book-scraping-fzf

#!/bin/bash

# Created by IamJony
# My github: https://github.com/IamJony
# DESCRIPTION: A Bash script to download books using libraries shadows
# Date: 2024-15-08 
# Version: 1.3.3-1 

version_number="1.3.3-1"

# Local version
version_info() {
    printf "%s\n" "$version_number"
    exit 0
}

# Cheack update
update_script() {
    update="$(curl -s -A "$agent" "https://raw.githubusercontent.com/IamJony/book-scraping/main/book-scraping-fzf")" || die "Connection error"
    update="$(printf '%s\n' "$update" | diff -u "$0" -)"
    if [ -z "$update" ]; then
		echo -e $BBlue''
        printf "Script is up to date :)\n"
        echo -e $White''
    else
        if printf '%s\n' "$update" | patch "$0" -; then
			echo -e $BGreen''
            printf "Script has been updated\n"
			echo -e $White''
        else
			echo -e $BRed''
            die "Can't update for some reason!"
			echo -e $White''
        fi
    fi
    exit 0
}


 anna='https://annas-archive.org/search?q='




# User Agent Random
numRandom=$((RANDOM % 59))
agent=$(jq --raw-output ".[${numRandom}]" user-agent.json 2>/dev/null)

if [[ -z "$agent" ]]; then
    agent="Mozilla/5.0 (Windows NT 6.1; Win64; rv:109.0) Gecko/20100101 Firefox/109.0"
fi



# Set color
#
White='\e[0;37m'
Black='\e[0;30m'        
Green='\e[0;32m'        
Yellow='\e[0;33m'     
Blue='\e[0;34m' 
Red='\e[0;31m'          
Purple='\e[0;35m'     
Cyan='\e[0;36m'       
     
BBlack='\e[1;30m'       # Black
BRed='\e[1;31m'         # Red
BGreen='\e[1;32m'       # Green
BYellow='\e[1;33m'      # Yellow
BBlue='\e[1;34m'        # Blue
BPurple='\e[1;35m'      # Purple
BCyan='\e[1;36m'        # Cyan
BWhite='\e[1;37m'       # White

# Directory
dir="$HOME/.bookScraping"
rm -dfr $dir 2>/dev/null &
mkdir $dir/ 2>/dev/null &


# scraping anna site
scraping_fast() {
	
	title_book=$(sed -n 's/.*<h3[^>]*class="[^"]*truncate[^"]*text-xl[^"]*font-bold"[^>]*>\(.*\)<\/h3>.*/\1/p' $dir/.html_anna > $dir/.title_book_anna)
	book_autor=$(sed -n 's/.*<div[^>]*class="[^"]*truncate[^"]*italic"[^>]*>\(.*\)<\/div>.*/\1/p' $dir/.html_anna > $dir/.book_autor_anna)
	format_book=$(sed -n 's/.*<div[^>]*class="[^"]*text-gray-500[^"]*">\([^<]*\)<\/div>.*/\1/p' $dir/.html_anna > $dir/.format_book_anna)
	link_pag=$(sed -n 's/^.*<a[^>]*href="\([^"]*\)".*$/\1/p' $dir/.html_anna | sed -n '/md5/p' > $dir/.link_page_ana)
	link_page=$(cat $dir/.link_page_ana | sed '/\/md5\/${item.md5}/d' > $dir/.link_page_anna)
	md5=$(cat $dir/.link_page_anna)

	file1="$dir/.title_book_anna"
	file2="$dir/.book_autor_anna"
	file3="$dir/.format_book_anna"
	file4="$dir/.link_page_anna"

# Counter
line_num=1

	
while true; do

    # Print the first line of the files
    echo "$(sed -n "${line_num}p" "${file1}") | $(sed -n "${line_num}p" "${file2}") | $(sed -n "${line_num}p" "${file3}")"

    # Increment the line number
    line_num=$((line_num+1))
    
    # Check if the end of the file has been reached #1
    if [[ $(sed -n "$=" "${file1}") -lt $line_num ]]; then
        break
    fi
done
	
}


# User input

user() {

    echo -e $BYellow''
    read -p "Enter the name of the book to search: " input &&
    input=${input// /+}
    wget --user-agent "$agent" -O $dir/.html_anna -q "${anna}${input}${parametros}"

    # Fail
    if [ $? -ne 0 ]; then
    	echo -e "${Red}The command failed." 
    	echo ""
    	echo "wget --user-agent \"$agent\" \"${anna}${input}${parametros}\""
    	echo ""
    	http_status=$(wget --spider --server-response --user-agent "$agent" "${anna}${input}${parametros}" | 2>&1)
    	echo "$http_status"
    	exit 1
    fi

    scraping_fast > $dir/result
    echo -e $White''
}


parametros=""

while [[ $# -gt 0 ]]; do
    case $1 in
        --version)
            version_info
            ;;
        --update)
            update_script
            ;;
        --help | -h)
            cat <<- _EOF_
Available options:
  --version         Show version information
  --update          Update the script
  --help, -h        Show this help message
  --external_download  Download external resources
  --lib             Prioritize book searches on libgen 
  --es              Search in Spanish
  --en              Search in English
  --pdf             Search for PDF files
  --epub            Search for EPUB files
  --author           Specify the author
_EOF_
            exit 0
            ;;
        --external_download)
            parametros="${parametros}&acc=external_download"
            ;;
        --lib)
            parametros="${parametros}&src=lgli"
            ;;
        --es)
            parametros="${parametros}&sort=&lang=es"
            ;;
        --en)
            parametros="${parametros}&sort=&lang=en"
            ;;
        --pdf)
            parametros="${parametros}&ext=pdf"
            ;;
        --epub)
            parametros="${parametros}&ext=epub"
            ;;
        --author)
            if [[ -n "$2" && "$2" != --* ]]; then
                autor=$(echo "$2" | sed 's/ /+/g')
                parametros="${parametros}&termtype_1=author&termval_1=${autor}"
                shift
            else
                echo "Error: A value for --author was expected"
                exit 1
            fi
            ;;
        *)
            echo "Optión no found: $1"
            ;;
    esac
    shift
done

user


# FZF
export FZF_DEFAULT_OPTS="--bind='ctrl-x:execute(exit 0)+abort'"
	

if [ ! -s $dir/.title_book_anna ]; then
  echo -e $BRed'No results found'
  sleep 2
  clear
  exit 1
fi

# Read the file and save each line to an array
readarray -t LINES < $dir/result

# Check if the file is empty
if [ ${#LINES[@]} -eq 0 ]; then
  echo "No results found."
  exit 1
fi

OPTIONS=()
for i in "${!LINES[@]}"; do
line_number=$((i+1))
  OPTIONS+=("$line_number ${LINES[$i]}")

done

# Run FZF and get the user's selection
OPTION=$(printf '%s\n' "${OPTIONS[@]}" | fzf | awk '{print $1}')

# Validate the user's selection
if [[ "$OPTION" =~ ^[0-9]+$ && "$OPTION" -ge 0 && "$OPTION" -lt "${#LINES[@]}" ]]; then
  echo ""
  namedocument=$(echo "$OPTION: ${LINES[$OPTION-1]}" | sed -n 's/^[^:]*: *\(.*[^ ]\) *|[^|]*|.*/\1/p' | sed 's/[^[:alnum:][:space:]]//g')
  echo -e $BGreen''
  echo "Ha seleccionado la opción $((OPTION)): ${LINES[$OPTION-1]}"
  echo -e $White''
  
  # get md5 of the book selected by the user
  ANOTHER_FILE_LINE=$(sed -n "$((OPTION))p" $dir/.link_page_anna)
  
  # get downloads url
  
 curl -s -A "$agent" "https://annas-archive.org$ANOTHER_FILE_LINE" \
    | sed -n '/class="js-download-link"/p' \
    | grep -o "href='[^']*'" \
    | sed -e "s/href='\([^']*\)'/\1/" > "$dir/.download_link"

if [[ ! -s "$dir/.download_link" ]]; then
echo -e $BRed 'Failed to get download link'
exit 1
 fi

# Downloads link dowsnt start automatically 
echo -e ''

echo -e $BYellow'If the download doesnt start automatically, you can open this link in your browser'

cat $dir/.download_link | grep /slow | sed 's|^|https://annas-archive.org|' 2>/dev/null &
cat $dir/.download_link | grep ht 2>/dev/null &
cat $dir/.download_link | sed -n '/\.onion/p' 2>/dev/null &

echo -e $White''
echo ""

# Downloads directory  
dirdownload=~/Documents

if [[ -d $dirdownload ]]; 
then
echo ""
else 
	mkdir $dirdownload 
fi

readarray -t urls < "$dir/.download_link"

for url in "${urls[@]}"; do
    filename=$(basename "$url")
    shortname=$(basename "$filename" | cut -c 1-50)
    extension=$(echo "$filename" | sed 's/.*\.//')
    
    if [[ $filename =~ \.(pdf|epub|txt|zip|rar|djvu|fb2|mobi|doc|docx|fb2|cbz|rtf|azw3|azw|cbr)$ ]]; then
        if wget -nc -P "$dir/" --read-timeout=10 "$url"; then
            echo -e "$BGreen'Download finished: $dirdownload/$namedocument.$extension'"
            mv "$dir"/*."$extension" "$dirdownload/"
            cd "$dirdownload/" && mv *."$extension" "$shortname.$extension" && mv "$shortname.$extension" "$namedocument.$extension"
            break
        else
            echo "Failed to download: $url"  
        fi
     
       
     elif [[ $url == *libgen.li* ]]; then
     libgenlink=$(cat $dir/.download_link | sed -n '/^http*:\/\/libgen\.[^\/]*/p')
	 comandoo=$(wget --user-agent "$agent" -q -O - "$url" | sed -n 's/.*<a[^>]*href="\([^"]*get\.php[^"]*\)".*/\1/p')
	 
	 if [ -z "$comandoo" ]; then
    echo -e $BRed' 1 Error in libgenlink The link could not be extracted to start the automatic download.'
    break
fi
	 
	 echo ""
	 echo  -e $BYellow'An attempt is being made to download automatically.'
	 echo -e $White''
	
	 wget  -P "$dirdownload" --user-agent "$agent" --content-disposition --max-redirect=30 "https://libgen.li/""$comandoo"
	 
	 if [ $? -ne 0 ]; then
    echo -e $BRed 'Error could not be downloaded automatically'
    exit 1
    else
    break
fi
			
			
    fi
done
exit 1
fi