Пример #1
0
def check_for_new_titles(bot):
    old_data = {}
    new_data = {}

    json_path = join(ROOT_PATH, 'telegram_bot', 'data', 'forums.json')
    if exists(json_path):
        with open(json_path, encoding='utf-8') as f:
            old_data = json.load(f)

    for forum in forums:
        content = load_page(forum)
        titles = re.findall('^==(.*)==\s*$', content, re.MULTILINE)
        titles = list(map(str.strip, titles))
        new_data[forum] = titles
        old_titles = old_data.get(forum, [])
        new_titles = list(set(titles) - set(old_titles))
        if new_titles:
            forum_name = forum[len('Викисловарь:'):]
            message_text = f'📝 <b>Новая тема на форуме!</b>\n' \
                           f'«{forum_name}»\n'
            for title in new_titles:
                title = title.replace('<', '&lt;')
                title = title.replace('>', '&gt;')
                title = title.strip('=').strip()
                link = f'→ <a href="https://ru.wiktionary.org/wiki/{forum}">' \
                       f'{title}</a>\n'
                message_text += link
            # chat_id = DEV_CHAT_ID
            chat_id = MAIN_GROUP_CHAT_ID
            send(bot, chat_id, message_text)

    with open(json_path, 'w', encoding='utf-8') as f:
        json.dump(new_data, f, indent=4)
Пример #2
0
    def __init__(self):
        super().__init__()
        self.base_path = 'Отчёты/ru/Глаголы/Без созданных деепричастий'
        self.base_class = derive(KeyTitle, CustomDetails, ReversedIndex)

        self.report_keys = [
            '-ать',
            '-аться',
            '-ереть',
            '-ереться',
            '-еть',
            '-еться',
            '-ить',
            '-иться',
            '-оть',
            '-оться',
            '-уть',
            '-уться',
            '-ыть',
            '-ыться',
            '-ять',
            '-яться',
            '-ресть',
            '-ресться',
            '-честь',
            '-честься',
            '-сть',
            '-сться',
            '-сти',
            '-стись',
            '-чь',
            '-чься',
            '-зти',
            '-зтись',
            '-зть',
            '-зться',
            '-йти',
            '-йтись',
            '-???',
            '(безличные)',
            '(через дефис)',
        ]
        self.create_reports()

        self.aspects = {}
        for i in range(11):
            if i == 7:
                continue
            lines = load_page(f'User:Vesailok/verb{i}').split('\n')
            for line in lines:
                verb, aspect, verb_stressed = \
                    re.match('# \[\[([^]]+)\]\] \((сов|несов)\) (.+)$', line).\
                    groups()
                # if verb != self.remove_stress(verb_stressed).strip() \
                #         or '́' not in verb_stressed and 'ё' not in verb_stressed:
                #     if verb != verb_stressed:
                #         raise Exception()
                #     print('-', verb)
                #     # raise ImpossibleError(f"Ошибка в данных: {i}/{verb}")
                self.aspects[verb] = aspect
Пример #3
0
def get_new_data(title):
    content = load_page(title, skip_absent=True)
    if not content:
        return {}
    data = {}
    for day, title in re.findall('\|\s*(\d+)\s*=\s*\[\[([^]]+)]]', content):
        print('*', day, '-', title)
        data[day] = title
    return data
Пример #4
0
def prepare_template(title, day, month, year):
    try:
        content = load_page(title)
    except NoPage:
        link = get_title_link(title)
        send(f'⛔️ Страница не найдена: {link}')
        return None, None
    template = '{{слово дня|' + f'{day}|{month}|{year}' + '}}'
    return content, template
Пример #5
0
def download_module(title, path):
    print(f'- {title}', end='')
    content = load_page(title) + '\n'
    content = content.replace("\n-- dev_prefix = 'User:Vitalik/'",
                              "\ndev_prefix = 'User:Vitalik/'")
    outs = ['', '.out'] if not debug else [
        '',
    ]
    for out in outs:
        write(path.replace('[.out]', out), content)
    print(' - OK')
Пример #6
0
 def upload_changes(self, desc, minor=True, debug=False):
     server_content = load_page(self.title)
     if server_content != self._old_content:
         raise Exception('Content on the server was suddenly changed.')
     new_content = self.new_content
     if new_content != self._old_content:
         if debug:
             print('=' * 10)
             print(self.title)
             print('-' * 10)
             print(new_content)
             print('-' * 10)
             return
         save_page(self.title, new_content, desc, minor, check_changes=False)
Пример #7
0
 def __init__(self):
     super().__init__()
     self.aspects = {}
     for i in range(11):
         if i == 7:
             continue
         lines = load_page(f'User:Vesailok/verb{i}').split('\n')
         for line in lines:
             verb, aspect, verb_stressed = \
                 re.match('# \[\[([^]]+)\]\] \((сов|несов)\) (.+)$', line).\
                 groups()
             # if verb != self.remove_stress(verb_stressed).strip() \
             #         or '́' not in verb_stressed and 'ё' not in verb_stressed:
             #     if verb != verb_stressed:
             #         raise Exception()
             #     print('-', verb)
             #     # raise ImpossibleError(f"Ошибка в данных: {i}/{verb}")
             self.aspects[verb] = aspect
Пример #8
0
def download_page(title, path):
    print(f'- {title}', end='')
    try:
        content = load_page(title) + '\n'
    except NoPage:
        print(' - No page')
        return
    content = content.replace("\n-- dev_prefix = 'User:Vitalik/'",
                              "\ndev_prefix = 'User:Vitalik/'")
    if exists(path):
        old_content = read(path)
        if old_content != content:
            print(' - OK')
        else:
            write(path, content)
            print(' - Not changed')
    else:
        write(path, content)
        print(' - NEW')
Пример #9
0
def process_words_of_days():
    current_year = datetime.now().year
    content = load_page('Викисловарь:Слово_дня')
    content = \
        re.search('== Кандидаты ==\n(.*?)\n== ', content, re.DOTALL).group(1)

    processed = False
    for title in re.findall('\[\[(Викисловарь:Слово дня/[^]]+)]]', content):
        title = title.replace('{{#expr: - 1 + {{CURRENTYEAR}} }}',
                              f'{current_year - 1}')
        title = title.replace('{{#expr: + 1 + {{CURRENTYEAR}} }}',
                              f'{current_year + 1}')
        title = title.replace('{{CURRENTYEAR}}', f'{current_year}')
        print('@', title)
        if process_list(title):
            processed = True

    if processed:
        send('✔️ Бот завершил работу')
Пример #10
0
def check_for_new_titles(bot):
    old_data = {}
    new_data = {}

    json_path = join(conf.data_path, 'forum_news', 'forums.json')
    if exists(json_path):
        with open(json_path, encoding='utf-8') as f:
            old_data = json.load(f)

    for forum in forums:
        old_titles = old_data.get(forum, [])

        content = load_page(forum)
        titles = re.findall('^==(.*)==\s*$', content, re.MULTILINE)
        titles = list(map(str.strip, titles))
        new_data[forum] = titles

        new_titles = []
        for title in titles:
            if title not in old_titles:
                new_titles.append(title)

        if new_titles:
            forum_name = forum[len('Викисловарь:'):]
            message_text = f'📝 <b>Новая тема на форуме!</b>\n' \
                           f'«{forum_name}»\n'
            for title in new_titles:
                title = title.replace('<', '&lt;')
                title = title.replace('>', '&gt;')
                title = title.strip('=').strip()
                forum = forum.replace(' ', '_')
                link = f'→ <a href="https://ru.wiktionary.org/wiki/{forum}">' \
                       f'{title}</a>\n'
                message_text += link
            # chat_id = DEV_CHAT_ID
            chat_id = conf.main_group_id
            send(bot, chat_id, message_text)

    with open(json_path, 'w', encoding='utf-8') as f:
        json.dump(new_data, f, indent=4)
Пример #11
0
    def start(self):
        name = re.search(u':Cinemantique/(.+)', self.data_page).group(1)

        if f'* [[{self.data_page}|{name}]] = on' \
                not in load_page(u'User:Cinemantique/bot'):
            print(f'Bot `{self.data_page}` is offline.')
            return

        entries = load_page(self.data_page).strip()
        if not entries:
            print(f'Page `{self.data_page}` is empty.')
            return

        self.report.status('Бот запущен')

        processed = []
        for i, entry in enumerate(entries.split('\n\n')):
            title, *values = entry.split('\n ')
            if not values:
                continue
            if not self.check_entries(title, values):
                continue
            if title in processed:
                self.report.error(title, 'дублируется в списке')
                continue
            processed.append(title)
            try:
                if self.debug:
                    page = StoragePage(title, silent=True)
                else:
                    page = OnlinePage(title, silent=True)
            except PageNotFound:
                self.report.error(title, 'в ВС нет статьи')
                continue
            if page.is_redirect:
                self.report.error(title, 'статья-редирект')
                continue
            if not page.ru:
                self.report.error(title, 'нет русского раздела в статье')
                continue
            if len(page.ru.homonyms.all()) > 1:
                self.report.error(title, 'омонимы в статье')
                continue

            if not self.process_page(page, title, values):
                continue

            try:
                if not self.debug:
                    page.upload_changes(self.desc)
            except Exception:
                self.report.error(title, 'что-то пошло не так')
                self.report.save('unexpected error')
                raise

            self.report.success(title)

        self.report.status('Бот завершён')

        if not self.debug:
            desc = f'Готово: [[{self.data_page}/report|отчёт]]'
            save_page(self.data_page, '', desc)
Пример #12
0
 def append(self, report_title, lines, desc):
     title = f"{self.base.data_page}/{report_title}"
     old_content = load_page(title, skip_absent=True)
     if not self.base.debug:
         save_page(title, f'{old_content}\n{lines}', desc)
Пример #13
0
def process_message(update, context):
    bot = context.bot
    message = update.message
    if not message:
        slack_error('❔ Событие без сообщения?')
        return
    chat = message.chat
    title = message.text.strip()
    user = message.from_user

    is_main_group = chat.id == conf.main_group_id
    is_new_group = chat.id == conf.new_group_id
    system_message = user.id == 777000

    if is_new_group and message.text_html.startswith(new_foreign_header):
        sub_messages = new_foreign_messages.load()
        for sub_message in sub_messages:
            send(bot, conf.new_group_id, sub_message,
                 reply_to=message.message_id, pause=2)
            time.sleep(1)
        return

    if is_new_group and message.text_html.startswith(daily_stats_header):
        sub_messages = daily_stats_messages.load()
        for sub_message in sub_messages:
            send(bot, conf.new_group_id, sub_message,
                 reply_to=message.message_id, pause=2)
            time.sleep(1)
        return

    if '\n' in title or 'https://' in title or 'http://' in title:
        if is_main_group or is_new_group and system_message:
            pass  # do nothing
        else:
            slack_message(message, 'ignore (multiline or link)')
        return

    update_command = title in ["=", "update", "upd", "refresh",
                               "обновить", "обнови", "обновись"]
    reply_bot = None
    reply = message.reply_to_message
    if reply and reply.from_user.id in [conf.bot_chat_id, 777000]:  # fixme: 777000 doesn't work (and perhaps we don't need it?)
        reply_bot = reply

    if message.chat_id < 0:  # if we are in a group chat
        if title.endswith(('=', '~', ' ?')):
            pass  # okay
        elif update_command and reply_bot:
            pass  # okay
        else:
            if not is_main_group \
                    and chat.id not in [-1001369947386, -1001163650570]:
                slack_message(message, 'ignore (chat messages)')
            return  # do nothing

    if user.id in conf.admin_ids and title.lower() == 'update!':
        content = load_page('User:VitalikBot/conf/telegram/tpls.json')
        data = json.loads(content)
        json_dump(tpls_filename, data)
        send(bot, chat.id, 'Done')
        if not is_main_group:
            slack_message(message, 'Done')
        return

    if update_command and reply_bot:
        msg = reply_bot
        m = re.search('<b>(?P<title>.*?)</b>', reply_bot.text_html)
        if not m:
            send(bot, chat.id, '🤷🏻‍♂️ Внутренняя ошибка '
                               '(не получилось распарсить сообщение)')
            return
        title = remove_stress(m.group('title'))
    else:
        bot.send_chat_action(chat.id, telegram.ChatAction.TYPING)  # typing...
        msg = send(bot, chat.id, '🔎 <i>Делаю запрос...</i>')

    skip_content = title.endswith('==')

    title = re.sub(r'\s*=+$', '', title)
    homonym, title = get_homonym(title)
    lang, title = get_lang(title)
    title = re.sub(r'#(\w+)', '', title)
    title = title.strip()
    save_log(message, title)

    def edit_message(reply, suffix=''):
        buttons = reply.buttons
        if message.chat.id == conf.new_channel_id:
            buttons = None
        edit(bot, chat.id, msg.message_id, reply.text + suffix, buttons)
        replies.append(reply)

    replies = []
    if skip_content:
        edit_message(ShortReply(title))
    else:
        try:
            edit_message(StorageReply(title, lang, homonym))
        except StorageError as e:
            edit_message(ErrorReply(title))
            slack_exception('storage', e)

        try:
            suffix = ''
            if message.chat.id == conf.new_channel_id:
                suffix = get_author(title)
            edit_message(Reply(title, lang, homonym), suffix)
        except Exception:
            edit_message(ErrorReply(title))
            raise

    slack_message_raw(':large_blue_circle: ' * 3)
    for reply in replies:
        slack_message(message, reply.text)
Пример #14
0
 def __init__(self, title, site_lang: str, silent=False):
     content = load_page(title)
     # todo: process `is_redirect`
     super().__init__(title, content, site_lang, silent=silent)
Пример #15
0
def read_lines(title):
    lines = load_page(title).split('\n')
    for line in lines:
        if not line:
            continue
        yield line
Пример #16
0
def save_new_page(title, content, desc='Заливка деепричастий'):
    try:
        load_page(title)
        return
    except NoPage:
        save_page(title, content, desc)