You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@stormcrawler.apache.org by rz...@apache.org on 2025/09/19 11:23:55 UTC

(stormcrawler) 01/01: Merge remote-tracking branch 'origin/main' into docs

This is an automated email from the ASF dual-hosted git repository.

rzo1 pushed a commit to branch docs
in repository https://gitbox.apache.org/repos/asf/stormcrawler.git

commit 18bb91041bbfb5ccd18f6bd2cfae1a48611461ab
Merge: a706f266 038152df
Author: Richard Zowalla <rz...@apache.org>
AuthorDate: Fri Sep 19 13:23:43 2025 +0200

    Merge remote-tracking branch 'origin/main' into docs

 .github/workflows/main.yml                         |   2 +-
 .github/workflows/maven.yml                        |   4 +-
 .github/workflows/snapshots.yaml                   |   2 +-
 THIRD-PARTY.txt                                    | 124 +++++-----
 core/pom.xml                                       |  33 +--
 .../filtering/basic/BasicURLFilter.java            |   7 +-
 .../filtering/basic/BasicURLNormalizer.java        |   2 +-
 .../filtering/metadata/MetadataFilter.java         | 246 +++++++++++++++++--
 .../apache/stormcrawler/jsoup/LinkParseFilter.java |   2 +-
 .../org/apache/stormcrawler/parse/ParseResult.java |   4 +-
 .../parse/filter/CollectionTagger.java             |   4 +-
 .../stormcrawler/parse/filter/LinkParseFilter.java |   2 +-
 .../stormcrawler/parse/filter/XPathFilter.java     |   4 +-
 .../persistence/urlbuffer/AbstractURLBuffer.java   |   3 +-
 .../protocol/HttpRobotRulesParser.java             |   5 +-
 .../protocol/httpclient/HttpProtocol.java          |   2 +-
 .../apache/stormcrawler/util/CookieConverter.java  |   2 +-
 .../java/org/apache/stormcrawler/util/URLUtil.java |  24 +-
 core/src/main/resources/crawler-default.yaml       |  24 --
 .../filtering/MetadataFilterFromJsonTest.java      | 152 ++++++++++++
 .../stormcrawler/filtering/MetadataFilterTest.java | 262 +++++++++++++++++++++
 .../test/resources/test.metadata.1.urlfilters.json |  11 +
 .../test/resources/test.metadata.2.urlfilters.json |  15 ++
 .../test/resources/test.metadata.3.urlfilters.json |  21 ++
 external/ai/pom.xml                                |   4 +-
 external/aws/pom.xml                               |   2 +-
 external/playwright/pom.xml                        |   2 +-
 external/selenium/README.md                        |  43 ++++
 external/{playwright => selenium}/pom.xml          |  56 +++--
 external/selenium/selenium-conf.yaml               |  41 ++++
 .../protocol/selenium/NavigationFilter.java        |   0
 .../protocol/selenium/NavigationFilters.java       |   0
 .../protocol/selenium/RemoteDriverProtocol.java    |   0
 .../protocol/selenium/SeleniumProtocol.java        |   0
 .../protocol/selenium/ProtocolTest.java            |   0
 .../apache/stormcrawler/sql/StatusUpdaterBolt.java |   2 +-
 .../apache/stormcrawler/warc/WARCHdfsBoltTest.java |   2 +-
 .../apache/stormcrawler/warc/WARCSpoutTest.java    |   2 +-
 pom.xml                                            |  25 +-
 39 files changed, 953 insertions(+), 183 deletions(-)