def test_invalid_rfc3339_timestamps(self):
"""
Validate that datetime strings that are valid ISO 8601 but invalid RFC
3339 trigger a ValueError when passed to RFC 3339, and that this
ValueError explicitly mentions RFC 3339.
"""
for timestamp in [
"2018-01-02", # Missing mandatory time
"2018-01-02T03", # Missing mandatory minute and second
"2018-01-02T03Z", # Missing mandatory minute and second
"2018-01-02T03:04", # Missing mandatory minute and second
"2018-01-02T03:04Z", # Missing mandatory minute and second
"2018-01-02T03:04:01+04", # Missing mandatory offset minute
"2018-01-02T03:04:05", # Missing mandatory offset
"2018-01-02T03:04:05.12345", # Missing mandatory offset
"2018-01-02T24:00:00Z", # 24:00:00 is not valid in RFC 3339
'20180102T03:04:05-12:34', # Missing mandatory date separators
'2018-01-02T030405-12:34', # Missing mandatory time separators
'2018-01-02T03:04:05-1234', # Missing mandatory offset separator
'2018-01-02T03:04:05,12345Z' # Invalid comma fractional second separator
]:
with self.assertRaisesRegex(
ValueError,
r"RFC 3339",
msg=
"Timestamp '{0}' was supposed to be invalid, but parsing it didn't raise ValueError."
.format(timestamp)):
ciso8601.parse_rfc3339(timestamp)
def munge(dct: Dict[str, str]) -> AttrDict:
dct = AttrDict(**dct)
if 'text' in dct:
dct.text = html.escape(dct.text)
for pat, repl in HTML_FILTERS.items():
dct.text = pat.sub(repl, dct.text)
for pat, repl in ABBREVS.items():
dct.text = pat.sub(repl, dct.text)
dct.text = dct.text.replace('\N{STX}', '<').replace('\N{ETX}', '>')
if 'timestamp' in dct:
dct.timestamp = parse_rfc3339(dct.timestamp)
if 'self' in dct:
dct.self = parse_rfc3339(dct.self)
return dct
def safe_parse_rfc3339(time_string):
"""
>>> from datetime import datetime
>>> isinstance(safe_parse_rfc3339('2018-01-01T10:00:00.52Z'), datetime)
True
>>> safe_parse_rfc3339('2018-01-01T10:00:00.52Z')
datetime.datetime(2018, 1, 1, 10, 0, 0, 520000, tzinfo=datetime.timezone.utc)
>>> safe_parse_rfc3339('2018-01-01T10:00:58-06:00')
datetime.datetime(2018, 1, 1, 10, 0, 58, tzinfo=datetime.timezone(datetime.timedelta(days=-1, seconds=64800)))
>>> safe_parse_rfc3339('2018-05-10') is None
True
>>> safe_parse_rfc3339('malformed $h14') is None
True
>>> safe_parse_rfc3339('2018-01-01T00:00:00') is None
True
>>> safe_parse_rfc3339(None) is None
True
"""
if not isinstance(time_string, str):
return None
try:
return parse_rfc3339(time_string)
except ValueError: # noqa
return None
def test_valid_rfc3339_timestamps(self):
"""
Validate that valid RFC 3339 datetimes are parseable by parse_rfc3339
and produce the same result as parse_datetime.
"""
for string in [
'2018-01-02T03:04:05Z',
'2018-01-02t03:04:05z',
'2018-01-02 03:04:05z',
'2018-01-02T03:04:05+00:00',
'2018-01-02T03:04:05-00:00',
'2018-01-02T03:04:05.12345Z',
'2018-01-02T03:04:05+01:23',
'2018-01-02T03:04:05-12:34',
'2018-01-02T03:04:05-12:34',
]:
self.assertEqual(ciso8601.parse_datetime(string),
ciso8601.parse_rfc3339(string))
def test_valid_rfc3339_timestamps(self):
"""
Validate that valid RFC 3339 datetimes are parseable by parse_rfc3339
and produce the same result as parse_datetime.
"""
for string in [
"2018-01-02T03:04:05Z",
"2018-01-02t03:04:05z",
"2018-01-02 03:04:05z",
"2018-01-02T03:04:05+00:00",
"2018-01-02T03:04:05-00:00",
"2018-01-02T03:04:05.12345Z",
"2018-01-02T03:04:05+01:23",
"2018-01-02T03:04:05-12:34",
"2018-01-02T03:04:05-12:34",
]:
self.assertEqual(
parse_datetime(string), parse_rfc3339(string)
)
def valid_timestamp(s: str) -> str:
try:
ciso8601.parse_rfc3339(s)
except ValueError as e:
raise argparse.ArgumentTypeError(e.args[0])
return s
def _time_check(v):
# Return datetime.datetime here to avoid parsing twice in places
return ciso8601.parse_rfc3339(v)
from ciso8601 import parse_rfc3339
from jnrbase.attrdict import AttrDict
from lxml import html
from feedwerk.atom import AtomFeed
with open(sys.argv[1]) as f:
page = html.parse(f)
with open('data/µnotes.json') as f:
notes = json.load(f, object_hook=AttrDict)
with open('data/config.json') as f:
config = json.load(f, object_hook=AttrDict)
feed = AtomFeed(**config)
for note, post in list(zip(reversed(notes),
page.getroot().cssselect('.note')))[:15]:
title = note.text
content = html.tostring(post, True).decode()
content = content.strip().replace('\n', '')
time = parse_rfc3339(post.cssselect('p.meta time')[0].get('datetime'))
feed.add(title=title,
content=content,
content_type='html',
url='%s#%s' % (config.url, post.get("id")),
updated=time,
published=time,
xml_base=config.url)
print(feed.to_string())