24 lines
503 B
Plaintext
24 lines
503 B
Plaintext
|
pandas==2.2.3
|
||
|
|
tabulate==0.9.0
|
||
|
|
tqdm==4.66.5
|
||
|
|
# rouge-score==0.1.2
|
||
|
|
|
||
|
|
trafilatura==1.12.2
|
||
|
|
|
||
|
|
# alternatives
|
||
|
|
beautifulsoup4==4.12.3
|
||
|
|
boilerpy3==1.0.7
|
||
|
|
# dragnet==2.0.4 # unmaintained!
|
||
|
|
goose3==3.1.19
|
||
|
|
html2text==2024.2.26
|
||
|
|
html-text==0.6.2
|
||
|
|
inscriptis==2.5.0
|
||
|
|
justext==3.0.1
|
||
|
|
newspaper3k==0.2.8
|
||
|
|
# newspaper4k==0.9.3.1 # replaces newspaper3k if installed
|
||
|
|
news-please==1.6.13
|
||
|
|
# readabilipy==0.2.0 # unmaintained!
|
||
|
|
readability-lxml==0.8.1
|
||
|
|
resiliparse==0.14.9
|
||
|
|
# magic_html @ git+https://github.com/opendatalab/magic-html
|