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

fetchdoc.sh

#!/bin/bash

if [ -z "$1" ]; then
  echo "Usage: $0 <URL>"
  echo "URL: product document index pagehttps://docs.redhat.com/en/documentation/red_hat_enterprise_linux/9"
  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"
  
  # Find pdf link from first page
  PDF_URL=$(curl -s "$FULL_URL" | grep -oP "(?<=href=\")[^\"]*" | grep "\.pdf$")
  if [ -n "$PDF_URL" ]; then
    # Download PDF
    FILENAME=$(basename "$PDF_URL")
    curl -s -o "$FILENAME" '"$BASE_URL"'"$PDF_URL" 
  fi
'