aboutsummaryrefslogtreecommitdiff
path: root/references/convert-and-slurp-attachments.sh
diff options
context:
space:
mode:
Diffstat (limited to 'references/convert-and-slurp-attachments.sh')
-rwxr-xr-xreferences/convert-and-slurp-attachments.sh18
1 files changed, 18 insertions, 0 deletions
diff --git a/references/convert-and-slurp-attachments.sh b/references/convert-and-slurp-attachments.sh
new file mode 100755
index 0000000..ce7f34d
--- /dev/null
+++ b/references/convert-and-slurp-attachments.sh
@@ -0,0 +1,18 @@
+#!/bin/sh -
+
+ls | fgrep -v . |
+while read page
+do
+ base="https://trac.rpki.net"
+ path="/wiki/$(echo $page | sed s=%2F=/=g)"
+
+ # Fetch the Wiki page, extract the useful portion of the HTML, convert that into Markdown
+ curl "${base}${path}" |
+ xsltproc --html extract-wiki-content.xsl - |
+ html2markdown --no-skip-internal-links --reference-links >"$page.md"
+
+ # Fetch a ZIP file containing any attachments, clean up if result is empty or broken
+ curl "${base}/zip-attachment${path}/" >"$page.zip"
+ zipinfo "$page.zip" >/dev/null 2>&1 || rm -f "$page.zip"
+
+done