def list_fonts():
u = 'http://sofia.nmsu.edu/~mleisher/Software/cu/'
collector = html_link_collector()
with io.open(acquire(u, 'local'), mode='r', encoding='utf-8') as f:
for line in f:
collector.feed(line)
collector.close()
for link in collector.links:
if link.endswith('.tgz'):
# hack for broken link as of Feb 2019
link = link.replace('www.math.nmsu.edu', 'sofia.nmsu.edu')
with tarfile.open(acquire(link, 'local'), 'r') as tar:
for name in tar.getnames():
if name.endswith('.bdf'):
tar.extract(name, cache_path())
path = os.path.join(cache_path(), name)
name = name.split('/')[-1][:-4]
with open(path, 'r') as bdf:
for line in bdf:
if line.startswith('FAMILY_NAME'):
name = line[11:].strip()
if name.startswith('"') and name.endswith(
'"'):
name = name[1:-1]
yield (name, path, u)
def list_fonts():
u = 'https://apagreekkeys.org/NAUdownload.html'
collector = html_link_collector()
with io.open(acquire(u, 'local'), mode='r', encoding='utf-8') as f:
for line in f:
collector.feed(line)
collector.close()
latestDate = None
latestLink = None
for link in collector.links:
m = re.search('/NAU([0-9_]+)[.]zip$', link)
if m is not None:
if latestDate is None or m.group(1) > latestDate:
latestDate = m.group(1)
latestLink = link
with zipfile.ZipFile(
acquire('https://apagreekkeys.org/' + latestLink, 'local'),
'r') as zip:
for info in zip.infolist():
if info.filename.endswith('.ttf'):
name = info.filename.split('/')[-1][:-4]
name = re.sub('newathu', 'New Athena Unicode', name)
name = re.sub('([a-z])([A-Z])', '\\1 \\2', name)
name = re.sub('[0-9_]+', '', name)
yield (name, zip.extract(info, cache_path()), u)
def list_fonts():
u = 'http://users.teilar.gr/~g1951d/'
collector = html_link_collector()
with io.open(acquire(u, 'local'), mode='r', encoding='utf16') as f:
for line in f:
collector.feed(line)
collector.close()
for link in collector.links:
if link.endswith('.zip'):
with zipfile.ZipFile(acquire(u + link, 'local'), 'r') as zip:
for info in zip.infolist():
if 'hint' not in info.filename and info.filename.endswith(
'.ttf'):
name = info.filename[:-4].split('/')[-1]
yield (name, zip.extract(info, cache_path()), u)
def list_fonts():
u = 'http://unifoundry.com/unifont/index.html'
collector = html_link_collector()
with io.open(acquire(u, 'local'), mode='r', encoding='iso-8859-1') as f:
for line in f:
collector.feed(line)
collector.close()
for link in collector.links:
if 'sample' not in link and link.endswith('.ttf'):
name = link.split('/')[-1].split('-')[0]
name = re.sub('unifont', 'Unifont', name)
name = re.sub('upper', 'Upper', name)
name = re.sub('csur', 'CSUR', name)
name = re.sub('_', ' ', name)
link = 'http://unifoundry.com' + link
yield (name, acquire(link, 'local'), u)
def list_fonts():
u = 'https://www.kurinto.com/'
collector = html_link_collector()
with io.open(acquire(u + 'download.htm', 'local'),
mode='r',
encoding='utf-8') as f:
for line in f:
collector.feed(line)
collector.close()
for link in collector.links:
if link.endswith('_Full.zip'):
with zipfile.ZipFile(acquire(u + link, 'local'), 'r') as zip:
for info in zip.infolist():
if info.filename.endswith('-Rg.ttf'):
name = info.filename[:-7].split('/')[-1]
yield (name, zip.extract(info, cache_path()), u)
def list_fonts():
yield ('Alco Sans', acquire('http://www.kreativekorp.com/lib/font/AlcoSans.ttf', 'local'), 'http://www.kreativekorp.com/software/fonts/alco.shtml')
yield ('Constructium', acquire('http://www.kreativekorp.com/lib/font/Constructium.ttf', 'local'), 'http://www.kreativekorp.com/software/fonts/constructium.shtml')
yield ('Fairfax', acquire('http://www.kreativekorp.com/lib/font/Fairfax.ttf', 'local'), 'http://www.kreativekorp.com/software/fonts/fairfax.shtml')
yield ('Fairfax Bold', acquire('http://www.kreativekorp.com/lib/font/FairfaxBold.ttf', 'local'), 'http://www.kreativekorp.com/software/fonts/fairfax.shtml')
yield ('Fairfax Italic', acquire('http://www.kreativekorp.com/lib/font/FairfaxItalic.ttf', 'local'), 'http://www.kreativekorp.com/software/fonts/fairfax.shtml')
yield ('Fairfax Serif', acquire('http://www.kreativekorp.com/lib/font/FairfaxSerif.ttf', 'local'), 'http://www.kreativekorp.com/software/fonts/fairfax.shtml')
yield ('Fairfax HD', acquire('http://www.kreativekorp.com/lib/font/FairfaxHD.ttf', 'local'), 'http://www.kreativekorp.com/software/fonts/fairfaxhd.shtml')
yield ('Kreative Square', acquire('http://www.kreativekorp.com/lib/font/KreativeSquare.ttf', 'local'), 'http://www.kreativekorp.com/software/fonts/ksquare.shtml')
def list_vendors():
vip = __vendor_id_index_parser()
with io.open(acquire('https://docs.microsoft.com/en-us/typography/vendors/', 'local'), mode='r', encoding='utf-8') as f:
for line in f:
vip.feed(line)
vip.close()
for vendor in vip.vendors:
yield vendor
def list_fonts():
with zipfile.ZipFile(
acquire('https://umihotaru.work/nishiki-teki.zip', 'local'),
'r') as zip:
for info in zip.infolist():
if info.filename.endswith('.ttf'):
yield ('Nishiki-teki', zip.extract(info, cache_path()),
'https://umihotaru.work/')
def list_fonts():
u = 'https://www.google.com/get/noto/'
collector = html_link_collector()
with io.open(acquire(u, 'local'), mode='r', encoding='utf-8') as f:
for line in f:
collector.feed(line)
collector.close()
for link in collector.links:
if '/Noto-' not in link and link.endswith('.zip'):
with zipfile.ZipFile(acquire(link, 'local'), 'r') as zip:
for info in zip.infolist():
if info.filename.endswith(
'.ttf') or info.filename.endswith('.otf'):
name = info.filename[:-4]
name = re.sub('([a-z])([A-Z])', '\\1 \\2', name)
name = re.sub('-Regular', '', name)
name = re.sub('-', ' ', name)
yield (name, zip.extract(info, cache_path()), u)
def list_fonts():
with zipfile.ZipFile(
acquire('http://www.evertype.com/emono/evermono.zip', 'local'),
'r') as zip:
for info in zip.infolist():
if '._' not in info.filename and info.filename.endswith('.ttf'):
yield (info.filename[:-4].split('/')[-1],
zip.extract(info, cache_path()),
'http://www.evertype.com/emono/')
def list_fonts():
u = 'https://design.ubuntu.com/font/'
collector = html_link_collector()
with io.open(acquire(u, 'local', compressed=True), mode='r', encoding='iso-8859-1') as f:
for line in f:
collector.feed(line)
collector.close()
for link in collector.links:
if link.endswith('.zip'):
with zipfile.ZipFile(acquire(link, 'local'), 'r') as zip:
for info in zip.infolist():
if '__MACOSX' in info.filename:
continue
if info.filename.endswith('.ttf'):
name = info.filename.split('/')[-1][:-4]
name = re.sub('([a-z])([A-Z])', '\\1 \\2', name)
name = re.sub('-', ' ', name)
yield (name, zip.extract(info, cache_path()), u)
break
def list_fonts():
for code in [
'GA', 'GB', 'GC', 'GD', 'GE', 'GF', 'GH', 'GK', 'GV', 'GW', 'MA',
'MB', 'MC', 'MD', 'ME', 'MF', 'MH', 'MK', 'MV', 'MW', 'VB', 'VF',
'VN'
]:
name = 'Kreative Vexillo %s' % code
url = 'https://github.com/kreativekorp/vexillo/raw/master/fonts/Vexillo/Vexillo%s.ttf.sbix.ttf' % code
yield (name, acquire(url, 'local'),
'https://github.com/kreativekorp/vexillo')
def list_fonts():
u = 'http://junicode.sourceforge.net/'
du = 'https://sourceforge.net/projects/junicode/files/latest/download'
with zipfile.ZipFile(acquire(du, 'local', None), 'r') as zip:
for info in zip.infolist():
if info.filename.endswith('.ttf'):
name = info.filename.split('/')[-1][:-4]
name = re.sub('([a-z])([A-Z])', '\\1 \\2', name)
name = re.sub('-', ' ', name)
yield (name, zip.extract(info, cache_path()), u)
def list_fonts():
for name in ['fluorine', 'fluorinem']:
with zipfile.ZipFile(
acquire(
'http://www.kreativekorp.com/swdownload/fonts/relay/%s.zip'
% name, 'local'), 'r') as zip:
for info in zip.infolist():
if info.filename.endswith('.ttf'):
yield (info.filename[:-4], zip.extract(info, cache_path()),
'http://www.kreativekorp.com/software/fonts/')
def list_fonts():
u = 'https://dejavu-fonts.github.io/'
du = 'https://dejavu-fonts.github.io/Download.html'
collector = html_link_collector()
with io.open(acquire(du, 'local'), mode='r', encoding='utf-8') as f:
for line in f:
collector.feed(line)
collector.close()
for link in collector.links:
bn = link.split('/')[-1]
if bn.startswith('dejavu-fonts-ttf') and bn.endswith('.zip'):
with zipfile.ZipFile(acquire(link, 'local', None), 'r') as zip:
for info in zip.infolist():
if info.filename.endswith('.ttf'):
name = info.filename.split('/')[-1][:-4]
name = re.sub('([a-z])([A-Z])', '\\1 \\2', name)
name = re.sub('Deja Vu', 'DejaVu', name)
name = re.sub('-', ' ', name)
yield (name, zip.extract(info, cache_path()), u)
def list_fonts():
u = 'https://pagure.io/liberation-fonts'
collector = html_link_collector()
with io.open(acquire(u, 'local'), mode='r', encoding='utf-8') as f:
for line in f:
collector.feed(line)
collector.close()
for link in collector.links:
if '-ttf-' in link and link.endswith('.tar.gz'):
with tarfile.open(acquire(link, 'local'), 'r') as tar:
for name in tar.getnames():
if name.endswith('.ttf'):
tar.extract(name, cache_path())
path = os.path.join(cache_path(), name)
name = name.split('/')[-1][:-4]
name = re.sub('([a-z])([A-Z])', '\\1 \\2', name)
name = re.sub('-', ' ', name)
yield (name, path, u)
break
def list_fonts():
with zipfile.ZipFile(
acquire(
'http://www.kreativekorp.com/swdownload/fonts/xlang/voynich.zip',
'local'), 'r') as zip:
for info in zip.infolist():
if info.filename.endswith('.ttf'):
yield (
info.filename[:-4], zip.extract(info, cache_path()),
'http://www.kreativekorp.com/software/fonts/voynich.shtml')
def list_fonts():
for id in ['source-code-pro', 'source-sans-pro', 'source-serif-pro']:
u = 'https://github.com/adobe-fonts/' + id
collector = html_link_collector()
with io.open(acquire(u + '/releases', 'local'),
mode='r',
encoding='utf-8') as f:
for line in f:
collector.feed(line)
collector.close()
for link in collector.links:
if link.endswith('.ttf') or link.endswith('.otf'):
du = 'https://github.com' + link
name = link.split('/')[-1][:-4]
name = re.sub('([a-z])([A-Z])', '\\1 \\2', name)
name = re.sub('( *Variable)?-(Roman)?', ' Pro ', name)
yield (name.strip(), acquire(du, 'local'), u)
elif link.endswith('.zip') or link.endswith('.tar.gz'):
break
def list_entities():
with io.open(acquire('https://dev.w3.org/html5/html-author/charref',
'local'),
mode='r',
encoding='utf-8') as f:
for line in f:
dm = __dec_matcher.search(line)
if dm is not None:
cp = int(dm.group(1))
nm = __named_matcher.search(line)
if nm is not None:
yield cp, '&' + nm.group(1) + ';'
def list_fonts():
bu = 'http://scholarsfonts.net/'
u = bu + 'cardofnt.html'
collector = html_link_collector()
with io.open(acquire(u, 'local'), mode='r', encoding='windows-1252') as f:
for line in f:
collector.feed(line)
collector.close()
for link in collector.links:
if link.endswith('.zip'):
with zipfile.ZipFile(acquire(bu + link, 'local'), 'r') as zip:
for info in zip.infolist():
if info.filename.endswith('.ttf'):
name = info.filename[:-4].split('/')[-1]
if name.startswith('Cardob'):
name = 'Cardo Bold'
elif name.startswith('Cardoi'):
name = 'Cardo Italic'
else:
name = 'Cardo'
yield (name, zip.extract(info, cache_path()), u)
break
def list_fonts():
visited = []
mu = 'https://www.babelstone.co.uk/Fonts/'
mc = html_link_collector()
with io.open(acquire(mu, 'local'), mode='r', encoding='utf-8') as f:
for line in f:
mc.feed(line)
mc.close()
for ml in mc.links:
if '/' not in ml and ml.endswith('.html') and ml not in visited:
visited.append(ml)
u = mu + ml
c = html_link_collector()
with io.open(acquire(u, 'local'), mode='r', encoding='utf-8') as f:
for line in f:
c.feed(line)
c.close()
for l in c.links:
if l.endswith('.ttf') and l not in visited:
visited.append(l)
name = l.split('/')[-1][:-4]
name = re.sub('([a-z])([A-Z])', '\\1 \\2', name)
yield (name.strip(), acquire(mu + l, 'local'), u)
def list_fonts():
u = 'http://savannah.gnu.org/projects/freefont/'
du = 'http://ftp.gnu.org/gnu/freefont/'
collector = html_link_collector()
with io.open(acquire(du, 'local'), mode='r', encoding='utf-8') as f:
for line in f:
collector.feed(line)
collector.close()
latestDate = None
latestLink = None
for link in collector.links:
m = re.match('^freefont-[ot]tf-([0-9]+)[.]zip$', link)
if m is not None:
if latestDate is None or m.group(1) > latestDate:
latestDate = m.group(1)
latestLink = link
with zipfile.ZipFile(acquire(du + latestLink, 'local'), 'r') as zip:
for info in zip.infolist():
if info.filename.endswith('.ttf') or info.filename.endswith(
'.otf'):
name = info.filename.split('/')[-1][:-4]
name = re.sub('([a-z])([A-Z])', '\\1 \\2', name)
name = re.sub('Free (Sans|Serif|Mono)', 'Free\\1', name)
yield (name, zip.extract(info, cache_path()), u)
def list_fonts():
for name in ['pr', 'petme']:
with zipfile.ZipFile(
acquire(
'http://www.kreativekorp.com/swdownload/fonts/retro/%s.zip'
% name, 'local'), 'r') as zip:
for info in zip.infolist():
if info.filename.endswith('.ttf'):
name = info.filename[:-4]
name = re.sub('PrintChar', 'Print Char ', name)
name = re.sub('PRNumber', 'PR Number ', name)
name = re.sub('PetMe', 'Pet Me ', name)
name = re.sub('(64|128)(2X|2Y)', '\\1 \\2', name)
yield (name.strip(), zip.extract(info, cache_path()),
'http://www.kreativekorp.com/software/fonts/')
def list_files():
parser = html_table_parser()
with io.open(acquire('https://msdn.microsoft.com/en-us/library/windows/desktop/dd317756.aspx', 'local'), mode='r', encoding='utf-8') as f:
for line in f:
parser.feed(line)
parser.close()
path = charset_path('identifiers', 'codepages-microsoft.txt')
with io.open(path, mode='w', encoding='utf-8') as f:
print(u'@codepage\t@charset', file=f)
for row in parser.rows:
if re.match('[0-9]+', row[0]):
id = int(row[0])
cs = row[1] if row[1] else '--'
name = row[2]
if (id < 100):
print(u'%03d\t%s\t# %s' % (id, cs, name), file=f)
else:
print(u'%d\t%s\t# %s' % (id, cs, name), file=f)
yield ('codepages-microsoft.txt', path)
def list_fonts():
for name in ['magdalena', 'mcmillen', 'mischke', 'monterey']:
with zipfile.ZipFile(acquire('http://www.kreativekorp.com/swdownload/fonts/relaybm/%s.zip' % name, 'local'), 'r') as zip:
for info in zip.infolist():
if info.filename.endswith('.ttf'):
yield (re.sub('Bold', ' Bold', info.filename[:-4]), zip.extract(info, cache_path()), 'http://www.kreativekorp.com/software/fonts/')
def verify(path):
url = None
map = {}
for line in expand(path):
u = __verify_matcher.match(line)
if u is not None:
url = u
else:
b, c, ba, ca = split_mapline(line)
if b is not None and c is not None:
if not ba or tuple(b) not in map:
map[tuple(b)] = tuple(c)
if url is None:
return None
else:
expmap = {}
with open(acquire(url, 'local'), 'r') as f:
for line in f:
# Hacks for reference encodings: JIS X 0208 has three columns.
if url.endswith('/MAPPINGS/OBSOLETE/EASTASIA/JIS/JIS0208.TXT'):
m = __jis_x_0208_matcher.match(line)
if m is not None:
line = line[:m.start(1)] + m.group(2) + '\t' + m.group(
3) + line[m.end(3):]
# Hacks for reference encodings: Adobe reverses bytes and chars.
if '/MAPPINGS/VENDORS/ADOBE/' in url:
m = __adobe_line_matcher.match(line)
if m is not None:
if (int(m.group(2), 16), ) in expmap:
continue
elif url.endswith('/symbol.txt') and m.group(
1) == '00B5' and m.group(2) == '6D':
continue
else:
line = line[:m.start(1)] + '0x' + m.group(
2) + '\t0x' + m.group(1) + line[m.end(2):]
# Hacks for reference encodings: Bytes delimited by +0x.
m = __delimited_byte_matcher.match(line)
if m is not None:
line = line[:m.start(1)] + __delimited_byte_sub.sub(
'', m.group(1)) + line[m.end(1):]
# Hacks for reference encodings: Odd number of hex digits in bytes.
line = __odd_hex_digits_sub.sub('\\g<1>0\\g<2>', line)
# Hacks for reference encodings: Apple's <LR> and <RL> markup.
line = __apple_lr_sub.sub('\\g<1>0x202D\\g<2>+0x202C', line)
line = __apple_rl_sub.sub('\\g<1>0x202E\\g<2>+0x202C', line)
# End hacks.
b, c, ba, ca = split_mapline(line)
if b is not None and c is not None:
expmap[tuple(b)] = tuple(c)
if not url.endswith('/MAPPINGS/OBSOLETE/EASTASIA/OTHER/CNS11643.TXT'):
# Hacks for reference encodings: No ASCII characters.
if all((x, ) not in expmap and (x, x) not in expmap
for x in range(0, 128)):
for x in range(0, 128):
expmap[(x, )] = (x, )
# Hacks for reference encodings: No C0 control characters.
if all((x, ) not in expmap and (x, x) not in expmap
for x in range(0, 32) + [127]):
for x in range(0, 32) + [127]:
expmap[(x, )] = (x, )
# Hacks for reference encodings: No C1 control characters.
if '/MAPPINGS/VENDORS/ADOBE/' in url or '/MAPPINGS/OBSOLETE/EASTASIA/' in url:
if any((x, ) in expmap
for x in range(160, 256)) or url.endswith('/BIG5.TXT'):
if all((x, ) not in expmap and (x, x) not in expmap
for x in range(128, 160)):
for x in range(128, 160):
expmap[(x, )] = (x, )
# Hacks for reference encodings: Undefined characters mapped to U+FFFD.
for k, v in expmap.items():
if v == (0xFFFD, ):
del expmap[k]
# End hacks.
return set(map.items()) ^ set(expmap.items())
def list_fonts():
yield ('Catrinity',
acquire('http://catrinity-font.de/downloads/Catrinity.otf',
'local'), 'http://catrinity-font.de/')
def list_fonts():
yield ('Conlang Unicode',
acquire('http://dedalvs.free.fr/writing/ConlangUnicode.ttf',
'local'), None)
def list_fonts():
yield ('Neoletters',
acquire('http://www.orenwatson.be/neoletters.ttf',
'local'), 'http://www.orenwatson.be/fontdemo.htm')
def list_files():
parser = html_table_parser()
with io.open(acquire(
'https://www-01.ibm.com/software/globalization/cs/cs_gcsgid.html',
'local'),
mode='r',
encoding='utf-8') as f:
for line in f:
parser.feed(line)
parser.close()
path = charset_path('identifiers', 'ibm-gcsgid.txt')
with io.open(path, mode='w', encoding='utf-8') as f:
for row in parser.rows:
if row[0] != 'GCSGID':
id = int(row[0])
name = row[1]
print(u'%05d\t%04X\t%s' % (id, id, name), file=f)
yield ('ibm-gcsgid.txt', path)
parser = html_table_parser()
with io.open(acquire(
'https://www-01.ibm.com/software/globalization/cp/cp_cpgid.html',
'local'),
mode='r',
encoding='utf-8') as f:
for line in f:
parser.feed(line)
parser.close()
path = charset_path('identifiers', 'ibm-cpgid.txt')
with io.open(path, mode='w', encoding='utf-8') as f:
for row in parser.rows:
if row[0] != 'CPGID':
id = int(row[0])
name = row[1]
print(u'%05d\t%04X\t%s' % (id, id, name), file=f)
yield ('ibm-cpgid.txt', path)
parser = html_table_parser()
with io.open(acquire(
'https://www-01.ibm.com/software/globalization/ccsid/ccsid_registered.html',
'local'),
mode='r',
encoding='utf-8') as f:
for line in f:
parser.feed(line)
parser.close()
path = charset_path('identifiers', 'ibm-ccsid.txt')
with io.open(path, mode='w', encoding='utf-8') as f:
for row in parser.rows:
if not row[0].startswith('CCSID'):
id = int(row[0])
name = row[2]
print(u'%05d\t%04X\t%s' % (id, id, name), file=f)
yield ('ibm-ccsid.txt', path)
path = charset_path('identifiers', 'codepages-ibm.txt')
with io.open(path, mode='w', encoding='utf-8') as f:
print(u'@codepage', file=f)
for row in parser.rows:
if not row[0].startswith('CCSID'):
id = int(row[0])
name = row[2]
if (id < 100):
print(u'%03d\t# %s' % (id, name), file=f)
else:
print(u'%d\t# %s' % (id, name), file=f)
yield ('codepages-ibm.txt', path)
