Exemplo n.º 1
0
def download_file(update, context, file_type):
    """
    This function downloads files from Telegram.
    :param update:
    :param context:
    :param file_type: `photo` or `voice`. Type of downloaded file.
    :return: old filename and new_filename if file_type is correct else False.
    filename - path to file, new_filename - filename with order number of file
    in database.
    """
    user_id = update.effective_user.id

    if file_type == 'voice':
        file_id = update.message.voice.file_id
        filename = f'{user_id}_voice.ogg'
        path = CONFIG['VOICE_FOLDER_PATH']
    elif file_type == 'photo':
        file_id = update.message.photo[-1].file_id
        filename = f'{user_id}_photo.jpg'
        path = CONFIG['PHOTO_FOLDER_PATH']
    else:
        return False

    new_file = context.bot.get_file(file_id)
    new_file.download(os.path.join(path, filename))

    conn, cursor = create_conn()

    new_filename = os.path.join(path, get_name(cursor, user_id, file_type,
                                               f'{file_type}_path'))

    close_conn(conn)

    return filename, new_filename
Exemplo n.º 2
0
def message_processing(update, context):
    """
    Function saves voice messages in wav format with simple rate 16MHz and
    photos if a face is detected there. All path store in database `bot`.
    :return: None
    """

    logger.info(f'Waiting for message_processing function for '
                f'{update.effective_user.name} at '
                f'{update.effective_message.date}')

    user_id = update.effective_user.id

    conn, cursor = create_conn()

    if update.message.voice:
        filename, new_filename = download_file(update, context, 'voice')
        new_filename = f'{new_filename}.wav'

        convert(os.path.join(CONFIG['VOICE_FOLDER_PATH'], filename),
                new_filename)

        insert_data(conn, cursor, 'voice', user_id, 'audio_path', new_filename)

        answer_text = 'Thanks, I\'ve saved this voice message to my database.'

    elif update.message.photo:
        filename, new_filename = download_file(update, context, 'photo')
        new_filename = f'{new_filename}.jpg'

        PHOTO_FOLDER_PATH = CONFIG['PHOTO_FOLDER_PATH']

        if check_face(f'{PHOTO_FOLDER_PATH}/{user_id}_photo.jpg',
                      new_filename):
            insert_data(conn, cursor, 'photo', user_id, 'photo_path',
                        new_filename)
            answer_text = ('I saved this photo in the database because I\'ve '
                           'detected the face here.')
        else:
            answer_text = ('I didn\'t save this photo in my database, because '
                           'I haven\'t found the face here.')

    else:
        context.bot.send_sticker(chat_id=update.effective_chat.id,
                                 sticker=CONFIG['STICKER_PATH'])
        answer_text = 'Send me a voice message or a photo, please.'

    context.bot.send_message(parse_mode=ParseMode.MARKDOWN,
                             chat_id=update.effective_chat.id,
                             text=answer_text)
    close_conn(conn)

    logger.info(f'Answer ready for {update.effective_user.name} '
                f'at {update.effective_message.date}')
Exemplo n.º 3
0
def db_sha1(domain, family, bookname):
    conn = db.create_conn(domain = domain, family = family)
    cursor = db.use_db(conn, domain, family)

    q = 'SELECT img_sha1 FROM image WHERE img_name = %s'
    cursor.execute(q, [bookname])
    data = cursor.fetchall()

    cursor.close()
    conn.close()

    return data[0][0] if len(data) else None
Exemplo n.º 4
0
def db_sha1(domain, family, bookname):
    conn = db.create_conn(domain=domain, family=family)
    cursor = db.use_db(conn, domain, family)

    q = 'SELECT img_sha1 FROM image WHERE img_name = %s'
    cursor.execute(q, [bookname])
    data = cursor.fetchall()

    cursor.close()
    conn.close()

    return data[0][0] if len(data) else None
Exemplo n.º 5
0
def get_images_credit(cursor, images):
    if not len(images):
        return []

    images = [x.replace(' ', '_') for x in images]
    results = []

    conn = db.create_conn(domain='commons', family='wiki')
    common_cursor = db.use_db(conn, 'commons', 'wiki')
    for r in get_images_credit_db(common_cursor, images):
        results.append(r[0])
    common_cursor.close()
    conn.close()

    for r in get_images_credit_db(cursor, images):
        results.append(r[0])

    return results
Exemplo n.º 6
0
def get_images_credit(cursor, images):
    if not len(images):
        return []

    images = [ x.replace(' ', '_') for x in images ]
    results = []

    conn = db.create_conn(domain = 'commons', family = 'wiki')
    common_cursor = db.use_db(conn, 'commons', 'wiki')
    for r in get_images_credit_db(common_cursor, images):
        results.append(r[0])
    common_cursor.close()
    conn.close()

    for r in get_images_credit_db(cursor, images):
        results.append(r[0])

    return results
def handle_scan_query(params, start_response):
    text = common_html.get_head(
        'pages without scan',
        css='shared.css').encode('utf-8') + '\n  <body>\n'

    if params['lang']:
        try:
            offset = int(params.get('offset', 0))
            limit = min(500, int(params.get('limit', 500)))
            lang = params['lang']
            conn = db.create_conn(domain=lang, family='wikisource')
            cursor = db.use_db(conn, domain=lang, family='wikisource')
            ns = ws_category.domain_urls[lang][0]
            page_ids = disamb_page(cursor) | page_with_scan(ns, cursor)
            all_p = all_pages(cursor)
            result = [(unicode(x[0], 'utf-8'), x[1]) for x in all_p
                      if x[2] not in page_ids]
            text += 'Total: ' + str(len(result)) + '<br />'
            next_link = prev_next_link(False, len(result), lang, limit, offset)
            prev_link = prev_next_link(True, len(result), lang, limit, offset)
            text += prev_link + '&#160;' + next_link + '<br /><br />'

            result = result[offset:offset + limit]
            for x in result:
                text += u'<a href="//%s.wikisource.org/wiki/%s">' % (
                    lang, x[0]) + x[0].replace('_', ' ') + u'</a>, ' + str(
                        x[1]) + u'<br />'

            text += u'<br />' + prev_link + '&#160;' + next_link
            cursor.close()
            conn.close()
            ret_code = '200 OK'
        except:
            utils.print_traceback()
            ret_code = '500 Internal Server Error'
            text = '<h1>' + ret_code + '</h1>'
    else:
        ret_code = '400 Bad Request'
        text = '<h1>' + ret_code + '</h1>'

    text += '  </body>\n</html>'

    return return_response(start_response, text.encode('utf-8'), False,
                           ret_code, 'text/html')
Exemplo n.º 8
0
def handle_scan_query(params, start_response):
    text = common_html.get_head("pages without scan", css="shared.css").encode("utf-8") + "\n  <body>\n"

    if params["lang"]:
        try:
            offset = int(params.get("offset", 0))
            limit = min(500, int(params.get("limit", 500)))
            lang = params["lang"]
            conn = db.create_conn(domain=lang, family="wikisource")
            cursor = db.use_db(conn, domain=lang, family="wikisource")
            ns = ws_category.domain_urls[lang][0]
            page_ids = disamb_page(cursor) | page_with_scan(ns, cursor)
            all_p = all_pages(cursor)
            result = [(unicode(x[0], "utf-8"), x[1]) for x in all_p if x[2] not in page_ids]
            text += "Total: " + str(len(result)) + "<br />"
            next_link = prev_next_link(False, len(result), lang, limit, offset)
            prev_link = prev_next_link(True, len(result), lang, limit, offset)
            text += prev_link + "&#160;" + next_link + "<br /><br />"

            result = result[offset : offset + limit]
            for x in result:
                text += (
                    u'<a href="//%s.wikisource.org/wiki/%s">' % (lang, x[0])
                    + x[0].replace("_", " ")
                    + u"</a>, "
                    + str(x[1])
                    + u"<br />"
                )

            text += u"<br />" + prev_link + "&#160;" + next_link
            cursor.close()
            conn.close()
            ret_code = "200 OK"
        except:
            utils.print_traceback()
            ret_code = "500 Internal Server Error"
            text = "<h1>" + ret_code + "</h1>"
    else:
        ret_code = "400 Bad Request"
        text = "<h1>" + ret_code + "</h1>"

    text += "  </body>\n</html>"

    return return_response(start_response, text.encode("utf-8"), False, ret_code, "text/html")
Exemplo n.º 9
0
def get_credit(domain, family, books, pages, images):
    conn = db.create_conn(domain=domain, family=family)
    ns = get_source_ns(domain, family)
    cursor = db.use_db(conn, domain, family)

    books_name = []
    results = {}
    for book in books:
        contribs = get_book_credit(domain, family, cursor, book, ns)
        merge_contrib(results, contribs)
        books_name.append(get_index_ns(domain, family) + ':' + book)

    contribs = get_pages_credit(cursor, pages + books_name, ns)
    merge_contrib(results, contribs)

    for user_name in get_images_credit(cursor, images):
        results.setdefault(user_name, default_userdict())
        results[user_name]['count'] += 1

    conn.close()
    cursor.close()

    return results
Exemplo n.º 10
0
def get_credit(domain, family, books, pages, images):
    conn = db.create_conn(domain = domain, family = family)
    ns = get_source_ns(domain, family)
    cursor = db.use_db(conn, domain, family)

    books_name = []
    results = {}
    for book in books:
        contribs = get_book_credit(domain, family, cursor, book, ns)
        merge_contrib(results, contribs)
        books_name.append(get_index_ns(domain, family) + ':' + book)

    contribs = get_pages_credit(cursor, pages + books_name, ns)
    merge_contrib(results, contribs)

    for user_name in get_images_credit(cursor, images):
        results.setdefault(user_name, default_userdict())
        results[user_name]['count'] += 1

    conn.close()
    cursor.close()

    return results
Exemplo n.º 11
0
def get_stats(domains):

    import urllib
    res = {}

    for dom in domains:
        print dom
        conn = db.create_conn(domain = dom, family = 'wikisource')
        cursor = db.use_db(conn, domain = dom, family = 'wikisource')
	ns = urls[dom][0]

	q="select /* SLOW_OK */ count(page_id) as num from page where page_namespace=%d and page_is_redirect=0"%ns
	cursor.execute(q)
	row = cursor.fetchone ()
        num_pages = int(row[0])

	if len(urls[dom])>1:
	    cat3 = urllib.unquote(urls[dom][1])
  	    cat4 = urllib.unquote(urls[dom][2])
	    cursor.execute(catreq(cat3,ns))
	    row = cursor.fetchall()[0]
            num_q3 = int(row[0])
	    cursor.execute(catreq(cat4,ns))
	    row = cursor.fetchall()[0]
            num_q4 = int(row[0])
	else:
	    num_q3 = 0
	    num_q4 = 0

	if len(urls[dom])>3:
	    cat0 = urls[dom][3]
  	    cat2 = urls[dom][4]
	    cursor.execute(catreq(cat0,ns))
	    row = cursor.fetchall()[0]
            num_q0 = int(row[0])
	    cursor.execute(catreq(cat2,ns))
	    row = cursor.fetchall()[0]
            num_q2 = int(row[0])
	else:
	    num_q0 = 0
	    num_q2 = 0

	q = "select /* SLOW_OK */ count(distinct tl_from) as num from templatelinks left join page on page_id=tl_from where tl_namespace=%d and page_namespace=0;"%ns
	cursor.execute(q)
	row = cursor.fetchone ()
        num_trans = int(row[0])

	cursor.execute ("select /* SLOW_OK */ count(distinct page_id) from page where page_namespace=0 and page_is_redirect=0;")
	row = cursor.fetchone ()
        num_texts = int(row[0])

        #disambiguation pages
        # first try the __DISAMBIG__ keyword
        cursor.execute("select count(page_title) from page where page_namespace = 0 and page_is_redirect = 0 and page_id in (select pp_page from page_props where pp_propname = 'disambiguation')")
        row = cursor.fetchone ()
        num_disambig = int(row[0])

        if num_disambig == 0:
            #then test if the message is a template...
            q = "select /* SLOW_OK */ count(page_title) from page left join templatelinks on page_id=tl_from where page_namespace=0 and tl_namespace=10 and tl_title in ( select pl_title from page left join pagelinks on page_id=pl_from where pl_namespace=10 and page_namespace=8 and page_title='Disambiguationspage' )"
            cursor.execute (q)
            row = cursor.fetchone ()
            num_disambig = int(row[0])

            if num_disambig==0 and disambiguations.get(dom) :
                q = "select /* SLOW_OK */ count(page_title) from page left join templatelinks on page_id=tl_from where page_namespace=0 and tl_namespace=10 and tl_title='%s'"%disambiguations.get(dom)
                cursor.execute (q)
                row = cursor.fetchone ()
                num_disambig = int(row[0])

        if dom=='no':
            import pywikibot
            qq = "select /* SLOW_OK */ page_title from page where page_namespace=0 and page_is_redirect=0 and page_id not in ( select distinct tl_from from templatelinks left join page on page_id=tl_from where tl_namespace=104 and page_namespace=0 ) and page_id not in ( %s );" % q.replace("count(page_title)","page_id")
            cursor.execute(qq)
            rows = cursor.fetchall()
	    site = pywikibot.getSite(dom,fam='wikisource')
            f = codecs.open(os.path.expanduser('~/public_html/data/nakedtexts_')+dom+'.html','w',"utf-8")
            f.write("<html><head></head><body>")
            f.write("<meta http-equiv=\"Content-Type\" content=\"text/html; charset=utf-8\" />")
            f.write("<b>Naked texts at "+dom+".wikisource.org</b> (%d)</br/>"%len(rows) )
            f.write("<ul>")
            for row in rows:
                pagename = row[0]
                page = pywikibot.Page(site, pagename.decode('utf8'))
                page_path = site.nice_get_address(page.title(asUrl = True))
                page_url = "http://"+dom+".wikisource.org"+page_path
                s="<li><a href=\"%s\">%s</a></li>"%(page_url,page.title())
                f.write(s)
            f.write("</ul>")
            f.write("</body>")
        
        res[dom] = (num_pages, num_q0, num_q2, num_q3, num_q4, num_trans, num_texts, num_disambig)
        
        cursor.close ()
        conn.close ()
    return res
Exemplo n.º 12
0
from time import *
import random

print('PRILER BOT')

log = logging.getLogger('aiogram')
logging.basicConfig(level=logging.INFO)

bot = Bot(token=token, parse_mode=ParseMode.MARKDOWN)

storage = MemoryStorage()
dp = Dispatcher(bot, storage=storage)

loop = asyncio.get_event_loop()

conn = loop.run_until_complete(create_conn(**DB))
prepared_query = loop.run_until_complete(gen_prepared_query(conn))


class CheckFilter(BoundFilter):
    key = 'is_admin'

    def __init__(self, is_admin):
        self.is_admin = is_admin

    async def check(self, message: types.Message):
        member = await bot.get_chat_member(message.chat.id,
                                           message.from_user.id)
        return member.is_chat_admin() == self.is_admin

Exemplo n.º 13
0
def get_stats(domains):

    import urllib
    res = {}

    for dom in domains:
        print dom
        conn = db.create_conn(domain=dom, family='wikisource')
        cursor = db.use_db(conn, domain=dom, family='wikisource')
        ns = urls[dom][0]

        q = "select /* SLOW_OK */ count(page_id) as num from page where page_namespace=%d and page_is_redirect=0" % ns
        cursor.execute(q)
        row = cursor.fetchone()
        num_pages = int(row[0])

        if len(urls[dom]) > 1:
            cat3 = urllib.unquote(urls[dom][1])
            cat4 = urllib.unquote(urls[dom][2])
            cursor.execute(catreq(cat3, ns))
            row = cursor.fetchall()[0]
            num_q3 = int(row[0])
            cursor.execute(catreq(cat4, ns))
            row = cursor.fetchall()[0]
            num_q4 = int(row[0])
        else:
            num_q3 = 0
            num_q4 = 0

        if len(urls[dom]) > 3:
            cat0 = urls[dom][3]
            cat2 = urls[dom][4]
            cursor.execute(catreq(cat0, ns))
            row = cursor.fetchall()[0]
            num_q0 = int(row[0])
            cursor.execute(catreq(cat2, ns))
            row = cursor.fetchall()[0]
            num_q2 = int(row[0])
        else:
            num_q0 = 0
            num_q2 = 0

        q = "select /* SLOW_OK */ count(distinct tl_from) as num from templatelinks left join page on page_id=tl_from where tl_namespace=%d and page_namespace=0;" % ns
        cursor.execute(q)
        row = cursor.fetchone()
        num_trans = int(row[0])

        cursor.execute(
            "select /* SLOW_OK */ count(distinct page_id) from page where page_namespace=0 and page_is_redirect=0;"
        )
        row = cursor.fetchone()
        num_texts = int(row[0])

        #disambiguation pages
        # first try the __DISAMBIG__ keyword
        cursor.execute(
            "select count(page_title) from page where page_namespace = 0 and page_is_redirect = 0 and page_id in (select pp_page from page_props where pp_propname = 'disambiguation')"
        )
        row = cursor.fetchone()
        num_disambig = int(row[0])

        if num_disambig == 0:
            #then test if the message is a template...
            q = "select /* SLOW_OK */ count(page_title) from page left join templatelinks on page_id=tl_from where page_namespace=0 and tl_namespace=10 and tl_title in ( select pl_title from page left join pagelinks on page_id=pl_from where pl_namespace=10 and page_namespace=8 and page_title='Disambiguationspage' )"
            cursor.execute(q)
            row = cursor.fetchone()
            num_disambig = int(row[0])

            if num_disambig == 0 and disambiguations.get(dom):
                q = "select /* SLOW_OK */ count(page_title) from page left join templatelinks on page_id=tl_from where page_namespace=0 and tl_namespace=10 and tl_title='%s'" % disambiguations.get(
                    dom)
                cursor.execute(q)
                row = cursor.fetchone()
                num_disambig = int(row[0])

        if dom == 'no':
            import pywikibot
            qq = "select /* SLOW_OK */ page_title from page where page_namespace=0 and page_is_redirect=0 and page_id not in ( select distinct tl_from from templatelinks left join page on page_id=tl_from where tl_namespace=104 and page_namespace=0 ) and page_id not in ( %s );" % q.replace(
                "count(page_title)", "page_id")
            cursor.execute(qq)
            rows = cursor.fetchall()
            site = pywikibot.getSite(dom, fam='wikisource')
            f = codecs.open(
                os.path.expanduser('~/public_html/data/nakedtexts_') + dom +
                '.html', 'w', "utf-8")
            f.write("<html><head></head><body>")
            f.write(
                "<meta http-equiv=\"Content-Type\" content=\"text/html; charset=utf-8\" />"
            )
            f.write("<b>Naked texts at " + dom +
                    ".wikisource.org</b> (%d)</br/>" % len(rows))
            f.write("<ul>")
            for row in rows:
                pagename = row[0]
                page = pywikibot.Page(site, pagename.decode('utf8'))
                page_path = site.nice_get_address(page.title(asUrl=True))
                page_url = "http://" + dom + ".wikisource.org" + page_path
                s = "<li><a href=\"%s\">%s</a></li>" % (page_url, page.title())
                f.write(s)
            f.write("</ul>")
            f.write("</body>")

        res[dom] = (num_pages, num_q0, num_q2, num_q3, num_q4, num_trans,
                    num_texts, num_disambig)

        cursor.close()
        conn.close()
    return res
Exemplo n.º 14
0
def open_db(domain, family, cursor_class = None):
    conn = db.create_conn(domain = domain, family = family)
    cursor = db.use_db(conn, domain, family, cursor_class)

    return conn, cursor
Exemplo n.º 15
0
def open_db(domain, family, cursor_class=None):
    conn = db.create_conn(domain=domain, family=family)
    cursor = db.use_db(conn, domain, family, cursor_class)

    return conn, cursor