telnettext: ORF Teletext HTML to ANSI

2022-07-12

Previous post: The VEXX File Format
Next post: PyOtherSide 1.6.0 released

A small script to convert the HTML version of ORF Teletext into ANSI escape sequences so that you can browse teletext from your terminal.

You can also download the script here: telnettext

#!/usr/bin/env python3
#
# telnettext: ORF Teletext HTML to ANSI
# Copyright (C) 2022 Thomas Perl <m@thp.io>
#
# This program is free software; you can redistribute it and/or
# modify it under the terms of the GNU General Public License
# as published by the Free Software Foundation; either version 2
# of the License, or (at your option) any later version.
#
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
# GNU General Public License for more details.
#
# You should have received a copy of the GNU General Public License
# along with this program; if not, write to the Free Software
# Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.
#

"""
This tool parses the HTML pages at text.orf.at and converts
them to ANSI escape sequences to be read in your terminal.

---------

Commands understood in --interactive/-i mode:

    [channel:]000[.0] .... Navigate to channel, page, subpage
    j .................... Go to next page
    k .................... Go to previous page
    h .................... Go to previous subpage
    l .................... Go to next subpage
    p .................... Go back one page in history
    q .................... Exit interactive mode


Examples:

    orfiii:100 ........... Go to ORFIII, page 100
    100.3 ................ Go to page 100, subpage 3
    orf1: ................ Switch channel to ORF1
    .4 ................... Go to subpage 4
    200 .................. Go to page 100, subpage 1

"""

import re
import argparse
import html.parser
import urllib.request

parser = argparse.ArgumentParser(description='ORF Teletext HTML to ANSI')
parser.add_argument('page', type=int, nargs='?', default=100, help='Page number (e.g. 100 or 886)')
parser.add_argument('sub', type=int, nargs='?', default=1, help='Sub-page number (e.g. 1)')
parser.add_argument('--channel', '-c', type=str, nargs='?', default='orf1',
                    help='Channel (orf1, orf2, orfiii, sportplus)')
parser.add_argument('--interactive', '-i', action='store_true', help='Interactive browsing mode')
args = parser.parse_args()

colormap = {
    'black': 30,
    'red': 31,
    'green': 32,
    'yellow': 33,
    'blue': 34,
    'magenta': 35,
    'cyan': 36,
    'white': 37,
}

for k, v in dict(colormap).items():
    colormap[f'G{k}'] = v

class TeletextHTMLParser(html.parser.HTMLParser):
    def __init__(self):
        super().__init__()
        self.path = []
        self.pagewrapper = False

    def handle_starttag(self, tag, attrs):
        a = dict(attrs)

        if tag == 'div' and a.get('id') == 'pagewrapper':
            self.pagewrapper = True

        self.path.append((tag, a))
        if self.pagewrapper:
            if tag == 'div' and a.get('class') == 'line':
                print()  # newline
            if tag == 'div' and a.get('class') == 'run':
                bg = a['data-bg']
                fg = a['data-fg']
                fgi = colormap[fg]
                bgi = colormap[bg] + 10
                print(end='\033[%d;%dm' % (fgi, bgi))
                if a.get('data-flash') == 'true':
                    # https://www.real-world-systems.com/docs/ANSIcode.html#bridim
                    print(end='\033[5m')
                if a.get('data-size') == 'double size':
                    print(end='\033#3')  # TODO: Store + print next line with #4
                if a.get('data-size') == 'double width':
                    print(end='\033#6')  # FIXME: Non-double-width prefix/suffix not handled
                if a.get('data-size') == 'double height':
                    ...  # TODO: ANSI seems to not support single-width, double-height

    def handle_endtag(self, tag):
        _, a = self.path.pop()
        if tag == 'div' and a.get('class') == 'run':
            print(end='\033[0m')
        if tag == 'div' and a.get('id') == 'pagewrapper':
            self.pagewrapper = False
            print()  # newline

    def handle_data(self, data):
        if self.pagewrapper:
            tag, a = self.path[-1]
            if (tag == 'div' and a.get('class') == 'run') or (tag == 'a'):
                if a.get('data-charcode') is not None:
                    assert a['data-charcode'][-1] == 'h'
                    codepoint = int(a['data-charcode'][:-1], 16)

                    # https://text.orf.at/channel/orf1/page/886/1.html
                    # https://en.wikipedia.org/wiki/Teletext_character_set
                    if codepoint >= 0x20 and codepoint <= 0x2F:
                        data = ' ๐Ÿฌ€๐Ÿฌ๐Ÿฌ‚๐Ÿฌƒ๐Ÿฌ„๐Ÿฌ…๐Ÿฌ†๐Ÿฌ‡๐Ÿฌˆ๐Ÿฌ‰๐ŸฌŠ๐Ÿฌ‹๐ŸฌŒ๐Ÿฌ๐ŸฌŽ'[codepoint - 0x20]
                    elif codepoint >= 0x30 and codepoint <= 0x3F:
                        data = '๐Ÿฌ๐Ÿฌ๐Ÿฌ‘๐Ÿฌ’๐Ÿฌ“โ–Œ๐Ÿฌ”๐Ÿฌ•๐Ÿฌ–๐Ÿฌ—๐Ÿฌ˜๐Ÿฌ™๐Ÿฌš๐Ÿฌ›๐Ÿฌœ๐Ÿฌ'[codepoint - 0x30]
                    elif codepoint >= 0x60 and codepoint <= 0x6F:
                        data = '๐Ÿฌž๐ŸฌŸ๐Ÿฌ ๐Ÿฌก๐Ÿฌข๐Ÿฌฃ๐Ÿฌค๐Ÿฌฅ๐Ÿฌฆ๐Ÿฌงโ–๐Ÿฌจ๐Ÿฌฉ๐Ÿฌช๐Ÿฌซ๐Ÿฌฌ'[codepoint - 0x60]
                    elif codepoint >= 0x70 and codepoint <= 0x7F:
                        data = '๐Ÿฌญ๐Ÿฌฎ๐Ÿฌฏ๐Ÿฌฐ๐Ÿฌฑ๐Ÿฌฒ๐Ÿฌณ๐Ÿฌด๐Ÿฌต๐Ÿฌถ๐Ÿฌท๐Ÿฌธ๐Ÿฌน๐Ÿฌบ๐Ÿฌปโ–ˆ'[codepoint - 0x70]
                    else:
                        raise ValueError(codepoint)

                print(data, end='')


page = args.page
sub = args.sub
channel = args.channel

history = []

while True:
    history.append((page, sub))

    print(f'\033[2J\033[Htelnettext {channel}:{page:03d}.{sub} [2022 thp.io]')

    try:
        f = urllib.request.urlopen(f'https://text.orf.at/channel/{channel}/page/{page}/{sub}.html')
        d = f.read().decode()

        parser = TeletextHTMLParser()
        parser.feed(d)
    except urllib.error.HTTPError as e:
        print(f'HTTP Error: {e}')

    if not args.interactive:
        break

    d = input('([channel:]000[.0]|hjklpq|help)> ')
    if not d:
        break

    if d == 'help':
        print(__doc__)
        input('press any key to continue')

    m = re.match(r'^(?:(orf1|orf2|orfiii|sportplus)?[:])?(?:(?:(\d{3}))?(?:[.](\d+))?)?$', d)
    if m is not None:
        channel = m.group(1) or channel
        page = int(m.group(2) or page)
        if m.group(2) is not None:
            sub = 1
        sub = int(m.group(3) or sub)

    if d == 'q':
        break

    if d == 'h':
        sub = max(1, sub - 1)
    elif d == 'j':
        page += 1
    elif d == 'k':
        page -= 1
    elif d == 'l':
        sub += 1
    elif d == 'p' and len(history) > 1:
        history.pop()
        page, sub = history.pop()

    page = max(100, min(999, page))
    sub = max(1, sub)

Continue reading: PyOtherSide 1.6.0 released
Thomas Perl ยท 2022-07-12