Apache Tika is indexing HTTP response instead of document content - wordpress

Question

I'm using Solr 8.3 and Tika to index Wordpress (version 4.9.7) contents and attachments. Solr and Wordpress servers are in the same internal network in the company. Due to an organizational decision, I'm not using plugins such as WP-Solr and others (all of them good enough).
I wrote data-config.xml and managed-schema files, and uploaded them to Zookeeper. These files are updated in Solr admin interface. So I created a new collection, called wp, and indexed some files (in Solr admin interface, I set the range from 0 to 200).
So, when I query the contents, the meta fields are rightly indexed, but the conteudo_text and text fields return 301 HTTP Response (example bellow):
{
"responseHeader":{
"zkConnected":true,
"status":0,
"QTime":18,
"params":{
"q":"*:*",
"start":"0",
"rows":"1",
"_":"1580842143627"}},
"response":{"numFound":500,"start":0,"maxScore":1.0,"docs":[
{
"data_alteracao":"2019-09-06T11:05:10Z",
"conteudo":"Criação",
"titulo":"Criação",
"id":"37829",
"data_publicacao":"2019-09-06T11:04:55Z",
"url":"http://www.homolog.tjrs.jus.br/static/2019/09/estag-criacao.pdf",
"conteudo_text":["\nMoved Permanently\n\nThe document has moved here.\n\n\n\nApache Server at www.homolog.tjrs.jus.br Port 80\n\n"],
"_text_":["\nMoved Permanently\n\nThe document has moved here.\n\n\n\nApache Server at www.homolog.tjrs.jus.br Port 80\n\n"],
"_version_":1657631228775366656}]
}}
My data-config.xml:
<dataConfig>
<dataSource
type="JdbcDataSource"
driver="com.mysql.jdbc.Driver"
url="jdbc:mysql://mysql-grid-homol.tjrs.gov.br:3306/wordpress"
user="usr"
password="pwd"
name="wpdb"
batchSize="-1"
readOnly="true"
/>
<dataSource
type="BinURLDataSource"
name="url_doc"
/>
<document name="docs">
<entity
dataSource="wpdb"
name="wp"
pk="ID"
query="
SELECT
post.Id ID,
post_title TITULO,
IF (post_content = '', post_title, post_content) CONTEUDO,
CONCAT
(
DATE_FORMAT(post.Post_date, '%Y-%m-%d'),
'T',
DATE_FORMAT(post.Post_date, '%H:%i:%s'),
'Z'
) DATA_PUBLICACAO,
CONCAT
(
DATE_FORMAT(post.Post_modified, '%Y-%m-%d'),
'T',
DATE_FORMAT(post.Post_modified, '%H:%i:%s'),
'Z'
)DATA_ALTERACAO,
CONCAT
(
'http:',
guid
) URL
FROM
wpw_posts post
LEFT JOIN wpw_postmeta postmeta
ON (postmeta.Post_id = post.Id AND postmeta.Meta_key = 'publico')
WHERE
post.Post_type IN ('page', 'noticia', 'evento', 'curso', 'sistema', 'classificado', 'discurso', 'attachment')
AND post.post_status = 'inherit'
AND post.post_mime_type like 'application%'
ORDER BY post.Post_date DESC
"
>
<field column="ID" name="id"/>
<field column="TITULO" name="titulo"/>
<field column="CONTEUDO" name="conteudo"/>
<field column="DATA_PUBLICACAO" name="data_publicacao" dateTimeFormat="DD/MM/YYYY'T'hh:mm:ss"/>
<field column="DATA_ALTERACAO" name="data_alteracao" dateTimeFormat="DD/MM/YYYY'T'hh:mm:ss"/>
<field column="URL" name="url"/>
<entity
name="arquivo"
dataSource="url_doc"
processor="TikaEntityProcessor"
url="${wp.URL}"
format="text"
onError="continue"
extractEmbedded="true"
>
<field column="text" name="conteudo_text" />
</entity>
</entity>
</document>
</dataConfig>
My managed-schema:
<?xml version="1.0" encoding="UTF-8" ?>
<schema name="v2" version="1.6">
<field name="id" type="string" indexed="true" stored="true" required="true" multiValued="false" />
<uniqueKey>id</uniqueKey>
<field name="titulo" type="string" indexed="true" stored="true" required="true" />
<field name="conteudo" type="string" indexed="true" stored="true" required="true" />
<field name="data_publicacao" type="date" indexed="true" stored="true" docValues="true"/>
<field name="data_alteracao" type="date" indexed="true" stored="true" docValues="true" />
<field name="url" type="string" indexed="true" stored="true" required="true" multiValued="false"/>
<field name="conteudo_text" type="text" indexed="true" stored="true" required="true" multiValued="true" default=" "/>
<field name="text" type="sem_aspas" indexed="true" stored="true" required="true" multiValued="true"/>
<field name="_version_" type="long" indexed="false" stored="false" />
<field name="_root_" type="string" indexed="true" stored="false" docValues="false" />
<field name="_text_" type="sem_aspas" indexed="true" stored="true" multiValued="true"/>
<!-- primitive types -->
<fieldType name="integer" class="solr.IntPointField" docValues="true"/>
<fieldType name="integers" class="solr.IntPointField" docValues="true" multiValued="true"/>
<fieldType name="long" class="solr.LongPointField" docValues="true"/>
<fieldType name="longs" class="solr.LongPointField" docValues="true" multiValued="true"/>
<fieldType name="string" class="solr.StrField" sortMissingLast="true" docValues="true" />
<fieldType name="strings" class="solr.StrField" sortMissingLast="true" docValues="true" multiValued="true"/>
<fieldType name="date" class="solr.DatePointField" docValues="true"/>
<fieldType name="dates" class="solr.DatePointField" docValues="true" multiValued="true"/>
<fieldType name="boolean" class="solr.BoolField" sortMissingLast="true"/>
<fieldType name="booleans" class="solr.BoolField" sortMissingLast="true" multiValued="true"/>
<fieldType name="float" class="solr.FloatPointField" docValues="true" multiValued="false"/>
<fieldType name="floats" class="solr.FloatPointField" docValues="true" multiValued="true"/>
<fieldType name="double" class="solr.DoublePointField" docValues="true" multiValued="false"/>
<fieldType name="doubles" class="solr.DoublePointField" docValues="true" multiValued="true"/>
<fieldType name="binary" class="solr.BinaryField"/>
<copyField source="conteudo_text" dest="_text_" />
<fieldType name="sem_aspas" class="solr.TextField" positionIncrementGap="100">
<analyzer type="index">
<tokenizer class="solr.ClassicTokenizerFactory"/>
<charFilter class="solr.MappingCharFilterFactory" mapping="mapping-FoldToASCII.txt"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" format="snowball" />
<filter class="solr.BrazilianStemFilterFactory"/>
</analyzer>
<analyzer type="query">
<tokenizer class="solr.ClassicTokenizerFactory"/>
<charFilter class="solr.MappingCharFilterFactory" mapping="mapping-FoldToASCII.txt"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" format="snowball" />
<filter class="solr.BrazilianStemFilterFactory"/>
<filter class="solr.SynonymGraphFilterFactory" expand="true" ignoreCase="true" synonyms="synonyms.txt"/>
</analyzer>
</fieldType>
<fieldType name="text" class="solr.TextField" positionIncrementGap="100" multiValued="true">
<analyzer type="index">
<tokenizer class="solr.ClassicTokenizerFactory"/>
<charFilter class="solr.MappingCharFilterFactory" mapping="mapping-FoldToASCII.txt"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
<filter class="solr.LowerCaseFilterFactory"/>
</analyzer>
<analyzer type="query">
<tokenizer class="solr.ClassicTokenizerFactory"/>
<charFilter class="solr.MappingCharFilterFactory" mapping="mapping-FoldToASCII.txt"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
<filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
<filter class="solr.LowerCaseFilterFactory"/>
</analyzer>
</fieldType>
</schema>
Things I tried to solve the problem:
1) Change from BinURLDataSource to URLDataSource or FieldStreamDataSource;
2) Include, in BinURLDataSource definition, an user and password with permissions to access the files.
I'm a new user in Solr/Lucene and Tika technology (my 2nd project only), and any help is welcome.
Regards.