diff options
| -rw-r--r-- | abc.net.au.txt | 9 | ||||
| -rw-r--r-- | cbsnews.com.txt | 3 | ||||
| -rw-r--r-- | huffingtonpost.com.txt | 7 | ||||
| -rw-r--r-- | mashable.com.txt | 13 | ||||
| -rw-r--r-- | medialens.org.txt | 4 | ||||
| -rw-r--r-- | online.wsj.com.txt | 5 | ||||
| -rw-r--r-- | urbandictionary.com.txt | 4 | ||||
| -rw-r--r-- | wtatennis.com.txt | 7 |
8 files changed, 40 insertions, 12 deletions
diff --git a/abc.net.au.txt b/abc.net.au.txt index 2d99538..22b3a0f 100644 --- a/abc.net.au.txt +++ b/abc.net.au.txt @@ -1,4 +1,4 @@ -title: //h1 +title: //div[@class='article section']//h1 author: //div[@class="byline"]/a date: //span[@class="timestamp"] body: //div[@class="page section"] @@ -10,4 +10,9 @@ strip: //h1 strip: //div[@class="byline"] strip: //p[@class="published"] strip: //div[contains(@class,"featured-scroller")] -test_url: http://www.abc.net.au/news/2013-03-27/open-speed-highways-change-clp-giles/4597892
\ No newline at end of file +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 diff --git a/cbsnews.com.txt b/cbsnews.com.txt index 780bc15..04d2023 100644 --- a/cbsnews.com.txt +++ b/cbsnews.com.txt @@ -8,7 +8,8 @@ body: //div[@id='storyMediaBox'] | //div[contains(@class, 'storyText')] strip: //div[@class="scrollingArrows"] strip: //div[@class="timeLine"] strip: //dl[@class="storyBlogByline"] +strip: //span[@class='image-credit'] prune: no -test_url: http://www.cbsnews.com/8301-201_162-57366361/rescued-americans-dad-proud-of-the-u.s/
\ No newline at end of file +test_url: http://www.cbsnews.com/8301-201_162-57366361/rescued-americans-dad-proud-of-the-u.s/ diff --git a/huffingtonpost.com.txt b/huffingtonpost.com.txt index fb990a7..d4618c1 100644 --- a/huffingtonpost.com.txt +++ b/huffingtonpost.com.txt @@ -3,14 +3,19 @@ body: //div[img[starts-with(@id, 'img_caption')]] | //div[@class="big_photo"] | date: //meta[@name="publish_date"]/@content author: //a[@rel="author"] author: //meta[@name="author"]/@content + prune: no tidy: no + strip: //footer strip_id_or_class: ps-slideshow strip_id_or_class: fs-slideshow strip: //p[contains(., 'Related on HuffPost:')] +strip_id_or_class: contribute-story +strip_id_or_class: promo_holder + # end early replace_string(<div class="sbm-main): </body></html><div class="not-interested test_url: http://www.huffingtonpost.com/mitch-moxley/tracking-beijings-boom-th_b_1209828.html -test_url: http://www.huffingtonpost.com/2012/09/11/president-obama-iphone-throwdown_n_1873826.html
\ No newline at end of file +test_url: http://www.huffingtonpost.com/2012/09/11/president-obama-iphone-throwdown_n_1873826.html diff --git a/mashable.com.txt b/mashable.com.txt index 2c5a14a..b6efb6c 100644 --- a/mashable.com.txt +++ b/mashable.com.txt @@ -1,4 +1,11 @@ -title: //header[@class='entry-title']/h1 -body: //div[@class='description'] +title: //h1[@class='title'] +author: substring-after(//span[@class='author_name'], 'By ') +date: //time + +body: //article strip: //div[@class='ytm-gallery-box'] -test_url: http://mashable.com/2011/12/05/india-wants-google-and-facebook-to-censor-user-content/
\ No newline at end of file +strip: //div[contains(@class, 'adsense')] +strip: //aside[contains(@class, 'social')] +strip_id_or_class: article-topics + +test_url: http://mashable.com/2013/05/24/myspace-architects-rebuilding-a-brand/ diff --git a/medialens.org.txt b/medialens.org.txt index ff2a91c..4c333aa 100644 --- a/medialens.org.txt +++ b/medialens.org.txt @@ -1,2 +1,4 @@ -strip: //div[contains(@class, 'article-tools')] +strip_id_or_class: article-tools +strip_id_or_class: pagenav +prune: no test_url: http://www.medialens.org/index.php/alerts/alert-archive/2012/713-the-illusion-of-democracy.html
\ No newline at end of file diff --git a/online.wsj.com.txt b/online.wsj.com.txt index d20d1d2..e0f91ac 100644 --- a/online.wsj.com.txt +++ b/online.wsj.com.txt @@ -2,7 +2,7 @@ title: //meta[@property="og:title"]/@content body: //div[@id='article_story_body'] author: //h3[@class='byline']/a -# for slid show content +# for slide show content body: //ul[@id='imageSlide']//li[@class='firstSlide']//img | (//div[@class='txt_body']//p)[1] date: //li[@class='dateStamp']/small @@ -14,10 +14,11 @@ 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/article/SB10001424052970203363504577185322849515102.html # slide show -test_url: http://online.wsj.com/article/SB10001424052970204791104577110550376458164.html
\ No newline at end of file +test_url: http://online.wsj.com/article/SB10001424052970204791104577110550376458164.html diff --git a/urbandictionary.com.txt b/urbandictionary.com.txt index 01ba69c..385c95c 100644 --- a/urbandictionary.com.txt +++ b/urbandictionary.com.txt @@ -1,3 +1,3 @@ title: //title -body: //td[@id='content'] -test_url: http://www.urbandictionary.com/define.php?term=Grown-Ass
\ No newline at end of file +body: //table[@id='entries'] +test_url: http://www.urbandictionary.com/define.php?term=Grown-Ass diff --git a/wtatennis.com.txt b/wtatennis.com.txt new file mode 100644 index 0000000..1000ab2 --- /dev/null +++ b/wtatennis.com.txt @@ -0,0 +1,7 @@ +title: //h1[contains(@class, 'header-2')] +body: //article//*[contains(@class, 'teaserText') or contains(@class, 'lastUpdated') or contains(@class, 'image') or contains(@class, 'body')] +strip_id_or_class: articleIndex +prune: no + +test_url: http://www.wtatennis.com/news/article/3190914 +test_url: http://www.wtatennis.com/news/article/3190244
\ No newline at end of file |