diff options
| -rw-r--r-- | france24.com.txt | 14 | ||||
| -rw-r--r-- | mobile.nytimes.com.txt | 3 | ||||
| -rw-r--r-- | washingtonpost.com.txt | 5 |
3 files changed, 22 insertions, 0 deletions
diff --git a/france24.com.txt b/france24.com.txt new file mode 100644 index 0000000..6356e04 --- /dev/null +++ b/france24.com.txt @@ -0,0 +1,14 @@ +# 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%2Fwww.france24.com%2Fen%2F20150427-togo-gnassingbe-poised-extend-power-election%2F + +body: //article[contains(concat(' ',normalize-space(@class),' '),' article-long ')]//div[contains(concat(' ',normalize-space(@class),' '),' bd ')] +title: //h1[@class="title"] +author://p[@class="author"] +date://p[@class="modification"] + +find_string: <p class="modification">Latest update : +replace_string: <p class="modification"> + + +test_url: http://www.france24.com/en/20150427-togo-gnassingbe-poised-extend-power-election/
\ No newline at end of file diff --git a/mobile.nytimes.com.txt b/mobile.nytimes.com.txt index c60252e..ef1ce98 100644 --- a/mobile.nytimes.com.txt +++ b/mobile.nytimes.com.txt @@ -1,4 +1,7 @@ title: //h1[contains(@class, 'headline')] body: //article[contains(@class, 'full-art')] +date: //meta[@name="pdate"]/@content +author: //meta[@name="byl"]/@content + strip_id_or_class: image-credit test_url: http://mobile.nytimes.com/2014/06/19/opinion/gail-collins-romney-and-the-2016-contenders-huddle.html
\ No newline at end of file diff --git a/washingtonpost.com.txt b/washingtonpost.com.txt index 0aa9f1d..d60d696 100644 --- a/washingtonpost.com.txt +++ b/washingtonpost.com.txt @@ -5,9 +5,14 @@ body: //div[contains(@class, "article_body")] body: //div[@id='print_facet']//div[@id='body'] author://meta[@name='DC.creator']/@content +author://span[@class="pb-byline"] +author://h3[@property='dc.creator']//a[@rel='author'] title://meta[@name='title']/@content date://div[contains(@class,'byline')]//span[contains(@class,'published')]/@title date://meta[@name="DC.date.issued"]/@content +date://span[contains(@class,"pb-timestamp")] +date://meta[@name="eomportal-lastUpdate"]/@content + strip://div[@class="relative primary-slot padding-top img-border gallery-container photo-wrapper"] strip://div[@id="wp-column six end"] strip://div[contains(@class,'hidden')] |