PDF Document Downloader from docs.redhat.com

README.md

Usage:

```
$ mkdir RHEL9Doc
$ cd RHEL9Doc
$ fetchdoc.sh https://docs.redhat.com/en/documentation/red_hat_enterprise_linux/9
```

Prerequirement: curl, GNU Parallel

2024-11-21: fix for docs.redhat.com update

fetchdoc.sh

#!/bin/bash

if [ -z "$1" ]; then
  echo "Usage: $0 <URL>"
  exit 1
fi

# BASE_URL 
URL="$1"
BASE_URL=$(echo "$URL" | awk -F/ '{print $1"//"$3}')

# Download index page
curl -s "$URL" | grep -oP '(?<=href=")[^"]*' | grep '/html/' | parallel -j 10 '
  RELATIVE_URL={}
  FULL_URL='"$BASE_URL"'"$RELATIVE_URL"
  FULL_URL="${FULL_URL%/}/index"
  
  PDF_URL=${FULL_URL/html/pdf}
  if [ -n "$PDF_URL" ]; then
    # Download PDF
    FILENAME=${PDF_URL#*/pdf/}
    FILENAME=${FILENAME%%/*}.pdf
    curl -s -o "$FILENAME" "$PDF_URL" 
  fi
'