我正在使用Storm搜寻器1.10。我也试图包括搜寻器来搜寻文件。我根据一些研究添加了tika解析器，但是爬虫没有抓取 .pdf 网址。当我应用tika函数时，html页面中的新行（\ n）正在爬网，当我签入kibana时看起来很奇怪。正则表达式中的文档没有任何限制。我正在共享我的配置。在这种仅抓取文档的情况下，任何人都可以帮助我。
**es-crawler.flux:**
name: "crawler"
includes:
- resource: true
file: "/crawler-default.yaml"
override: false
- resource: false
file: "crawler-conf.yaml"
override: true
- resource: false
file: "es-conf.yaml"
override: true
spouts:
- id: "spout"
className: "com.digitalpebble.stormcrawler.elasticsearch.persistence.AggregationSpout"
parallelism: 10
bolts:
- id: "partitioner"
className: "com.digitalpebble.stormcrawler.bolt.URLPartitionerBolt"
parallelism: 1
- id: "fetcher"
className: "com.digitalpebble.stormcrawler.bolt.FetcherBolt"
parallelism: 1
- id: "sitemap"
className: "com.digitalpebble.stormcrawler.bolt.SiteMapParserBolt"
parallelism: 1
- id: "parse"
className: "com.digitalpebble.stormcrawler.bolt.JSoupParserBolt"
parallelism: 1
- id: "index"
className: "com.digitalpebble.stormcrawler.elasticsearch.bolt.IndexerBolt"
parallelism: 1
- id: "status"
className: "com.digitalpebble.stormcrawler.elasticsearch.persistence.StatusUpdaterBolt"
parallelism: 1
- id: "status_metrics"
className: "com.digitalpebble.stormcrawler.elasticsearch.metrics.StatusMetricsBolt"
parallelism: 1
- id: "redirection_bolt"
className: "com.digitalpebble.stormcrawler.tika.RedirectionBolt"
parallelism: 1
- id: "parser_bolt"
className: "com.digitalpebble.stormcrawler.tika.ParserBolt"
parallelism: 1
streams:
- from: "spout"
to: "partitioner"
grouping:
type: SHUFFLE
- from: "spout"
to: "status_metrics"
grouping:
type: SHUFFLE
- from: "partitioner"
to: "fetcher"
grouping:
type: FIELDS
args: ["key"]
- from: "fetcher"
to: "sitemap"
grouping:
type: LOCAL_OR_SHUFFLE
- from: "sitemap"
to: "parse"
grouping:
type: LOCAL_OR_SHUFFLE
- from: "parse"
to: "index"
grouping:
type: LOCAL_OR_SHUFFLE
- from: "fetcher"
to: "status"
grouping:
type: FIELDS
args: ["url"]
streamId: "status"
- from: "sitemap"
to: "status"
grouping:
type: FIELDS
args: ["url"]
streamId: "status"
- from: "parse"
to: "status"
grouping:
type: FIELDS
args: ["url"]
streamId: "status"
- from: "index"
to: "status"
grouping:
type: FIELDS
args: ["url"]
streamId: "status"
- from: "parse"
to: "redirection_bolt"
grouping:
type: LOCAL_OR_SHUFFLE
- from: "redirection_bolt"
to: "parser_bolt"
grouping:
type: LOCAL_OR_SHUFFLE
- from: "redirection_bolt"
to: "index"
grouping:
type: LOCAL_OR_SHUFFLE
- from: "parser_bolt"
to: "index"
grouping:
type: LOCAL_OR_SHUFFLE
- from: "redirection_bolt"
to: "parser_bolt"
grouping:
type: LOCAL_OR_SHUFFLE
streamId: "tika"
**pom.xml:**
<project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/maven-v4_0_0.xsd">
<modelVersion>4.0.0</modelVersion>
<groupId>com.saunderstika.test1</groupId>
<artifactId>saunderstika</artifactId>
<version>1.0-SNAPSHOT</version>
<packaging>jar</packaging>
<properties>
<project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
</properties>
<build>
<plugins>
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-compiler-plugin</artifactId>
<version>3.2</version>
<configuration>
<source>1.8</source>
<target>1.8</target>
</configuration>
</plugin>
<plugin>
<groupId>org.codehaus.mojo</groupId>
<artifactId>exec-maven-plugin</artifactId>
<version>1.3.2</version>
<executions>
<execution>
<goals>
<goal>exec</goal>
</goals>
</execution>
</executions>
<configuration>
<executable>java</executable>
<includeProjectDependencies>true</includeProjectDependencies>
<includePluginDependencies>false</includePluginDependencies>
<classpathScope>compile</classpathScope>
</configuration>
</plugin>
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-shade-plugin</artifactId>
<version>1.3.3</version>
<executions>
<execution>
<phase>package</phase>
<goals>
<goal>shade</goal>
</goals>
<configuration>
<createDependencyReducedPom>false</createDependencyReducedPom>
<transformers>
<transformer
implementation="org.apache.maven.plugins.shade.resource.ServicesResourceTransformer" />
<transformer
implementation="org.apache.maven.plugins.shade.resource.ManifestResourceTransformer">
<mainClass>org.apache.storm.flux.Flux</mainClass>
<manifestEntries>
<Change></Change>
<Build-Date></Build-Date>
</manifestEntries>
</transformer>
</transformers>
<!-- The filters below are necessary if you want to include the Tika
module -->
<filters>
<filter>
<artifact>*:*</artifact>
<excludes>
<exclude>META-INF/*.SF</exclude>
<exclude>META-INF/*.DSA</exclude>
<exclude>META-INF/*.RSA</exclude>
</excludes>
</filter>
<filter>
<!-- https://issues.apache.org/jira/browse/STORM-2428 -->
<artifact>org.apache.storm:flux-core</artifact>
<excludes>
<exclude>org/apache/commons/**</exclude>
<exclude>org/apache/http/**</exclude>
<exclude>org/yaml/**</exclude>
</excludes>
</filter>
</filters>
</configuration>
</execution>
</executions>
</plugin>
</plugins>
</build>
<dependencies>
<dependency>
<groupId>com.digitalpebble.stormcrawler</groupId>
<artifactId>storm-crawler-core</artifactId>
<version>1.10</version>
</dependency>
<dependency>
<groupId>com.digitalpebble.stormcrawler</groupId>
<artifactId>storm-crawler-elasticsearch</artifactId>
<version>1.10</version>
</dependency>
<dependency>
<groupId>com.digitalpebble.stormcrawler</groupId>
<artifactId>storm-crawler-tika</artifactId>
<version>1.10</version>
</dependency>
<dependency>
<groupId>org.apache.storm</groupId>
<artifactId>storm-core</artifactId>
<version>1.2.2</version>
<scope>provided</scope>
</dependency>
<dependency>
<groupId>org.apache.storm</groupId>
<artifactId>flux-core</artifactId>
<version>1.2.2</version>
</dependency>
</dependencies>
</project>
**es-injector.flux:**
name: "injector"
includes:
- resource: true
file: "/crawler-default.yaml"
override: false
- resource: false
file: "crawler-conf.yaml"
override: true
- resource: false
file: "es-conf.yaml"
override: true
components:
- id: "scheme"
className: "com.digitalpebble.stormcrawler.util.StringTabScheme"
constructorArgs:
- DISCOVERED
spouts:
- id: "spout"
className: "com.digitalpebble.stormcrawler.spout.FileSpout"
parallelism: 1
constructorArgs:
- "."
- "seeds.txt"
- ref: "scheme"
bolts:
- id: "status"
className: "com.digitalpebble.stormcrawler.elasticsearch.persistence.StatusUpdaterBolt"
parallelism: 1
- id: "parser_bolt"
className: "com.digitalpebble.stormcrawler.tika.ParserBolt"
parallelism: 1
streams:
- from: "spout"
to: "status"
grouping:
type: CUSTOM
customClass:
className: "com.digitalpebble.stormcrawler.util.URLStreamGrouping"
constructorArgs:
- "byHost"
答案 0 :(得分：0)
您是否在配置中设置了 jsoup.treat.non.html.as.error：false ？请参阅Tika模块中的README。
我尝试了您的Flux拓扑，但是我可以看到正在索引的PDF文档，不确定您的问题在哪里。也许尝试在PDF URL上使用MemorySpout，例如
spouts:
- id: "spout"
className: "com.digitalpebble.stormcrawler.spout.MemorySpout"
parallelism: 1
constructorArgs:
- ["http://blog.marc-seeger.de/assets/papers/thesis_seeger-building_blocks_of_a_scalable_webcrawler.pdf"]
并检查日志和ES索引是否正确获取了文档。
或者，您可以尝试仅使用Tika进行解析，而不尝试使用JSoup解析器，这样它就可以处理所有文档，无论其mime类型如何。它不如用于Xpath提取的JSoup起作用，这就是为什么后者是HTML内容的首选选项的原因。