def clear_definitions(text): # todo: move this to some `lib`
# удаление лишнего:
text = text.replace('{µ(Q)}', '')
text = re.sub('<!--(.+?)-->', '', text)
text = re.sub('<math>[^<>]+</math>', '', text)
text = re.sub('{{пример({{[^}]+\}\}|[^\}])*\}\}', '', text)
text = re.sub('{{семантика({{[^}]+\}\}|[^\}])+\}\}', '', text)
text = re.sub('{{списки семантических связей\}\}', '', text)
text = re.sub('^\s*{{прото\|([^}]+)\}\}',
'общее прототипическое значение: \\1', text)
text = text.replace('<sub>2</sub>', '₂')
text = text.replace('<sub>3</sub>', '₃')
text = text.replace('<sub>4</sub>', '₄')
# замена шаблонов:
text = re.sub('{{итп\}\}', 'и т.п.', text)
text = re.sub('{{итд\}\}', 'и т.д.', text)
text = re.sub('\|[a-z_]+\}\}', '}}', text)
# замена всех шаблонов {{...}} на {...}:
text = text.replace('{{', '{').replace('}}', '}')
# замены шаблонов:
text = re.sub('{=\|([^|}]+)\}', 'то же, что \\1', text)
text = re.sub('{=\|([^|}]+)\|([^|}]+)\}', 'то же, что \\1; \\2', text)
text = re.sub('\s*{-\}\s*', ' — ', text)
# ссылки [[...|...]] и [[...]]:
text = re.sub('\[\[[^][]*\|([^][]*)\]\]', '\\1', text)
text = re.sub('\[\[([^][]*)\]\]', '\\1', text)
text = text.replace('<', '<').replace('>', '>')
text = text.replace(' ', ' ')
# пометы:
text = text.replace('{п.}', '{перен.}')
text = text.replace('{помета.}', '')
# пометы курсивом:
text = re.sub('{([ .\w-]+\.)\}(,?)', '<i>\\1\\2</i> ', text)
text = re.sub("''([^']+?)''", '<i>\\1</i> ', text)
# замены шаблонов:
text = text.replace('{as ru}', '<i>(аналогично русскому слову)</i>')
tpls = json_load(tpls_filename)
for tpl, replace in tpls.items():
text = re.sub(replace_tpl(tpl), replace_result(replace), text)
return text.strip()
def send_daily_word():
bot = telegram.Bot(conf.telegram_token)
chat_id = conf.new_channel_id
now = datetime.now()
year_month = now.strftime('%Y/%m')
path = f'{conf.data_path}/word_of_day/{year_month}/latest.json'
data = json_load(path)
title = data[str(now.day)]
print(title)
text = '🔆 Слово дня\n' + Reply(title).text
send(bot, chat_id, text)
class messages:
filename = join(conf.data_path, 'new_articles', 'messages.json')
ids = json_load(filename)
@classmethod
def get(cls, title):
return cls.ids[title]
@classmethod
def set(cls, title, message_id):
if title in cls.ids:
slack_error(f'⚠️ Сообщение для "`{title}`" уже было?')
cls.ids[title] = message_id
json_dump(cls.filename, cls.ids)
def get_stats():
new_data = {}
for lang in langs:
html_content = read(html_path(lang))
# table = re.search(
# '<table class="wikitable mw-statistics-table">(.*?)</table>',
# html_content,
# re.DOTALL,
# ).group(1)
# write(f'table/{lang}.html', table)
numbers = re.findall('<td class="mw-statistics-numbers">(.*?)</td>',
html_content)
# write(f'numbers/{lang}.txt', '\n'.join(numbers))
# print(':', ' | '.join(numbers))
# if len(numbers) != 20:
# print(lang, len(numbers))
values = []
for index in [0, 1, 3, 5, 6]:
value = re.sub('[^0-9]', '', numbers[index])
if value:
values.append(value)
if values:
# write(f'values/{lang}.txt', '\n'.join(values))
new_data[lang] = {
'goods': int(values[0]),
'pages': int(values[1]),
'edits': int(values[2]),
'users': int(values[3]),
'active': int(values[4]),
}
# else:
# print(lang)
history_filename = join(conf.data_path, 'daily_stats', 'history', 'values',
f'{dtf("Ym/Ymd")}.json')
active_filename = join(conf.data_path, 'daily_stats', 'active.json')
old_data = json_load(active_filename)
json_dump(history_filename, new_data)
json_dump(active_filename, new_data)
return old_data, new_data
def import_entries(self, suffix=''):
filename = self.entries_filename(suffix)
if not exists(filename):
print(f'ImportEntriesError: File not found: "{filename}"')
return
self.entries = json_load(filename)