evaluation: review data, update packages, add magic_html (#731)

* evaluation: review data, update packages, add magic_html * update data and remove empty files
adbar · Nov 7, 2024 · 623b0ef · 623b0ef
1 parent 418f807
commit 623b0ef
Show file tree

Hide file tree

Showing 30 changed files with 2,231 additions and 16,223 deletions.
diff --git a/tests/eval-requirements.txt b/tests/eval-requirements.txt
@@ -1,9 +1,9 @@
-pandas==2.2.2
+pandas==2.2.3
 tabulate==0.9.0
-tqdm==4.66.4
+tqdm==4.66.5
 # rouge-score==0.1.2
 
-trafilatura==1.10.0
+trafilatura==1.12.2
 
 # alternatives
 beautifulsoup4==4.12.3
@@ -16,7 +16,8 @@ inscriptis==2.5.0
 justext==3.0.1
 newspaper3k==0.2.8
 # newspaper4k==0.9.3.1  # replaces newspaper3k if installed
-news-please==1.5.44
+news-please==1.6.13
 # readabilipy==0.2.0  # unmaintained!
 readability-lxml==0.8.1
-resiliparse==0.14.7
+resiliparse==0.14.9
+# magic_html @ git+https://github.com/opendatalab/magic-html
diff --git a/tests/eval/autohaus.de-mueller.html b/tests/eval/autohaus.de-mueller.html
diff --git a/tests/eval/bmbf.de-forschungsprojekt.html b/tests/eval/bmbf.de-forschungsprojekt.html
diff --git a/tests/eval/bmf.de.energiewende.html → tests/eval/bmbf.de.energiewende.html b/tests/eval/bmf.de.energiewende.html → tests/eval/bmbf.de.energiewende.html
diff --git a/tests/eval/bund.net-marode.html b/tests/eval/bund.net-marode.html
diff --git a/tests/eval/bund.net.akw.html b/tests/eval/bund.net.akw.html
diff --git a/tests/eval/bundeswehrkarriere.de.Laura.html b/tests/eval/bundeswehrkarriere.de.Laura.html
diff --git a/tests/eval/cecil.de.lieblingsfarbe.html b/tests/eval/cecil.de.lieblingsfarbe.html
diff --git a/tests/eval/changenow.de.loibl.html b/tests/eval/changenow.de.loibl.html