Add a CGI/DCGI for espresso.repubblica.it - gophercgis - Collection of gopher CGI/DCGI for geomyidae
 (HTM) hg clone https://bitbucket.org/iamleot/gophercgis
 (DIR) Log
 (DIR) Files
 (DIR) Refs
 (DIR) README
 (DIR) LICENSE
       ---
 (DIR) changeset 09cbd6d2abc3e6727ea6391b887a5906d8d31bbd
 (DIR) parent 7f79d08fcdd0e6dd9e798c783d781432f698ded7
 (HTM) Author: Leonardo Taccari <iamleot@gmail.com>
       Date:   Thu, 30 Aug 2018 00:58:04 
       
       Add a CGI/DCGI for espresso.repubblica.it
       
       Diffstat:
        espresso/article.cgi |  44 ++++++++++++++++++++++++++++++++++++++++++++
        espresso/feed.dcgi   |  45 +++++++++++++++++++++++++++++++++++++++++++++
        2 files changed, 89 insertions(+), 0 deletions(-)
       ---
       diff -r 7f79d08fcdd0 -r 09cbd6d2abc3 espresso/article.cgi
       --- /dev/null   Thu Jan 01 00:00:00 1970 +0000
       +++ b/espresso/article.cgi      Thu Aug 30 00:58:04 2018 +0200
       @@ -0,0 +1,44 @@
       +#!/bin/sh
       +
       +
       +#
       +# Extract article content
       +#
       +extract_article()
       +{
       +
       +       awk '
       +       /<article class="main-article/,/<\/article>/ {
       +               if (($0 ~ /<aside class="tags-list">/) || ($0 ~ /<footer /)) {
       +                       exit
       +               }
       +
       +               print
       +       }
       +       '
       +}
       +
       +
       +#
       +# Render HTML as text
       +#
       +html_to_text()
       +{
       +       # Nonexistent proxy to block HTTP requests
       +       export http_proxy="http://localhost:31283128"
       +
       +       browser="/usr/pkg/bin/w3m"
       +
       +       browser_options="-dump -T text/html -no-cookie -cols 72"
       +       browser_options="${browser_options} -o display_link=false"
       +       browser_options="${browser_options} -o display_link_number=false"
       +       browser_options="${browser_options} -o display_image=false"
       +
       +       env LANG=en_US.UTF-8 ${browser} ${browser_options}
       +}
       +
       +
       +url="$2"
       +/usr/pkg/bin/curl -sL "${url}" |
       +    extract_article |
       +    html_to_text
       diff -r 7f79d08fcdd0 -r 09cbd6d2abc3 espresso/feed.dcgi
       --- /dev/null   Thu Jan 01 00:00:00 1970 +0000
       +++ b/espresso/feed.dcgi        Thu Aug 30 00:58:04 2018 +0200
       @@ -0,0 +1,45 @@
       +#!/bin/sh
       +
       +
       +ARTICLE_CGI="/cgi/espresso/article.cgi"
       +
       +
       +echo ""
       +echo "l'Espresso"
       +echo ""
       +
       +url="http://espresso.repubblica.it/rss?sezione=espresso"
       +/usr/pkg/bin/curl -gs "${url}" |
       +awk '
       +/<rss/,/<lastBuildDate>/ {
       +       next    # ignore all non-item-s
       +}
       +
       +/<title/ {
       +       gsub("</?title>", "")
       +       gsub(/^[[:space:]]+/, "")
       +       gsub(/[[:space:]]+$/, "")
       +       title = $0
       +}
       +
       +/<link/ {
       +       gsub("</?link>", "")
       +       gsub(/^[[:space:]]+/, "")
       +       gsub(/[[:space:]]+$/, "")
       +       link = $0
       +}
       +
       +title && link {
       +       gsub("\\|", "\\|", title)
       +       gsub("\\|", "\\|", link)
       +       gsub("\\&quot;", "\"", title)
       +
       +       if (title !~ /^\[\$\] /) {
       +               printf("[0|%s|'"${ARTICLE_CGI}?"'%s|server|port]\n", title, link)
       +       }
       +
       +       title = link = ""
       +}
       +'
       +
       +echo ""