From df1bdea0291c04ded3fca23c6065a46c1444b05c Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Jakub=20Dost=C3=A1l?= Date: Thu, 12 Nov 2020 09:51:51 +0100 Subject: [PATCH] czech language support added --- README.rst | 1 + docs/index.rst | 1 + docs/user_guide/quickstart.rst | 1 + newspaper/resources/text/stopwords-cs.txt | 138 ++++++++++++++++++++++ newspaper/utils.py | 1 + 5 files changed, 142 insertions(+) create mode 100644 newspaper/resources/text/stopwords-cs.txt diff --git a/README.rst b/README.rst index 21373ba73..0ebb3f734 100644 --- a/README.rst +++ b/README.rst @@ -199,6 +199,7 @@ Features ar Arabic be Belarusian bg Bulgarian + cs Czech da Danish de German el Greek diff --git a/docs/index.rst b/docs/index.rst index 111ae633b..52b42f525 100644 --- a/docs/index.rst +++ b/docs/index.rst @@ -196,6 +196,7 @@ Features ar Arabic be Belarusian bg Bulgarian + cs Czech da Danish de German el Greek diff --git a/docs/user_guide/quickstart.rst b/docs/user_guide/quickstart.rst index 24fe07b62..d1bb01ebc 100644 --- a/docs/user_guide/quickstart.rst +++ b/docs/user_guide/quickstart.rst @@ -267,6 +267,7 @@ of popular news source urls.. In case you need help choosing a news source! input code full name ar Arabic + cs Czech de German en English es Spanish diff --git a/newspaper/resources/text/stopwords-cs.txt b/newspaper/resources/text/stopwords-cs.txt new file mode 100644 index 000000000..2030b6b37 --- /dev/null +++ b/newspaper/resources/text/stopwords-cs.txt @@ -0,0 +1,138 @@ +dnes +cz +timto +budes +budem +byli +jses +muj +svym +ta +tomto +tohle +tuto +tyto +jej +zda +proc +mate +tato +kam +tohoto +kdo +kteri +mi +nam +tom +tomuto +mit +nic +proto +kterou +byla +toho +protoze +asi +ho +nasi +napiste +re +coz +tim +takze +svych +jeji +svymi +jste +aj +tu +tedy +teto +bylo +kde +ke +prave +ji +nad +nejsou +ci +pod +tema +mezi +pres +ty +pak +vam +ani +kdyz +vsak +ne +jsem +tento +clanku +clanky +aby +jsme +pred +pta +jejich +byl +jeste +az +bez +take +pouze +prvni +vase +ktera +nas +novy +tipy +pokud +muze +design +strana +jeho +sve +jine +zpravy +nove +neni +vas +jen +podle +zde +clanek +uz +email +byt +vice +bude +jiz +nez +ktery +by +ktere +co +nebo +ten +tak +ma +pri +od +po +jsou +jak +dalsi +ale +si +ve +to +jako +za +zpet +ze +do +pro +je +na \ No newline at end of file diff --git a/newspaper/utils.py b/newspaper/utils.py index bfa441482..687cd82ec 100644 --- a/newspaper/utils.py +++ b/newspaper/utils.py @@ -358,6 +358,7 @@ def print_available_languages(): 'ar': 'Arabic', 'be': 'Belarusian', 'bg': 'Bulgarian', + 'cs': 'Czech', 'da': 'Danish', 'de': 'German', 'el': 'Greek',