NaseMS.cz photos backup

nasems-download.zsh

#!/usr/bin/env zsh
set -euo pipefail

BASE_URL="https://nasems.cz"
GALLERY_URL="${BASE_URL}/prihlaseno/fotogalerie"

OUT_DIR="${1:-nasems-data}"
PHOTOS_DIR="${OUT_DIR}/fotky"

mkdir -p "$OUT_DIR" "$PHOTOS_DIR"

command -v curl >/dev/null || { echo "Chybí curl"; exit 1; }
command -v jq >/dev/null || { echo "Chybí jq. Nainstaluj: sudo apt install jq"; exit 1; }
command -v file >/dev/null || { echo "Chybí file"; exit 1; }

if [[ -z "${NASEMS_SID:-}" ]]; then
  echo "Chybí env proměnná NASEMS_SID"
  echo "Použij:"
  echo "  export NASEMS_SID='hodnota_cookie_bez___Host-SID='"
  exit 1
fi

COMMON_HEADERS=(
  -H "Host: nasems.cz"
  -H "Accept-Language: en-US,en;q=0.9,cs-CZ;q=0.8,cs;q=0.7"
  -H "Cache-Control: no-cache"
  -H "Pragma: no-cache"
  -H "User-Agent: Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/149.0.0.0 Safari/537.36"
  -H "Cookie: __Host-SID=${NASEMS_SID}"
)

IMAGE_HEADERS=(
  -H "Host: nasems.cz"
  -H "Accept: image/avif,image/webp,image/apng,image/svg+xml,image/*,*/*;q=0.8"
  -H "Accept-Language: en-US,en;q=0.9,cs-CZ;q=0.8,cs;q=0.7"
  -H "Cache-Control: no-cache"
  -H "Pragma: no-cache"
  -H "Sec-Fetch-Dest: image"
  -H "Sec-Fetch-Mode: no-cors"
  -H "Sec-Fetch-Site: same-origin"
  -H "User-Agent: Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/149.0.0.0 Safari/537.36"
  -H "Cookie: __Host-SID=${NASEMS_SID}"
)

sanitize_dirname() {
  local name="$1"

  echo "$name" \
    | sed -E 's/<[^>]+>//g' \
    | sed -E 's/&nbsp;/ /g; s/&amp;/\&/g; s/&quot;/"/g; s/&#039;/'\''/g' \
    | tr '/\\:*?"<>|' '-' \
    | sed -E 's/[[:space:]]+/ /g; s/^ //; s/ $//' \
    | cut -c 1-120
}

extract_gallery_title() {
  local json_file="$1"

  jq -r '.result // empty' "$json_file" \
    | grep -oE "<label>[^<]+</label>" \
    | head -n 1 \
    | sed -E 's#</?label>##g' \
    | sed -E 's/^[[:space:]]+//; s/[[:space:]]+$//' || true
}

extract_fullsize_urls() {
  local json_file="$1"

  jq -r '.result // empty' "$json_file" \
    | grep -oE '<a[^>]+href="https://nasems\.cz/fotografie/[A-Za-z0-9]+"' \
    | grep -oE 'https://nasems\.cz/fotografie/[A-Za-z0-9]+' \
    | sort \
    | uniq || true
}

download_photo() {
  local photo_url="$1"
  local tmp="$2"

  curl -f -L --compressed \
    "$photo_url" \
    "${IMAGE_HEADERS[@]}" \
    -o "$tmp"

  local mime
  local ext

  mime="$(file --mime-type -b "$tmp")"

  case "$mime" in
    image/jpeg) ext="jpg" ;;
    image/png)  ext="png" ;;
    image/webp) ext="webp" ;;
    image/gif)  ext="gif" ;;
    *)          ext="unknown" ;;
  esac

  mv "$tmp" "${tmp}.${ext}"
}

echo "1) Stahuji hlavní stránku fotogalerie..."

curl -f -L --compressed \
  "$GALLERY_URL" \
  "${COMMON_HEADERS[@]}" \
  -H "Accept: text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8" \
  -o "${OUT_DIR}/fotogalerie.html"

echo "2) Vytahuji ID galerií..."

: > "${OUT_DIR}/slozky.txt"

grep -Eo "data-slozka=['\"][0-9]+['\"]" "${OUT_DIR}/fotogalerie.html" \
  | grep -Eo '[0-9]+' \
  >> "${OUT_DIR}/slozky.txt" || true

grep -Eo "slozka['\"]?[=: ]+['\"]?[0-9]+" "${OUT_DIR}/fotogalerie.html" \
  | grep -Eo '[0-9]+' \
  >> "${OUT_DIR}/slozky.txt" || true

sort -n "${OUT_DIR}/slozky.txt" | uniq > "${OUT_DIR}/slozky.tmp"
mv "${OUT_DIR}/slozky.tmp" "${OUT_DIR}/slozky.txt"

SLOZKY_COUNT="$(wc -l < "${OUT_DIR}/slozky.txt" | tr -d ' ')"
echo "Nalezeno galerií: ${SLOZKY_COUNT}"

if [[ "$SLOZKY_COUNT" == "0" ]]; then
  echo "Nenalezeny žádné galerie."
  grep -oE '.{0,80}slozka.{0,80}' "${OUT_DIR}/fotogalerie.html" | head -n 10 || true
  exit 1
fi

echo "3) Stahuji detaily galerií a fotky..."

while IFS= read -r SLOZKA_ID || [[ -n "$SLOZKA_ID" ]]; do
  [[ -z "$SLOZKA_ID" ]] && continue

  JSON_FILE="${OUT_DIR}/slozka-${SLOZKA_ID}.json"

  echo
  echo "Galerie ${SLOZKA_ID}: načítám detail"

  curl -f -L --compressed \
    "$GALLERY_URL" \
    "${COMMON_HEADERS[@]}" \
    -H "Accept: */*" \
    -H "Content-Type: application/x-www-form-urlencoded; charset=UTF-8" \
    -H "Origin: ${BASE_URL}" \
    -H "Referer: ${GALLERY_URL}" \
    -H "X-Requested-With: XMLHttpRequest" \
    --data-urlencode "ajax=ajax" \
    --data-urlencode "what=fotogalerie" \
    --data-urlencode "action=load_html_fotogalerie_slozka" \
    --data-urlencode "slozka=${SLOZKA_ID}" \
    -o "$JSON_FILE"

  TITLE="$(extract_gallery_title "$JSON_FILE")"

  if [[ -z "$TITLE" ]]; then
    TITLE="galerie-${SLOZKA_ID}"
  fi

  SAFE_TITLE="$(sanitize_dirname "$TITLE")"

  if [[ -z "$SAFE_TITLE" ]]; then
    SAFE_TITLE="galerie-${SLOZKA_ID}"
  fi

  GALLERY_DIR="${PHOTOS_DIR}/${SLOZKA_ID} - ${SAFE_TITLE}"
  mkdir -p "$GALLERY_DIR"

  URLS_FILE="${OUT_DIR}/fotky-${SLOZKA_ID}.txt"
  extract_fullsize_urls "$JSON_FILE" > "$URLS_FILE"

  PHOTOS_COUNT="$(wc -l < "$URLS_FILE" | tr -d ' ')"

  echo "Název: ${TITLE}"
  echo "Fotky: ${PHOTOS_COUNT}"
  echo "Složka: ${GALLERY_DIR}"

  if [[ "$PHOTOS_COUNT" == "0" ]]; then
    echo "VAROVÁNÍ: žádné fullsize fotky nenalezeny"
    continue
  fi

  i=1

  while IFS= read -r PHOTO_URL || [[ -n "$PHOTO_URL" ]]; do
    [[ -z "$PHOTO_URL" ]] && continue

    tmp="${GALLERY_DIR}/$(printf "%04d-image" "$i")"

    echo "  Fotka $(printf "%04d" "$i")"

    download_photo "$PHOTO_URL" "$tmp"

    ((i++))
  done < "$URLS_FILE"

done < "${OUT_DIR}/slozky.txt"

echo
echo "Hotovo."
echo "Data:  ${OUT_DIR}"
echo "Fotky: ${PHOTOS_DIR}"