forkparser 2026.1.0__py3-none-any.whl

feedparser/datetimes/hungarian.py

@@ -0,0 +1,66 @@
+# Copyright 2010-2025 Kurt McKee <contactme@kurtmckee.org>
+# Copyright 2002-2008 Mark Pilgrim
+# All rights reserved.
+#
+# This file is a part of feedparser.
+#
+# Redistribution and use in source and binary forms, with or without
+# modification, are permitted provided that the following conditions are met:
+#
+# * Redistributions of source code must retain the above copyright notice,
+#   this list of conditions and the following disclaimer.
+# * Redistributions in binary form must reproduce the above copyright notice,
+#   this list of conditions and the following disclaimer in the documentation
+#   and/or other materials provided with the distribution.
+#
+# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS 'AS IS'
+# AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+# ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+# LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+# CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+# SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+# INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+# CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+# ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+# POSSIBILITY OF SUCH DAMAGE.
+
+import re
+
+from .w3dtf import _parse_date_w3dtf
+
+# Unicode strings for Hungarian date strings
+_hungarian_months = {
+    "janu\u00e1r": "01",  # e1 in iso-8859-2
+    "febru\u00e1ri": "02",  # e1 in iso-8859-2
+    "m\u00e1rcius": "03",  # e1 in iso-8859-2
+    "\u00e1prilis": "04",  # e1 in iso-8859-2
+    "m\u00e1ujus": "05",  # e1 in iso-8859-2
+    "j\u00fanius": "06",  # fa in iso-8859-2
+    "j\u00falius": "07",  # fa in iso-8859-2
+    "augusztus": "08",
+    "szeptember": "09",
+    "okt\u00f3ber": "10",  # f3 in iso-8859-2
+    "november": "11",
+    "december": "12",
+}
+
+_hungarian_date_format_re = re.compile(
+    r"(\d{4})-([^-]+)-(\d{,2})T(\d{,2}):(\d{2})([+-](\d{,2}:\d{2}))"
+)
+
+
+def _parse_date_hungarian(date_string):
+    """Parse a string according to a Hungarian 8-bit date format."""
+    m = _hungarian_date_format_re.match(date_string)
+    if not m or m.group(2) not in _hungarian_months:
+        return None
+    month = _hungarian_months[m.group(2)]
+    day = m.group(3)
+    if len(day) == 1:
+        day = "0" + day
+    hour = m.group(4)
+    if len(hour) == 1:
+        hour = "0" + hour
+    w3dtfdate = f"{m.group(1)}-{month}-{day}T{hour}:{m.group(5)}{m.group(6)}"
+    return _parse_date_w3dtf(w3dtfdate)

feedparser/datetimes/iso8601.py

@@ -0,0 +1,160 @@
+# Copyright 2010-2025 Kurt McKee <contactme@kurtmckee.org>
+# Copyright 2002-2008 Mark Pilgrim
+# All rights reserved.
+#
+# This file is a part of feedparser.
+#
+# Redistribution and use in source and binary forms, with or without
+# modification, are permitted provided that the following conditions are met:
+#
+# * Redistributions of source code must retain the above copyright notice,
+#   this list of conditions and the following disclaimer.
+# * Redistributions in binary form must reproduce the above copyright notice,
+#   this list of conditions and the following disclaimer in the documentation
+#   and/or other materials provided with the distribution.
+#
+# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS 'AS IS'
+# AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+# ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+# LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+# CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+# SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+# INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+# CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+# ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+# POSSIBILITY OF SUCH DAMAGE.
+
+import re
+import time
+
+# ISO-8601 date parsing routines written by Fazal Majid.
+# The ISO 8601 standard is very convoluted and irregular - a full ISO 8601
+# parser is beyond the scope of feedparser and would be a worthwhile addition
+# to the Python library.
+# A single regular expression cannot parse ISO 8601 date formats into groups
+# as the standard is highly irregular (for instance is 030104 2003-01-04 or
+# 0301-04-01), so we use templates instead.
+# Please note the order in templates is significant because we need a
+# greedy match.
+_iso8601_tmpl = [
+    "YYYY-?MM-?DD",
+    "YYYY-0MM?-?DD",
+    "YYYY-MM",
+    "YYYY-?OOO",
+    "YY-?MM-?DD",
+    "YY-?OOO",
+    "YYYY",
+    "-YY-?MM",
+    "-OOO",
+    "-YY",
+    "--MM-?DD",
+    "--MM",
+    "---DD",
+    "CC",
+    "",
+]
+
+_iso8601_re = [
+    tmpl.replace("YYYY", r"(?P<year>\d{4})")
+    .replace("YY", r"(?P<year>\d\d)")
+    .replace("MM", r"(?P<month>[01]\d)")
+    .replace("DD", r"(?P<day>[0123]\d)")
+    .replace("OOO", r"(?P<ordinal>[0123]\d\d)")
+    .replace("CC", r"(?P<century>\d\d$)")
+    + r"(T?(?P<hour>\d{2}):(?P<minute>\d{2})"
+    + r"(:(?P<second>\d{2}))?"
+    + r"(\.(?P<fracsecond>\d+))?"
+    + r"(?P<tz>[+-](?P<tzhour>\d{2})(:(?P<tzmin>\d{2}))?|Z)?)?"
+    for tmpl in _iso8601_tmpl
+]
+_iso8601_matches = [re.compile(regex).match for regex in _iso8601_re]
+
+
+def _parse_date_iso8601(date_string):
+    """Parse a variety of ISO-8601-compatible formats like 20040105"""
+    m = None
+    for _iso8601_match in _iso8601_matches:
+        m = _iso8601_match(date_string)
+        if m:
+            break
+    if not m:
+        return
+    if m.span() == (0, 0):
+        return
+    params = m.groupdict()
+    ordinal = params.get("ordinal", 0)
+    if ordinal:
+        ordinal = int(ordinal)
+    else:
+        ordinal = 0
+    year = params.get("year", "--")
+    if not year or year == "--":
+        year = time.gmtime()[0]
+    elif len(year) == 2:
+        # ISO 8601 assumes current century, i.e. 93 -> 2093, NOT 1993
+        year = 100 * int(time.gmtime()[0] / 100) + int(year)
+    else:
+        year = int(year)
+    month = params.get("month", "-")
+    if not month or month == "-":
+        # ordinals are NOT normalized by mktime, we simulate them
+        # by setting month=1, day=ordinal
+        if ordinal:
+            month = 1
+        else:
+            month = time.gmtime()[1]
+    month = int(month)
+    day = params.get("day", 0)
+    if not day:
+        # see above
+        if ordinal:
+            day = ordinal
+        elif (
+            params.get("century", 0) or params.get("year", 0) or params.get("month", 0)
+        ):
+            day = 1
+        else:
+            day = time.gmtime()[2]
+    else:
+        day = int(day)
+    # special case of the century - is the first year of the 21st century
+    # 2000 or 2001 ? The debate goes on...
+    if "century" in params:
+        year = (int(params["century"]) - 1) * 100 + 1
+    # in ISO 8601 most fields are optional
+    for field in ["hour", "minute", "second", "tzhour", "tzmin"]:
+        if not params.get(field, None):
+            params[field] = 0
+    hour = int(params.get("hour", 0))
+    minute = int(params.get("minute", 0))
+    second = int(float(params.get("second", 0)))
+    # weekday is normalized by mktime(), we can ignore it
+    weekday = 0
+    daylight_savings_flag = -1
+    tm = [
+        year,
+        month,
+        day,
+        hour,
+        minute,
+        second,
+        weekday,
+        ordinal,
+        daylight_savings_flag,
+    ]
+    # ISO 8601 time zone adjustments
+    tz = params.get("tz")
+    if tz and tz != "Z":
+        if tz[0] == "-":
+            tm[3] += int(params.get("tzhour", 0))
+            tm[4] += int(params.get("tzmin", 0))
+        elif tz[0] == "+":
+            tm[3] -= int(params.get("tzhour", 0))
+            tm[4] -= int(params.get("tzmin", 0))
+        else:
+            return None
+    # Python's time.mktime() is a wrapper around the ANSI C mktime(3c)
+    # which is guaranteed to normalize d/m/y/h/m/s.
+    # Many implementations have bugs, but we'll pretend they don't.
+    return time.localtime(time.mktime(tuple(tm)))

feedparser/datetimes/korean.py

@@ -0,0 +1,94 @@
+# Copyright 2010-2025 Kurt McKee <contactme@kurtmckee.org>
+# Copyright 2002-2008 Mark Pilgrim
+# All rights reserved.
+#
+# This file is a part of feedparser.
+#
+# Redistribution and use in source and binary forms, with or without
+# modification, are permitted provided that the following conditions are met:
+#
+# * Redistributions of source code must retain the above copyright notice,
+#   this list of conditions and the following disclaimer.
+# * Redistributions in binary form must reproduce the above copyright notice,
+#   this list of conditions and the following disclaimer in the documentation
+#   and/or other materials provided with the distribution.
+#
+# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS 'AS IS'
+# AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+# ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+# LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+# CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+# SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+# INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+# CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+# ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+# POSSIBILITY OF SUCH DAMAGE.
+
+import re
+
+from .w3dtf import _parse_date_w3dtf
+
+# 8-bit date handling routines written by ytrewq1.
+_korean_year = "\ub144"  # b3e2 in euc-kr
+_korean_month = "\uc6d4"  # bff9 in euc-kr
+_korean_day = "\uc77c"  # c0cf in euc-kr
+_korean_am = "\uc624\uc804"  # bfc0 c0fc in euc-kr
+_korean_pm = "\uc624\ud6c4"  # bfc0 c8c4 in euc-kr
+
+_korean_onblog_date_re = re.compile(
+    r"(\d{4})%s\s+(\d{2})%s\s+(\d{2})%s\s+(\d{2}):(\d{2}):(\d{2})"
+    % (_korean_year, _korean_month, _korean_day)
+)
+
+_korean_nate_date_re = re.compile(
+    r"(\d{4})-(\d{2})-(\d{2})\s+(%s|%s)\s+(\d{,2}):(\d{,2}):(\d{,2})"
+    % (_korean_am, _korean_pm)
+)
+
+
+def _parse_date_onblog(dateString):
+    """Parse a string according to the OnBlog 8-bit date format"""
+    m = _korean_onblog_date_re.match(dateString)
+    if not m:
+        return
+    w3dtfdate = (
+        "%(year)s-%(month)s-%(day)sT%(hour)s:%(minute)s:%(second)s%(zonediff)s"
+        % {
+            "year": m.group(1),
+            "month": m.group(2),
+            "day": m.group(3),
+            "hour": m.group(4),
+            "minute": m.group(5),
+            "second": m.group(6),
+            "zonediff": "+09:00",
+        }
+    )
+    return _parse_date_w3dtf(w3dtfdate)
+
+
+def _parse_date_nate(dateString):
+    """Parse a string according to the Nate 8-bit date format"""
+    m = _korean_nate_date_re.match(dateString)
+    if not m:
+        return
+    hour = int(m.group(5))
+    ampm = m.group(4)
+    if ampm == _korean_pm:
+        hour += 12
+    hour = str(hour)
+    if len(hour) == 1:
+        hour = "0" + hour
+    w3dtfdate = (
+        "%(year)s-%(month)s-%(day)sT%(hour)s:%(minute)s:%(second)s%(zonediff)s"
+        % {
+            "year": m.group(1),
+            "month": m.group(2),
+            "day": m.group(3),
+            "hour": hour,
+            "minute": m.group(6),
+            "second": m.group(7),
+            "zonediff": "+09:00",
+        }
+    )
+    return _parse_date_w3dtf(w3dtfdate)

feedparser/datetimes/perforce.py

@@ -0,0 +1,63 @@
+# Copyright 2010-2025 Kurt McKee <contactme@kurtmckee.org>
+# Copyright 2002-2008 Mark Pilgrim
+# All rights reserved.
+#
+# This file is a part of feedparser.
+#
+# Redistribution and use in source and binary forms, with or without
+# modification, are permitted provided that the following conditions are met:
+#
+# * Redistributions of source code must retain the above copyright notice,
+#   this list of conditions and the following disclaimer.
+# * Redistributions in binary form must reproduce the above copyright notice,
+#   this list of conditions and the following disclaimer in the documentation
+#   and/or other materials provided with the distribution.
+#
+# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS 'AS IS'
+# AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+# ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+# LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+# CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+# SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+# INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+# CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+# ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+# POSSIBILITY OF SUCH DAMAGE.
+
+import email.utils
+import re
+import time
+
+
+def _parse_date_perforce(date_string):
+    """parse a date in yyyy/mm/dd hh:mm:ss TTT format"""
+    # Fri, 2006/09/15 08:19:53 EDT
+    _my_date_pattern = re.compile(
+        r"(\w{,3}), (\d{,4})/(\d{,2})/(\d{2}) (\d{,2}):(\d{2}):(\d{2}) (\w{,3})"
+    )
+
+    m = _my_date_pattern.search(date_string)
+    if m is None:
+        return None
+    dow, year, month, day, hour, minute, second, tz = m.groups()
+    months = [
+        "Jan",
+        "Feb",
+        "Mar",
+        "Apr",
+        "May",
+        "Jun",
+        "Jul",
+        "Aug",
+        "Sep",
+        "Oct",
+        "Nov",
+        "Dec",
+    ]
+    new_date_string = (
+        f"{dow}, {day} {months[int(month) - 1]} {year} {hour}:{minute}:{second} {tz}"
+    )
+    tm = email.utils.parsedate_tz(new_date_string)
+    if tm:
+        return time.gmtime(email.utils.mktime_tz(tm))

feedparser/datetimes/rfc822.py

@@ -0,0 +1,179 @@
+# Copyright 2010-2025 Kurt McKee <contactme@kurtmckee.org>
+# Copyright 2002-2008 Mark Pilgrim
+# All rights reserved.
+#
+# This file is a part of feedparser.
+#
+# Redistribution and use in source and binary forms, with or without
+# modification, are permitted provided that the following conditions are met:
+#
+# * Redistributions of source code must retain the above copyright notice,
+#   this list of conditions and the following disclaimer.
+# * Redistributions in binary form must reproduce the above copyright notice,
+#   this list of conditions and the following disclaimer in the documentation
+#   and/or other materials provided with the distribution.
+#
+# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS 'AS IS'
+# AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+# ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+# LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+# CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+# SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+# INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+# CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+# ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+# POSSIBILITY OF SUCH DAMAGE.
+
+import datetime
+
+timezone_names = {
+    "ut": 0,
+    "gmt": 0,
+    "z": 0,
+    "adt": -3,
+    "ast": -4,
+    "at": -4,
+    "edt": -4,
+    "est": -5,
+    "et": -5,
+    "cdt": -5,
+    "cst": -6,
+    "ct": -6,
+    "mdt": -6,
+    "mst": -7,
+    "mt": -7,
+    "pdt": -7,
+    "pst": -8,
+    "pt": -8,
+    "a": -1,
+    "n": 1,
+    "m": -12,
+    "y": 12,
+    "met": 1,
+    "mest": 2,
+}
+day_names = {"mon", "tue", "wed", "thu", "fri", "sat", "sun"}
+months = {
+    "jan": 1,
+    "feb": 2,
+    "mar": 3,
+    "apr": 4,
+    "may": 5,
+    "jun": 6,
+    "jul": 7,
+    "aug": 8,
+    "sep": 9,
+    "oct": 10,
+    "nov": 11,
+    "dec": 12,
+}
+
+
+def _parse_date_rfc822(date):
+    """Parse RFC 822 dates and times
+    http://tools.ietf.org/html/rfc822#section-5
+
+    There are some formatting differences that are accounted for:
+    1. Years may be two or four digits.
+    2. The month and day can be swapped.
+    3. Additional timezone names are supported.
+    4. A default time and timezone are assumed if only a date is present.
+
+    :param str date: a date/time string that will be converted to a time tuple
+    :returns: a UTC time tuple, or None
+    :rtype: time.struct_time | None
+    """
+
+    parts = date.lower().split()
+    if len(parts) < 5:
+        # Assume that the time and timezone are missing
+        parts.extend(("00:00:00", "0000"))
+    # Remove the day name
+    if parts[0][:3] in day_names:
+        # Comma without spaces:
+        # 'Fri,24 Nov 2023 18:28:36 -0000'
+        if "," in parts[0] and parts[0][-1] != ",":
+            parts.insert(1, parts[0].rpartition(",")[2])
+        parts = parts[1:]
+    if len(parts) < 5:
+        # If there are still fewer than five parts, there's not enough
+        # information to interpret this.
+        return None
+
+    # Handle the day and month name.
+    month = months.get(parts[1][:3])
+    try:
+        day = int(parts[0])
+    except ValueError:
+        # Check if the day and month are swapped.
+        if months.get(parts[0][:3]):
+            try:
+                day = int(parts[1])
+            except ValueError:
+                return None
+            month = months.get(parts[0][:3])
+        else:
+            return None
+    if not month:
+        return None
+
+    # Handle the year.
+    try:
+        year = int(parts[2])
+    except ValueError:
+        return None
+    # Normalize two-digit years:
+    # Anything in the 90's is interpreted as 1990 and on.
+    # Anything 89 or less is interpreted as 2089 or before.
+    if len(parts[2]) <= 2:
+        year += (1900, 2000)[year < 90]
+
+    # Handle the time (default to 00:00:00).
+    time_parts = parts[3].split(":")
+    time_parts.extend(("0",) * (3 - len(time_parts)))
+    try:
+        (hour, minute, second) = (int(i) for i in time_parts)
+    except ValueError:
+        return None
+
+    # Handle the timezone information, if any (default to +0000).
+    # Strip 'Etc/' from the timezone.
+    if parts[4].startswith("etc/"):
+        parts[4] = parts[4][4:]
+    # Normalize timezones that start with 'gmt':
+    # GMT-05:00 => -0500
+    # GMT => GMT
+    if parts[4].startswith("gmt"):
+        parts[4] = "".join(parts[4][3:].split(":")) or "gmt"
+    # Handle timezones like '-0500', '+0500', and 'EST'
+    if parts[4] and parts[4][0] in ("-", "+"):
+        try:
+            if ":" in parts[4]:
+                timezone_hours = int(parts[4][1:3])
+                timezone_minutes = int(parts[4][4:])
+            else:
+                timezone_hours = int(parts[4][1:3])
+                timezone_minutes = int(parts[4][3:])
+        except ValueError:
+            return None
+        if parts[4].startswith("-"):
+            timezone_hours *= -1
+            timezone_minutes *= -1
+    else:
+        timezone_hours = timezone_names.get(parts[4], 0)
+        timezone_minutes = 0
+
+    # Create the datetime object and timezone delta objects
+    try:
+        stamp = datetime.datetime(year, month, day, hour, minute, second)
+    except ValueError:
+        return None
+    delta = datetime.timedelta(0, 0, 0, 0, timezone_minutes, timezone_hours)
+
+    # Return the date and timestamp in a UTC 9-tuple
+    try:
+        return (stamp - delta).utctimetuple()
+    except (OverflowError, ValueError):
+        # IronPython throws ValueErrors instead of OverflowErrors
+        return None

feedparser/datetimes/w3dtf.py

@@ -0,0 +1,128 @@
+# Copyright 2010-2025 Kurt McKee <contactme@kurtmckee.org>
+# Copyright 2002-2008 Mark Pilgrim
+# All rights reserved.
+#
+# This file is a part of feedparser.
+#
+# Redistribution and use in source and binary forms, with or without
+# modification, are permitted provided that the following conditions are met:
+#
+# * Redistributions of source code must retain the above copyright notice,
+#   this list of conditions and the following disclaimer.
+# * Redistributions in binary form must reproduce the above copyright notice,
+#   this list of conditions and the following disclaimer in the documentation
+#   and/or other materials provided with the distribution.
+#
+# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS 'AS IS'
+# AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+# ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+# LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+# CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+# SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+# INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+# CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+# ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+# POSSIBILITY OF SUCH DAMAGE.
+
+import datetime
+
+timezonenames = {
+    "ut": 0,
+    "gmt": 0,
+    "z": 0,
+    "adt": -3,
+    "ast": -4,
+    "at": -4,
+    "edt": -4,
+    "est": -5,
+    "et": -5,
+    "cdt": -5,
+    "cst": -6,
+    "ct": -6,
+    "mdt": -6,
+    "mst": -7,
+    "mt": -7,
+    "pdt": -7,
+    "pst": -8,
+    "pt": -8,
+    "a": -1,
+    "n": 1,
+    "m": -12,
+    "y": 12,
+}
+# W3 date and time format parser
+# http://www.w3.org/TR/NOTE-datetime
+# Also supports MSSQL-style datetimes as defined at:
+# http://msdn.microsoft.com/en-us/library/ms186724.aspx
+# (basically, allow a space as a date/time/timezone separator)
+
+
+def _parse_date_w3dtf(datestr):
+    if not datestr.strip():
+        return None
+    parts = datestr.lower().split("t")
+    if len(parts) == 1:
+        # This may be a date only, or may be an MSSQL-style date
+        parts = parts[0].split()
+        if len(parts) == 1:
+            # Treat this as a date only
+            parts.append("00:00:00z")
+    elif len(parts) > 2:
+        return None
+    date = parts[0].split("-", 2)
+    if not date or len(date[0]) != 4:
+        return None
+    # Ensure that `date` has 3 elements. Using '1' sets the default
+    # month to January and the default day to the 1st of the month.
+    date.extend(["1"] * (3 - len(date)))
+    try:
+        year, month, day = (int(i) for i in date)
+    except ValueError:
+        # `date` may have more than 3 elements or may contain
+        # non-integer strings.
+        return None
+    if parts[1].endswith("z"):
+        parts[1] = parts[1][:-1]
+        parts.append("z")
+    # Append the numeric timezone offset, if any, to parts.
+    # If this is an MSSQL-style date then parts[2] already contains
+    # the timezone information, so `append()` will not affect it.
+    # Add 1 to each value so that if `find()` returns -1 it will be
+    # treated as False.
+    loc = parts[1].find("-") + 1 or parts[1].find("+") + 1 or len(parts[1]) + 1
+    loc = loc - 1
+    parts.append(parts[1][loc:])
+    parts[1] = parts[1][:loc]
+    time = parts[1].split(":", 2)
+    # Ensure that time has 3 elements. Using '0' means that the
+    # minutes and seconds, if missing, will default to 0.
+    time.extend(["0"] * (3 - len(time)))
+    if parts[2][:1] in ("-", "+"):
+        try:
+            tzhour = int(parts[2][1:3])
+            tzmin = int(parts[2][4:])
+        except ValueError:
+            return None
+        if parts[2].startswith("-"):
+            tzhour = tzhour * -1
+            tzmin = tzmin * -1
+    else:
+        tzhour = timezonenames.get(parts[2], 0)
+        tzmin = 0
+    try:
+        hour, minute, second = (int(float(i)) for i in time)
+    except ValueError:
+        return None
+    # Create the datetime object and timezone delta objects
+    try:
+        stamp = datetime.datetime(year, month, day, hour, minute, second)
+    except ValueError:
+        return None
+    delta = datetime.timedelta(0, 0, 0, 0, tzmin, tzhour)
+    # Return the date and timestamp in a UTC 9-tuple
+    try:
+        return (stamp - delta).utctimetuple()
+    except (OverflowError, ValueError):
+        # IronPython throws ValueErrors instead of OverflowErrors
+        return None