wikionary to ruslingua

LICENSE

@@ -1,4 +1,4 @@
-Copyright (c) 2021 Vladislav Zenkevich
+Copyright (c) 2024 Vladislav Zenkevich
 
 Permission is hereby granted, free of charge, to any person obtaining a copy
 of this software and associated documentation files (the "Software"), to deal

README.MD

@@ -1,18 +1,68 @@
-<h1 align="center">wikionary - Модуль для поиска Синонимов, Антонимов и т.д.</h1>
+# RusLingua 📚
 
-<br>
+RusLingua is a Python library for retrieving various linguistic information about Russian words. It provides a simple API to get synonyms, antonyms, word associations, cognate words, and definitions.
 
-<h1 align="center"> -Как это работает?- </h1>
+## Features
+
+- Get synonyms of a word 👥
+- Get antonyms of a word 👎
+- Get word associations 💭
+- Get cognate words (words with a common root) 🌳
+- Get definitions from dictionaries 📖
+
+## Quickstart
+
+```python
+from ruslingua import RusLingua
+
+ruslingua = RusLingua()
+
+synonyms = ruslingua.get_synonyms('дом')
+antonyms = ruslingua.get_antonyms('дом')
+associations = ruslingua.get_associations('дом')
+cognates = ruslingua.get_cognate_words('дом')  
+definition = ruslingua.get_definition('дом')
+
+print(synonyms)  
+print(antonyms)
+print(associations)
+print(cognates)
+print(definition)
+```
+
+## Installation 
+
+```
+pip install ruslingua
+```
+
+## Usage
+
+Import the RusLingua class and instantiate it:
 
 ```python
-import wikionary as w
+from ruslingua import RusLingua
+
+ruslingua = RusLingua()
+```
+
+Then call the methods with a word to get the linguistic information:
+
+```python 
+synonyms = ruslingua.get_synonyms('дом')
+antonyms = ruslingua.get_antonyms('дом')
+associations = ruslingua.get_associations('дом')
+cognates = ruslingua.get_cognate_words('дом')
+definition = ruslingua.get_definition('дом') 
+```
+
+The methods return lists of strings.
+
+## Credits 
 
-print(w.getSynonims('привет')) #Найти синонимы к слову привет
-print(w.getAntonyms('привет')) #Найти антонимы к слову привет
-print(w.getPhraseologs('привет')) #Найти фразеологизмы к слову привет
-print(w.getHyperonims('привет')) #Найти гиперонимы к слову привет
-print(w.getAssociations('привет')) #Найти ассоциации к слову привет
-print(w.getRandomWord()) #Найти случайное слово
+RusLingua retrieves data from various sources:
 
-print(w.inflectWord('привет')) #Сделать разбор по падежам
-```
+- [jeck.ru](https://jeck.ru) - synonyms 👥
+- [razbiraem-slovo.ru](https://razbiraem-slovo.ru) - antonyms 👎 and cognate words 🌳
+- [wordassociations.net](https://wordassociations.net) - word associations 💭
+- [gramota.ru](https://gramota.ru) - definitions 📖

ruslingua/__init__.py

@@ -0,0 +1 @@
+from .ruslingua import RusLingua

ruslingua/ruslingua.py

@@ -0,0 +1,59 @@
+import requests
+from lxml import html
+from urllib.parse import unquote
+
+class RusLingua:
+    def __init__(self):
+        self.user_agent = ('Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 '
+                           '(KHTML, like Gecko) Chrome/51.0.2704.103 Safari/537.36')
+        self.headers = {'User-Agent': self.user_agent}
+
+    def get_html_tree(self, url):
+        response = requests.get(url, headers=self.headers)
+        return html.fromstring(response.content)
+
+    def get_synonyms(self, word):
+        synonyms = []
+        tree = self.get_html_tree(
+            f'https://jeck.ru/tools/SynonymsDictionary/{word}')
+
+        for url in tree.xpath('//td/a/@href'):
+            if '+' not in url:
+                parts = url.split('Dictionary/')
+                if len(parts) > 1:
+                    synonyms.append(unquote(parts[1]))
+
+        return synonyms
+
+    def get_antonyms(self, word):
+        tree = self.get_html_tree(f'https://razbiraem-slovo.ru/antonyms/{word}')
+        elements = tree.xpath("//*[contains(@href, 'antonyms')][count(@class)=0]")
+
+        antonyms = [element.text.strip() for element in elements if element.text.strip()]
+        return antonyms
+
+    def get_cognate_words(self, word):
+        tree = self.get_html_tree(f'https://razbiraem-slovo.ru/odnokorennye/{word}')
+        elements = tree.xpath("//*[contains(@href, 'po-sostavu')][count(@class)=1]")
+
+        cognates = [element.attrib['href'].split('/')[-1] for element in elements if 'разбор' in element.text]
+        return cognates
+
+    def get_associations(self, word):
+        associations = []
+        tree = self.get_html_tree(
+            f'https://wordassociations.net/ru/ассоциации-к-слову/{word}')
+
+        for url in tree.xpath('//li/a/@href'):
+            if 'D1%83/' in url:
+                associations.append(unquote(url.split('D1%83/')[1]).lower())
+
+        return associations
+
+    def get_definition(self, word):
+        tree = self.get_html_tree(
+            f'https://gramota.ru/poisk?query={word}&mode=slovari&l=1&dicts[]=42')
+
+        full_text = ''.join(tree.xpath("//div[contains(@class, 'description')]//text()"))
+
+        return full_text.strip()

setup.py

@@ -4,23 +4,23 @@
     long_description = f.read()
 
 setup(
-    name="wikionary",
-    version="1.2.1",
+    name="ruslingua",
+    version="1.0.0",
     author="Maehdakvan",
     author_email="visitanimation@google.com",
-    description="Модуль для поиска Синонимов, Антонимов и т.д.",
+    description="",
     long_description=long_description,
     long_description_content_type="text/markdown",
-    url="https://github.com/DedInc/wikionary",
+    url="https://github.com/DedInc/ruslingua",
     project_urls={
-        "Bug Tracker": "https://github.com/DedInc/wikionary/issues",
+        "Bug Tracker": "https://github.com/DedInc/ruslingua/issues",
     },
     classifiers=[
         "Programming Language :: Python :: 3",
         "License :: OSI Approved :: MIT License",
         "Operating System :: OS Independent",
     ],
     packages=find_packages(),
-    install_requires=['requests', 'lxml', 'pymorphy2'],
+    install_requires=['requests', 'lxml'],
     python_requires=">=3.6"
 )