diff options
| -rw-r--r-- | .gitignore | 1 | ||||
| -rw-r--r-- | derstandard.at/international/asien/hongkong/stylesheet_html.xml | 25 | ||||
| -rwxr-xr-x | generate | 30 |
3 files changed, 48 insertions, 8 deletions
diff --git a/.gitignore b/.gitignore index fbd9934..1591f35 100644 --- a/.gitignore +++ b/.gitignore @@ -1,2 +1,3 @@ cookies feed.xml +*.html diff --git a/derstandard.at/international/asien/hongkong/stylesheet_html.xml b/derstandard.at/international/asien/hongkong/stylesheet_html.xml new file mode 100644 index 0000000..30842e4 --- /dev/null +++ b/derstandard.at/international/asien/hongkong/stylesheet_html.xml @@ -0,0 +1,25 @@ +<?xml version="1.0" encoding="UTF-8"?> +<xsl:stylesheet version="1.0" xmlns:xsl="http://www.w3.org/1999/XSL/Transform"> + <xsl:output method="html" encoding="utf-8" indent="yes" /> + <xsl:template match="/main"> + <xsl:text disable-output-escaping="yes"><!DOCTYPE html></xsl:text> + <head> + <title>derStandard.at - <xsl:value-of select="normalize-space(//header/h1)"/></title> + <link rel="alternate" type="application/atom+xml" href="https://grafoo.tilde.institute/transfeed/derstandard.at/international/asien/hongkong/feed.xml" /> + </head> + <body> + <xsl:for-each select="//section"> + <article> + <header> + <a> + <xsl:attribute name="href">https://www.derstandard.at<xsl:value-of select="article//a/@href"/></xsl:attribute> + <h1><xsl:value-of select="normalize-space(article//header/h1[@class='teaser-title'])"/></h1> + </a> + <p><time><xsl:value-of select="normalize-space(article//header/time/@datetime)"/></time></p> + </header> + <p><xsl:value-of select="normalize-space(article//header/p[@class='teaser-subtitle'])"/></p> + </article> + </xsl:for-each> + </body> + </xsl:template> +</xsl:stylesheet> diff --git a/generate b/generate index 0d5705d..47fb755 100755 --- a/generate +++ b/generate @@ -1,15 +1,29 @@ #!/bin/sh -test $# -ne 1 && - { - echo "Usage: ${0} <xslt-stylesheet-file>" - exit 2 - } + +usage() { + echo "Usage: ${0} <xslt-stylesheet-file> [atom | html]" + exit 2 +} + +test $# -ne 2 && usage "$0" echo "$1" | grep 'derstandard.at/international/asien/hongkong' -q && url='https://www.derstandard.at/international/asien/hongkong' # TODO: Add option to aggregate older articles using e.g. https://www.derstandard.at/international/asien/hongkong/2020/1/1 -curl -sL -b cookies "$url" | +out=$(curl -sL -b cookies "$url" | xmllint --html --xpath '//main' /dev/stdin 2>/dev/null | - xsltproc "$1" /dev/stdin | - xmllint --format /dev/stdin \ + xsltproc "$1" /dev/stdin) + +case "$2" in +atom) + printf "%s" "$out" | xmllint --format /dev/stdin \ >"$(dirname "$1")/feed.xml" + ;; +html) + printf "%s" "$out" | xmllint --format --html /dev/stdin \ + >"$(dirname "$1")/index.html" + ;; +*) + usage "$0" + ;; +esac |