1
0
Files
ollama/rag/download.sh
2025-08-27 00:20:10 +08:00

68 lines
2.5 KiB
Bash
Executable File
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

#!/bin/bash
# shellcheck disable=SC1091,SC2181,SC2000
command -v curl >/dev/null 2>&1 || { echo >&2 "Ошибка: curl не установлен"; exit 1; }
command -v jq >/dev/null 2>&1 || { echo >&2 "Ошибка: jq не установлен"; exit 1; }
if [ $# -lt 1 ]; then
echo >&2 "Ошибка: не указан ID страницы для загрузки"
echo "Использование: $0 <pageId1> [<pageId2>...]"
exit 1
fi
[ ! -f ../.env ] && cp ../.env.example ../.env
source ../.env
[ -z "$CONF_URL" ] && { echo >&2 "Ошибка: CONF_URL не указан в файле .env"; exit 1; }
[ -z "$CONF_USERNAME" ] && { echo >&2 "Ошибка: CONF_USERNAME не указан в файле .env"; exit 1; }
[ -z "$CONF_PASSWORD" ] && { echo >&2 "Ошибка: CONF_PASSWORD не указан в файле .env"; exit 1; }
OUTPUT_PATH="./input_html"
[ ! -d "$OUTPUT_PATH" ] && mkdir -p "$OUTPUT_PATH"
for PAGE_ID in "$@"; do
API_ENDPOINT="${CONF_URL}/rest/api/content/${PAGE_ID}?expand=body.view,children.page"
echo
echo "Загрузка: $API_ENDPOINT"
RESPONSE=$(curl -s -u "$CONF_USERNAME:$CONF_PASSWORD" -H "Accept: application/json" "${API_ENDPOINT}")
if [ $? -ne 0 ]; then
echo "$RESPONSE"
exit 1
fi
ERROR_MESSAGE=$(echo "$RESPONSE" | jq -r '.message' 2>/dev/null)
if [ -n "$ERROR_MESSAGE" ] && [ "$ERROR_MESSAGE" != "null" ]; then
echo "$RESPONSE"
exit 1
fi
TITLE=$(echo "$RESPONSE" | jq -r .title)
CONTENT=$(echo "$RESPONSE" | jq -r .body.view.value)
if [ -z "$CONTENT" ]; then
echo "Пустая страница, пропущено"
exit
fi
TITLE_ESC="${TITLE//\//_}"
FILENAME="$TITLE_ESC.html"
if [ "$(echo "$FILENAME" | wc -c)" -gt 255 ]; then # измерение по байтам, а не длине
FILENAME="${TITLE_ESC:0:120}.html"
fi
HTML_FILEPATH="$OUTPUT_PATH/$FILENAME"
CONTENT=${CONTENT//href=\"\//href=\"$CONF_URL}
CONTENT=${CONTENT//src=\"\//src=\"$CONF_URL}
URL="$CONF_URL/pages/viewpage.action?pageId=$PAGE_ID"
echo -e "@@$URL@@\n<br><html><body>Исходная страница: <a href=\"$URL\">$URL</a><br><br><h1>$TITLE</h1>$CONTENT</body></html>" > "$HTML_FILEPATH"
echo "Сохранено: $OUTPUT_PATH/$TITLE.html"
CHILD_IDS=$(echo "$RESPONSE" | jq -r '.children.page.results[]?.id' 2>/dev/null)
for CHILD_ID in $CHILD_IDS; do
echo "Переход к дочерней странице: $PAGE_ID => $CHILD_ID"
$0 "$CHILD_ID"
done
done