/blog_5054769e0102dtja.html

0
inc/3rdparty/site_config/standard/blog.spu.edu.txt vendored Normal file → Executable file
View File

10
inc/3rdparty/site_config/standard/blog.wells.ee.txt vendored Normal file → Executable file
View File

@ -1,6 +1,6 @@
title: //h2/a[@class="no-link title"]
author: //h2[@id="blog_owner"]
date: //time
strip: //h2/a[@class="no-link title"]
test_url: http://blog.wells.ee/retina
title: //h2/a[@class="no-link title"]
author: //h2[@id="blog_owner"]
date: //time
strip: //h2/a[@class="no-link title"]
test_url: http://blog.wells.ee/retina
test_url: http://blog.wells.ee/skeuomorphism

12
inc/3rdparty/site_config/standard/blogs.aljazeera.net.txt vendored Normal file → Executable file
View File

@ -1,8 +1,8 @@
# 2011-08-23 [carlo@...] Initial version.
author: //div[@id="blogauthordatebox-node"]//a[@title="View user profile."]/text()
# why yes, I do feel a bit dirty
date: substring-before( substring-after( substring-after( //div[@id="blogauthordatebox-node"]//td[3], "on " ), ", "), " " )
# 2011-08-23 [carlo@...] Initial version.
author: //div[@id="blogauthordatebox-node"]//a[@title="View user profile."]/text()
# why yes, I do feel a bit dirty
date: substring-before( substring-after( substring-after( //div[@id="blogauthordatebox-node"]//td[3], "on " ), ", "), " " )
test_url: http://blogs.aljazeera.net/asia/2011/08/22/peoples-hero

0
inc/3rdparty/site_config/standard/blogs.forbes.com.txt vendored Normal file → Executable file
View File

6
inc/3rdparty/site_config/standard/blogs.hbr.org.txt vendored Normal file → Executable file
View File

@ -1,4 +1,4 @@
title: //div[@id='pageFeature']/h1
body: //div[@id='articleBody']
strip: //div[@class='module wide']
title: //div[@id='pageFeature']/h1
body: //div[@id='articleBody']
strip: //div[@class='module wide']
test_url: http://blogs.hbr.org/bregman/2011/04/the-1-killer-of-meetings-and-w.html?utm_source=feedburner&utm_medium=feed&utm_campaign=Feed%3A+harvardbusiness+%28HBR.org%29

Some files were not shown because too many files have changed in this diff Show More