diff options
| -rw-r--r-- | .hardware.info.txt | 1 | ||||
| -rw-r--r-- | .posterous.com.txt | 11 | ||||
| -rw-r--r-- | .tweakblogs.net.txt | 1 | ||||
| -rw-r--r-- | au.news.yahoo.com.txt | 1 | ||||
| -rw-r--r-- | computerworld.com.txt | 2 | ||||
| -rw-r--r-- | hardwareluxx.de.txt | 2 | ||||
| -rw-r--r-- | infoworld.com.txt | 2 | ||||
| -rw-r--r-- | itnews.com.au.txt | 2 | ||||
| -rw-r--r-- | itworld.com.txt | 2 | ||||
| -rw-r--r-- | sueddeutsche.de.txt | 22 | ||||
| -rw-r--r-- | sz.de.txt | 22 |
11 files changed, 12 insertions, 56 deletions
diff --git a/.hardware.info.txt b/.hardware.info.txt index b684bcd..82c3379 100644 --- a/.hardware.info.txt +++ b/.hardware.info.txt @@ -3,5 +3,4 @@ author: //span[@itemprop='author'] body: //article[@itemprop='articleBody'] date: //span[@itemprop='datePublished']/@content -test_url: http://hardware.info/updates/all.rss test_url: http://be.hardware.info/reviews/6197/game-pcs-van-0-25-en-5-jaar-oud-review-tijd-om-te-upgraden diff --git a/.posterous.com.txt b/.posterous.com.txt deleted file mode 100644 index 2ec313e..0000000 --- a/.posterous.com.txt +++ /dev/null @@ -1,11 +0,0 @@ -body: //div[starts-with(@id, 'post_') and @class='post'] | //article[starts-with(@id, 'post_')] -strip: //div[contains(@class, 'sharing') or contains(@class, 'infobar') or contains(@class, 'editbox')] -strip: //aside[contains(@class, 'p_responses')] -strip: //h2[starts-with(@id, 'posttitle_')] -strip: //header | //footer -strip: //*[@id='extra_links'] -strip: //img[contains(@class, 'profile_border')] -# fixes paragraphing issues -replace_string(<p />): <br /><br /> -prune: no -test_url: http://blog.mariosc.com/book-recommendation-we-are-all-weird
\ No newline at end of file diff --git a/.tweakblogs.net.txt b/.tweakblogs.net.txt index fb022b7..784586c 100644 --- a/.tweakblogs.net.txt +++ b/.tweakblogs.net.txt @@ -2,4 +2,3 @@ body: //div[@class="article"] author: //p[@class="author"]/a test_url: http://harryl.tweakblogs.net/blog/11988/voorstellen -test_url: http://tweakblogs.net/feed/ diff --git a/au.news.yahoo.com.txt b/au.news.yahoo.com.txt index 8e84cbb..65753c4 100644 --- a/au.news.yahoo.com.txt +++ b/au.news.yahoo.com.txt @@ -2,3 +2,4 @@ strip: //a[contains(text(), "RELATED:")] author: //div[@class="info"]//span[@class="association printer-source"] author: //div[@class="info"]//span[@class="stamp printer-date"] +test_url: https://au.news.yahoo.com/a/31334394/brave-subway-employee-fights-off-masked-robber-using-her-bare-hands/ diff --git a/computerworld.com.txt b/computerworld.com.txt index 9898309..a93446a 100644 --- a/computerworld.com.txt +++ b/computerworld.com.txt @@ -15,3 +15,5 @@ strip: //h3[contains(., "See also:")] strip: //div[@id="article-top-page-number"] strip: //p[starts-with(normalize-space(.), '[')] strip: //p[starts-with(normalize-space(.), '+')] + +test_url: http://www.computerworld.com/article/3054550/data-storage/scientists-could-use-dna-to-shrink-a-data-center-into-a-sugar-cube.html diff --git a/hardwareluxx.de.txt b/hardwareluxx.de.txt index 3775d79..227bea7 100644 --- a/hardwareluxx.de.txt +++ b/hardwareluxx.de.txt @@ -1,7 +1,7 @@ tidy: no prune: no -title: //span[@itemprop='title'] +title: (//span[@itemprop='title'])[last()] author: //span[@itemprop='author']//span[@itemprop='name'] body: //article date: //time diff --git a/infoworld.com.txt b/infoworld.com.txt index 9898309..766dfba 100644 --- a/infoworld.com.txt +++ b/infoworld.com.txt @@ -15,3 +15,5 @@ strip: //h3[contains(., "See also:")] strip: //div[@id="article-top-page-number"] strip: //p[starts-with(normalize-space(.), '[')] strip: //p[starts-with(normalize-space(.), '+')] + +test_url: http://www.infoworld.com/article/3053563/it-management/disrupt-or-die-beware-the-siren-calls-of-tech-consultants.html diff --git a/itnews.com.au.txt b/itnews.com.au.txt index 47cbb0f..f1ff4c3 100644 --- a/itnews.com.au.txt +++ b/itnews.com.au.txt @@ -3,3 +3,5 @@ body: //div[@class='body-content'] author: //span[@class='author-byline']/a[contains(@id, 'Author')] strip: //span[contains(@id, 'Article_SourceLabel')] + +test_url: http://www.itnews.com.au/feature/the-untold-story-of-iinet-and-internodes-basslink-internet-woes-417296 diff --git a/itworld.com.txt b/itworld.com.txt index 9898309..b96ad33 100644 --- a/itworld.com.txt +++ b/itworld.com.txt @@ -15,3 +15,5 @@ strip: //h3[contains(., "See also:")] strip: //div[@id="article-top-page-number"] strip: //p[starts-with(normalize-space(.), '[')] strip: //p[starts-with(normalize-space(.), '+')] + +test_url: http://www.itworld.com/article/3055304/your-face-is-big-data-the-title-of-this-photographers-experiment-says-it-all.html diff --git a/sueddeutsche.de.txt b/sueddeutsche.de.txt index 71ec5aa..de619eb 100644 --- a/sueddeutsche.de.txt +++ b/sueddeutsche.de.txt @@ -1,24 +1,3 @@ -# 2012-12-04: complete rewrite after Süddeutsche.de relaunch - carlo@... - -#single_page_link: //a[ contains( @href, "/2.220/" ) ] - -#body: //article[@id="sitecontent"]/section[@class="body"] -#author: //address[@class="author"] -#date: //div[@class="header"]//h1//span[@class="updated"] -#wrap_in(small): //div[@class="footer"] -#wrap_in(i): //figcaption/h3 -#dissolve: //figcaption//h3 -#dissolve: //figure/div[@class="body"] -#dissolve: //figure/a - -#strip: //figure[ not( contains(@class, "zoomimage" ) ) ] -#strip: //div[@data-onlineonly="true"] -#strip: //address[@class="author"] - -#test_url: http://www.sueddeutsche.de/muenchen/mietshaus-am-gaertnerplatz-alles-muss-raus-1.1556693 - - - body: //article[@id="sitecontent"] author: //meta[@name="author"]/@content @@ -27,3 +6,4 @@ strip: //div[@id="article-sidebar-wrapper"] strip: //p[@class="anzeige"] strip: //section[@class="authors"] +test_url: http://www.sueddeutsche.de/muenchen/mietshaus-am-gaertnerplatz-alles-muss-raus-1.1556693 @@ -1,24 +1,3 @@ -# 2012-12-04: complete rewrite after Süddeutsche.de relaunch - carlo@... - -#single_page_link: //a[ contains( @href, "/2.220/" ) ] - -#body: //article[@id="sitecontent"]/section[@class="body"] -#author: //address[@class="author"] -#date: //div[@class="header"]//h1//span[@class="updated"] -#wrap_in(small): //div[@class="footer"] -#wrap_in(i): //figcaption/h3 -#dissolve: //figcaption//h3 -#dissolve: //figure/div[@class="body"] -#dissolve: //figure/a - -#strip: //figure[ not( contains(@class, "zoomimage" ) ) ] -#strip: //div[@data-onlineonly="true"] -#strip: //address[@class="author"] - -#test_url: http://www.sueddeutsche.de/muenchen/mietshaus-am-gaertnerplatz-alles-muss-raus-1.1556693 - - - body: //article[@id="sitecontent"] author: //meta[@name="author"]/@content @@ -28,3 +7,4 @@ strip: //p[@class="anzeige"] strip: //section[@class="authors"] strip: //div[contains(@class, "embed")] +test_url: http://www.sueddeutsche.de/muenchen/mietshaus-am-gaertnerplatz-alles-muss-raus-1.1556693 |