Add an extractor for il manifesto - 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 57112e2a27fe6d67a2a57db055467df4fa4de6e9
 (DIR) parent 8c321014eb1efc17e1cdd79c13fa791305c64868
 (HTM) Author: Leonardo Taccari <iamleot@gmail.com>
       Date:   Sat,  8 Dec 2018 21:42:41 
       
       Add an extractor for il manifesto
       
       Diffstat:
        ilmanifesto/article.cgi |  36 ++++++++++++++++++++++++++++++++++++
        ilmanifesto/feed.dcgi   |  16 ++++++++++++++++
        2 files changed, 52 insertions(+), 0 deletions(-)
       ---
       diff -r 8c321014eb1e -r 57112e2a27fe ilmanifesto/article.cgi
       --- /dev/null   Thu Jan 01 00:00:00 1970 +0000
       +++ b/ilmanifesto/article.cgi   Sat Dec 08 21:42:41 2018 +0100
       @@ -0,0 +1,36 @@
       +#!/bin/sh
       +
       +. ../common/config.sh
       +. ../common/html.sh
       +
       +#
       +# Extract article content
       +#
       +extract_article()
       +{
       +
       +       awk '
       +       /       <div class="article-header"/,/  <\/div>/ {
       +               # Remove the article section
       +               gsub(/<span itemprop="articleSection" .*<\/a><\/span>/, "")
       +
       +               print
       +       }
       +
       +       /<div class="entry-content" itemprop="articleBody">/,/<div class="entry-tools">/ {
       +               # Remove all img-s
       +               gsub(/<img [^>]+\/?>/, "")
       +
       +               print
       +       }
       +       '
       +}
       +
       +
       +url="$2"
       +curl -A Googlebot-News -Lgs -- "${url}" |
       +    extract_article |
       +    html_to_text
       +
       +echo ""
       +echo "URL: <${url}>"
       diff -r 8c321014eb1e -r 57112e2a27fe ilmanifesto/feed.dcgi
       --- /dev/null   Thu Jan 01 00:00:00 1970 +0000
       +++ b/ilmanifesto/feed.dcgi     Sat Dec 08 21:42:41 2018 +0100
       @@ -0,0 +1,16 @@
       +#!/bin/sh
       +
       +. ../common/config.sh
       +. ../common/feed.sh
       +
       +FEED_AUTHOR=yes
       +FEED_DATE=yes
       +ARTICLE_CGI="${CGI_BASEDIR}/ilmanifesto/article.cgi"
       +
       +echo ""
       +echo "il manifesto"
       +echo ""
       +
       +url="https://ilmanifesto.it/feed/"
       +curl -Lgs -- "${url}" |
       +feed_to_gph