You need to enable JavaScript to run this app.
优惠活动
大模型
产品
解决方案
定价
更多

Docker容器中启动FSCrawler+Elasticsearch/Kibana遇NoSuchElementException错误

问题:Docker部署FSCrawler、Elasticsearch和Kibana时,FSCrawler抛出NoSuchElementException异常

启动docker compose up后,FSCrawler容器输出以下异常:

fscrawler                  | Exception in thread "main" java.util.NoSuchElementException
fscrawler                  |    at java.base/java.util.Scanner.throwFor(Scanner.java:937)
fscrawler                  |    at java.base/java.util.Scanner.next(Scanner.java:1478)
fscrawler                  |    at fr.pilato.elasticsearch.crawler.fs.cli.FsCrawlerCli.main(FsCrawlerCli.java:254)

当前配置文件

docker-compose.yml

---
version: "2.2"

services:
  setup:
    image: docker.elastic.co/elasticsearch/elasticsearch:${STACK_VERSION}
    volumes:
      - certs:/usr/share/elasticsearch/config/certs
    user: "0"
    command: >
      bash -c '
        if [ x${ELASTIC_PASSWORD} == x ]; then
          echo "Set the ELASTIC_PASSWORD environment variable in the .env file";
          exit 1;
        elif [ x${KIBANA_PASSWORD} == x ]; then
          echo "Set the KIBANA_PASSWORD environment variable in the .env file";
          exit 1;
        fi;
        if [ ! -f certs/ca.zip ]; then
          echo "Creating CA";
          bin/elasticsearch-certutil ca --silent --pem -out config/certs/ca.zip;
          unzip config/certs/ca.zip -d config/certs;
        fi;
        if [ ! -f certs/certs.zip ]; then
          echo "Creating certs";
          echo -ne \
          "instances:\n"\
          "  - name: elasticsearch\n"\
          "    dns:\n"\
          "      - elasticsearch\n"\
          "      - localhost\n"\
          "    ip:\n"\
          "      - 127.0.0.1\n"\
          > config/certs/instances.yml;
          bin/elasticsearch-certutil cert --silent --pem -out config/certs/certs.zip --in config/certs/instances.yml --ca-cert config/certs/ca/ca.crt --ca-key config/certs/ca/ca.key;
          unzip config/certs/certs.zip -d config/certs;
        fi;
        echo "Setting file permissions"
        chown -R root:root config/certs;
        find . -type d -exec chmod 750 \{\} \;;
        find . -type f -exec chmod 640 \{\} \;;
        echo "Waiting for Elasticsearch availability";
        until curl -s --cacert config/certs/ca/ca.crt https://elasticsearch:9200 | grep -q "missing authentication credentials"; do sleep 30; done;
        echo "Setting kibana_system password";
        until curl -s -X POST --cacert config/certs/ca/ca.crt -u elastic:${ELASTIC_PASSWORD} -H "Content-Type: application/json" https://elasticsearch:9200/_security/user/kibana_system/_password -d "{\"password\":\"${KIBANA_PASSWORD}\"}" | grep -q "^{}"; do sleep 10; done;
        echo "All done!";
      '
    healthcheck:
      test: ["CMD-SHELL", "[ -f config/certs/elasticsearch/elasticsearch.crt ]"]
      interval: 1s
      timeout: 5s
      retries: 120

  elasticsearch:
    depends_on:
      setup:
        condition: service_healthy
    image: docker.elastic.co/elasticsearch/elasticsearch:${STACK_VERSION}
    volumes:
      - certs:/usr/share/elasticsearch/config/certs
      - esdata:/usr/share/elasticsearch/data
    ports:
      - ${ES_PORT}:9200
    environment:
      - node.name=elasticsearch
      - cluster.name=${CLUSTER_NAME}
      - cluster.initial_master_nodes=elasticsearch
      - ELASTIC_PASSWORD=${ELASTIC_PASSWORD}
      - bootstrap.memory_lock=true
      - xpack.security.enabled=true
      - xpack.security.http.ssl.enabled=true
      - xpack.security.http.ssl.key=certs/elasticsearch/elasticsearch.key
      - xpack.security.http.ssl.certificate=certs/elasticsearch/elasticsearch.crt
      - xpack.security.http.ssl.certificate_authorities=certs/ca/ca.crt
      - xpack.security.http.ssl.verification_mode=certificate
      - xpack.security.transport.ssl.enabled=true
      - xpack.security.transport.ssl.key=certs/elasticsearch/elasticsearch.key
      - xpack.security.transport.ssl.certificate=certs/elasticsearch/elasticsearch.crt
      - xpack.security.transport.ssl.certificate_authorities=certs/ca/ca.crt
      - xpack.security.transport.ssl.verification_mode=certificate
      - xpack.license.self_generated.type=${LICENSE}
    mem_limit: ${MEM_LIMIT}
    ulimits:
      memlock:
        soft: -1
        hard: -1
    healthcheck:
      test:
        [
          "CMD-SHELL",
          "curl -s --cacert config/certs/ca/ca.crt https://localhost:9200 | grep -q 'missing authentication credentials'",
        ]
      interval: 10s
      timeout: 10s
      retries: 120

  kibana:
    depends_on:
      elasticsearch:
        condition: service_healthy
    image: docker.elastic.co/kibana/kibana:${STACK_VERSION}
    volumes:
      - certs:/usr/share/kibana/config/certs
      - kibanadata:/usr/share/kibana/data
    ports:
      - ${KIBANA_PORT}:5601
    environment:
      - SERVERNAME=kibana
      - ELASTICSEARCH_HOSTS=https://elasticsearch:9200
      - ELASTICSEARCH_USERNAME=kibana_system
      - ELASTICSEARCH_PASSWORD=${KIBANA_PASSWORD}
      - ELASTICSEARCH_SSL_CERTIFICATEAUTHORITIES=config/certs/ca/ca.crt
      - ENTERPRISESEARCH_HOST=http://enterprisesearch:${ENTERPRISE_SEARCH_PORT}
    mem_limit: ${MEM_LIMIT}
    healthcheck:
      test:
        [
          "CMD-SHELL",
          "curl -s -I http://localhost:5601 | grep -q 'HTTP/1.1 302 Found'",
        ]
      interval: 10s
      timeout: 10s
      retries: 120

  # FSCrawler
  fscrawler:
    image: dadoonet/fscrawler:$FSCRAWLER_VERSION
    container_name: fscrawler
    restart: always
    volumes:
      - ../../test-documents/src/main/resources/documents/:/tmp/es:ro
      - ${PWD}/config:/root/.fscrawler
      - ${PWD}/logs:/usr/share/fscrawler/logs
    depends_on:
      elasticsearch:
        condition: service_healthy
    ports:
      - ${FSCRAWLER_PORT}:8080
    command: fscrawler idx --restart --rest

volumes:
  certs:
    driver: local
  esdata:
    driver: local
  kibanadata:
    driver: local

.env

# FSCrawler Settings

FSCRAWLER_VERSION=2.10-SNAPSHOT
FSCRAWLER_PORT=8080

# Password for the 'elastic' user (at least 6 characters)

ELASTIC_PASSWORD=changeme

# Password for the 'kibana_system' user (at least 6 characters)

KIBANA_PASSWORD=changeme

# Version of Elastic products

STACK_VERSION=8.6.2

# Set the cluster name

CLUSTER_NAME=docker-cluster

# Set to 'basic' or 'trial' to automatically start the 30-day trial

#LICENSE=basic
LICENSE=trial

# Port to expose Elasticsearch HTTP API to the host

ES_PORT=9200

# Port to expose Kibana to the host

KIBANA_PORT=5601

# Enterprise Search settings

ENTERPRISE_SEARCH_PORT=3002

# Increase or decrease based on the available host memory (in bytes)

MEM_LIMIT=1073741824

# Project namespace (defaults to the current folder name if not set)

COMPOSE_PROJECT_NAME=fscrawler

原因分析

这个异常是因为FSCrawler启动时尝试从交互式控制台读取Elasticsearch的认证信息(如用户名、密码),但Docker容器默认以非交互式模式运行,没有输入源,导致Scanner类抛出NoSuchElementException。

解决方案

1. 提前生成FSCrawler配置文件

在本地运行交互式容器,引导生成包含Elasticsearch认证和SSL配置的文件:

docker run -it -v ${PWD}/config:/root/.fscrawler dadoonet/fscrawler:$FSCRAWLER_VERSION fscrawler idx

按照提示输入以下信息:

  • Elasticsearch地址:https://elasticsearch:9200
  • 用户名:elastic
  • 密码:changeme
  • 是否启用SSL:Y
  • CA证书路径:后续挂载后设置为/usr/share/fscrawler/certs/ca/ca.crt

生成的配置文件会保存在本地config/idx目录下。

2. 修改FSCrawler容器配置

在docker-compose.yml的FSCrawler服务中添加certs卷挂载,以便容器访问Elasticsearch的CA证书:

fscrawler:
  image: dadoonet/fscrawler:$FSCRAWLER_VERSION
  container_name: fscrawler
  restart: always
  volumes:
    - ../../test-documents/src/main/resources/documents/:/tmp/es:ro
    - ${PWD}/config:/root/.fscrawler
    - ${PWD}/logs:/usr/share/fscrawler/logs
    - certs:/usr/share/fscrawler/certs  # 添加CA证书卷挂载
  depends_on:
    elasticsearch:
      condition: service_healthy
  ports:
    - ${FSCRAWLER_PORT}:8080
  command: fscrawler idx --restart --rest

3. 完善FSCrawler配置文件

编辑config/idx/_settings.json,补充SSL认证相关配置:

{
  "name": "idx",
  "fs": {
    "url": "/tmp/es",
    "update_rate": "15m",
    "remove_deleted": true,
    "index_content": true
  },
  "elasticsearch": {
    "nodes": [
      {
        "url": "https://elasticsearch:9200"
      }
    ],
    "username": "elastic",
    "password": "changeme",
    "ssl": {
      "enabled": true,
      "certificate_authorities": ["/usr/share/fscrawler/certs/ca/ca.crt"]
    }
  },
  "rest": {
    "enabled": true,
    "port": 8080
  }
}

4. 重新启动容器

执行docker compose up -d,FSCrawler会读取配置文件中的信息,无需交互式输入即可连接Elasticsearch,解决异常问题。

内容的提问来源于stack exchange,提问作者lenchester

相关产品推荐
方舟 Agent Plan

超全模态模型 × Harness 升级,最新支持 Deepseek-V4.1-Flash、GLM-5.3 系列、Doubao-Seedream-5.0-pro、Kimi-K3 (部分), 限时 9.9 元起

最近更新时间:2026.07.24 14:07:01