dateparser package

Submodules

dateparser.date module

class dateparser.date.DateDataParser(language=None, allow_redetect_language=False)

Bases: object

get_date_data(date_string, date_formats=None)

Return a dictionary with a date object and a period. Period values can be a ‘day’ (default), ‘week’, ‘month’, ‘year’. It aims to solve the following issue: In example, a forum could displays “2 weeks ago” in the thread list (in the thread itself there’s the right date) so the engine will translate “2 weeks ago” to a certain date. The next thread summary displays “3 weeks ago” which is translated to a other date seven days before first date. A valid date_string between both dates won’t be scraped because it’s not an exact date match. The period field helps to build better date range detection.

TODO: Timezone issues

dateparser.date.date_range(begin, end, **kwargs)

dateparser.date.get_date_from_timestamp(date_string)

dateparser.date.get_intersecting_periods(low, high, period='day')

dateparser.date.get_last_day_of_month(year, month)

dateparser.date.parse_with_formats(date_string, date_formats, final_call=False, alt_parser=None)

Parse with formats and return depending on final_call arg. If final_call is True, return a dictionary with ‘period’ and ‘obj_date’ because these data won’t be processed by any method outside. If final_call is False, return a ‘obj_date’ because it will be processed.

Returns:datetime.datetime, dict or None

dateparser.date.sanitize_date(date_string)

dateparser.date.sanitize_spaces(html_string)

dateparser.date_parser module

class dateparser.date_parser.AutoDetectLanguage(language=None, allow_redetection=False, *args, **kwargs)

Bases: dateparser.date_parser.DateParsingStrategy

Date parser with support for language detection.

It uses the get_language_candidates() function to get the possible languages for each date, keeps track of the previously detected languages and uses this information to reduce the set of possible languages.

detect_language(date_string)

detect_language_and_parse(date_string, date_format)

Attempt to detect language and parse date. If no language is detected, fallback to vanilla dateutil parser

detect_unseen_language(date_string)

has_found_candidates_previously()

parse(date_string, date_format)

class dateparser.date_parser.BaseParserInfo(dayfirst=False, yearfirst=False)

Bases: dateutil.parser.parserinfo

JUMP = [u' ', u'.', u',', u';', u'-', u'/', u"'", u'|', u'@', u'[', u']']

is_token_known(name)

weekday(name)

class dateparser.date_parser.DateParser(language=None, allow_redetect_language=False)

Bases: object

parse(date_string, date_format=None)

class dateparser.date_parser.DateParsingStrategy(language=None)

Bases: object

parse(date_string, date_format)

Attempts to parse a date using the given format

class dateparser.date_parser.ExactLanguage(language, *args, **kwargs)

Bases: dateparser.date_parser.DateParsingStrategy

Date parser that works only for a specific language

parse(date_string, date_format)

exception dateparser.date_parser.LanguageWasNotSeenBeforeError

Bases: exceptions.RuntimeError

dateparser.date_parser.convert_date_formats_to_numeric(date_format)

class dateparser.date_parser.cz_parserinfo(dayfirst=False, yearfirst=False)

Bases: dateparser.date_parser.BaseParserInfo

MONTHS = [(u'leden', u'led'), (u'\xfanor', u'\xfano'), (u'b\u0159ezen', u'b\u0159e'), (u'duben', u'dub'), (u'kv\u011bten', u'kv\u011b'), (u'\u010derven', u'\u010der'), (u'\u010dervenec', u'\u010drc'), (u'srpen', u'srp'), (u'z\xe1\u0159\xed', u'z\xe1\u0159'), (u'\u0159\xedjen', u'\u0159\xedj'), (u'listopad', u'lis'), (u'prosinec', u'pro')]

WEEKDAYS = [(u'pond\u011bl\xed', u'pon'), (u'\xfater\xfd', u'\xfate'), (u'st\u0159eda', u'st\u0159'), (u'\u010dtvrtek', u'\u010dtv'), (u'p\xe1tek', u'p\xe1t'), (u'sobota', u'sob'), (u'ned\u011ble', u'ned')]

dateparser.date_parser.dateutil_parse(date_string, **kwargs)

Wrapper function around dateutil.parser.parse

class dateparser.date_parser.de_parserinfo(dayfirst=False, yearfirst=False)

Bases: dateparser.date_parser.BaseParserInfo

JUMP = [u' ', u'.', u',', u';', u'-', u'/', u"'", u'|', u'@', u'[', u']', u'um', u'uhr']

MONTHS = [(u'Januar', u'Jan'), (u'Februar', u'Feb'), (u'M\xe4rz',), (u'April', u'Apr'), (u'Mai',), (u'Juni',), (u'Juli',), (u'August', u'Aug'), (u'September', u'Sept'), (u'Oktober', u'Okt'), (u'November', u'Nov'), (u'Dezember', u'Dez')]

class dateparser.date_parser.en_parserinfo(dayfirst=False, yearfirst=False)

Bases: dateparser.date_parser.BaseParserInfo

JUMP = [u'and', u'@', u'ad', u'on', u'm', u'at', u'[', u'st', u']', u' ', u"'", u'of', u'nd', u'-', u',', u'/', u'.', u'rd', u't', u'th', u';', u'|']

class dateparser.date_parser.es_parserinfo(dayfirst=False, yearfirst=False)

Bases: dateparser.date_parser.BaseParserInfo

JUMP = [u' ', u'.', u',', u';', u'-', u'/', u"'", u'|', u'@', u'[', u']', u'de', u'del']

MONTHS = [(u'enero', u'ene'), (u'febrero', u'feb'), (u'marzo', u'mar'), (u'abril', u'abr'), (u'mayo', u'may'), (u'junio', u'jun'), (u'julio', u'jul'), (u'agosto', u'ago'), (u'septiembre', u'setiembre', u'sep', u'set'), (u'octubre', u'oct'), (u'noviembre', u'nov'), (u'diciembre', u'dic')]

PERTAIN = [u'de', u'del']

WEEKDAYS = [(u'Lunes',), (u'Martes',), (u'Mi\xe9rcoles',), (u'Jueves',), (u'Viernes',), (u'S\xe1bado',), (u'Domingo',)]

class dateparser.date_parser.fr_parserinfo(dayfirst=False, yearfirst=False)

Bases: dateparser.date_parser.BaseParserInfo

JUMP = [u' ', u'.', u',', u';', u'-', u'/', u"'", u'|', u'@', u'[', u']', u'le']

MONTHS = [(u'janvier', u'janv', u'jan'), (u'f\xe9vrier', u'f\xe9vr', u'f\xe9v'), (u'mars', u'mar'), (u'avril', u'avr'), u'mai', u'juin', (u'juillet', u'juil'), (u'ao\xfbt', u'ao\xfb'), (u'septembre', u'sept', u'sep'), (u'octobre', u'oct'), (u'novembre', u'nov'), (u'd\xe9cembre', u'd\xe9c')]

WEEKDAYS = [(u'Lundi',), (u'Mardi',), (u'Mercredi',), (u'Jeudi',), (u'Vendredi',), (u'Samedi',), (u'Dimanche',)]

dateparser.date_parser.get_language_candidates(tokens, languages=None, exclude_languages=None)

Find the languages which have a word matching at least one of the given tokens and all tokens are known by this language

class dateparser.date_parser.it_parserinfo(dayfirst=False, yearfirst=False)

Bases: dateparser.date_parser.BaseParserInfo

MONTHS = [(u'gennaio', u'gen'), (u'febbraio', u'feb'), (u'marzo', u'mar'), (u'aprile', u'apr'), (u'maggio', u'mag'), (u'giugno', u'giu'), (u'luglio', u'lug'), (u'agosto', u'ago'), (u'settembre', u'set'), (u'ottobre', u'ott'), (u'novembre', u'nov'), (u'dicembre', u'dic')]

class dateparser.date_parser.new_relativedelta(dt1=None, dt2=None, years=0, months=0, days=0, leapdays=0, weeks=0, hours=0, minutes=0, seconds=0, microseconds=0, year=None, month=None, day=None, weekday=None, yearday=None, nlyearday=None, hour=None, minute=None, second=None, microsecond=None)

Bases: dateutil.relativedelta.relativedelta

dateutil does not check if result of parsing weekday is in the future. Although items dates are already in the past, so we need to fix this particular case.

class dateparser.date_parser.new_timelex(*args, **kwargs)

Bases: dateutil.parser._timelex

classmethod prepare_string(s)

classmethod split(s)

class dateparser.date_parser.nl_parserinfo(dayfirst=False, yearfirst=False)

Bases: dateparser.date_parser.BaseParserInfo

MONTHS = [(u'januari', u'jan'), (u'februari', u'feb'), (u'maart', u'mrt'), (u'april', u'apr'), (u'mei',), (u'juni', u'jun'), (u'juli', u'jul'), (u'augustus', u'aug'), (u'september', u'sep'), (u'oktober', u'okt'), (u'november', u'nov'), (u'december', u'dec')]

WEEKDAYS = [(u'Maandag', u'ma'), (u'Dinsdag', u'di'), (u'Woensdag', u'wo'), (u'Donderdag', u'do'), (u'Vrijdag', u'vr'), (u'Zaterdag', u'za'), (u'Zondag', u'zo')]

dateparser.date_parser.parse_using_languages(date_string, date_format, languages)

Try parsing date using the given format for each of the languages given as argument

dateparser.date_parser.parse_with_language_and_format(date_string, language, date_format)

class dateparser.date_parser.pt_parserinfo(dayfirst=False, yearfirst=False)

Bases: dateparser.date_parser.BaseParserInfo

JUMP = [u' ', u'.', u',', u';', u'-', u'/', u"'", u'|', u'@', u'[', u']', u'de']

MONTHS = [(u'janeiro', u'jan'), (u'fevereiro', u'fev'), (u'mar\xe7o', u'mar'), (u'abril', u'abr'), (u'maio', u'mai'), (u'junho', u'jun'), (u'julho', u'jul'), (u'agosto', u'ago'), (u'septembro', u'setembro', u'septemberembro', u'set'), (u'outubro', u'out'), (u'novembro', u'nov'), (u'dezembro', u'dez')]

PERTAIN = [u'de']

WEEKDAYS = [(u'Segunda-feira',), (u'Ter\xe7a-feira',), (u'Quarta-feira',), (u'Quinta-feira',), (u'Sexta-feira',), (u'S\xe1bado',), (u'Domingo',)]

class dateparser.date_parser.ro_parserinfo(dayfirst=False, yearfirst=False)

Bases: dateparser.date_parser.BaseParserInfo

MONTHS = [(u'ianuarie', u'ian'), (u'februarie', u'feb'), (u'martie', u'mar'), (u'aprilie', u'apr'), (u'mai',), (u'iunie',), (u'iulie',), (u'august', u'aug'), (u'septembrie', u'sept'), (u'octombrie', u'oct'), (u'noiembrie', u'noiem'), (u'decembrie', u'dec')]

class dateparser.date_parser.ru_parserinfo(dayfirst=False, yearfirst=False)

Bases: dateparser.date_parser.BaseParserInfo

JUMP = [u' ', u'.', u',', u';', u'-', u'/', u"'", u'|', u'@', u'[', u']', u'\u0432']

MONTHS = [(u'\u044f\u043d\u0432\u0430\u0440\u044f', u'\u042f\u043d\u0432\u0430\u0440\u044f'), (u'\u0444\u0435\u0432\u0440\u0430\u043b\u044f', u'\u0424\u0435\u0432\u0440\u0430\u043b\u044f'), (u'\u043c\u0430\u0440\u0442\u0430', u'\u041c\u0430\u0440\u0442\u0430'), (u'\u0430\u043f\u0440\u0435\u043b\u044f', u'\u0410\u043f\u0440\u0435\u043b\u044f'), (u'\u043c\u0430\u044f', u'\u041c\u0430\u044f'), (u'\u0438\u044e\u043d\u044f', u'\u0418\u044e\u043d\u044f'), (u'\u0438\u044e\u043b\u044f', u'\u0418\u044e\u043b\u044f'), (u'\u0430\u0432\u0433\u0443\u0441\u0442\u0430', u'\u0410\u0432\u0433\u0443\u0441\u0442\u0430'), (u'\u0441\u0435\u043d\u0442\u044f\u0431\u0440\u044f', u'\u0421\u0435\u043d\u0442\u044f\u0431\u0440\u044f'), (u'\u043e\u043a\u0442\u044f\u0431\u0440\u044f', u'\u041e\u043a\u0442\u044f\u0431\u0440\u044f'), (u'\u043d\u043e\u044f\u0431\u0440\u044f', u'\u041d\u043e\u044f\u0431\u0440\u044f'), (u'\u0434\u0435\u043a\u0430\u0431\u0440\u044f', u'\u0414\u0435\u043a\u0430\u0431\u0440\u044f')]

dateparser.date_parser.tokenize_date(s)

class dateparser.date_parser.tr_parserinfo(dayfirst=False, yearfirst=False)

Bases: dateparser.date_parser.BaseParserInfo

MONTHS = [(u'Ocak',), (u'\u015eubat',), (u'Mart',), (u'Nisan',), (u'May\u0131s',), (u'Haziran',), (u'Temmuz',), (u'A\u011fustos',), (u'Eyl\xfcl',), (u'Ekim',), (u'Kas\u0131m',), (u'Aral\u0131k',)]

dateparser.date_parser.translate_words(date_string, language)

Translate date words in the given language into its equivalent number e.g.: ‘January’ -> 1 (english), ‘Marzo’ -> 3 (spanish), ...

dateparser.dateparser module

dateparser.freshness_date_parser module

class dateparser.freshness_date_parser.FreshnessDateDataParser(now=None)

Bases: object

Parses date string like “1 year, 2 months ago” and “3 hours, 50 minutes ago”

apply_replacements(date_string, lang)

get_date_data(date_string)

langs = {u'ru': {u'units': {u'week': (u'\u043d\u0435\u0434\u0435\u043b\u044f', u'\u043d\u0435\u0434\u0435\u043b\u0438', u'\u043d\u0435\u0434\u0435\u043b\u044c', u'\u043d\u0435\u0434\u0435\u043b\u044e'), u'hour': (u'\u0447\u0430\u0441', u'\u0447\u0430\u0441\u0430', u'\u0447\u0430\u0441\u043e\u0432'), u'month': (u'\u043c\u0435\u0441\u044f\u0446', u'\u043c\u0435\u0441\u044f\u0446\u0430', u'\u043c\u0435\u0441\u044f\u0446\u0435\u0432'), u'second': (u'\u0441\u0435\u043a\u0443\u043d\u0434\u0430', u'\u0441\u0435\u043a\u0443\u043d\u0434\u044b', u'\u0441\u0435\u043a\u0443\u043d\u0434', u'\u0441\u0435\u043a\u0443\u043d\u0434\u0443'), u'year': (u'\u0433\u043e\u0434', u'\u0433\u043e\u0434\u0430', u'\u043b\u0435\u0442'), u'day': (u'\u0434\u0435\u043d\u044c', u'\u0434\u043d\u044f', u'\u0434\u043d\u0435\u0439'), u'minute': (u'\u043c\u0438\u043d\u0443\u0442\u0430', u'\u043c\u0438\u043d\u0443\u0442\u0430', u'\u043c\u0438\u043d\u0443\u0442', u'\u043c\u0438\u043d\u0443\u0442\u0443')}, u'word_replacements': [(u'1 \u0434\u043d\u0435\u0439', [u'\u0432\u0447\u0435\u0440\u0430\u0432\u0447\u0435\u0440\u0430', u'\u0412\u0447\u0435\u0440\u0430 \u0432', u'\u0432\u0447\u0435\u0440\u0430', u'\u0412\u0447\u0435\u0440\u0430']), (u'0 \u0434\u0435\u043d\u044c', [u'\u0441\u0435\u0433\u043e\u0434\u043d\u044f']), (u'\u0447\u0430\u0441', [u'\u0447']), (u'\u043c\u0438\u043d\u0443\u0442\u0443', [u'\u043c\u0438\u043d']), (u'1 \u043c\u0438\u043d\u0443\u0442\u0443', [u'^\u043c\u0438\u043d\u0443\u0442\u0443']), (u'1 \u0447\u0430\u0441', [u'^\u0447\u0430\u0441']), (u'44 \u0441\u0435\u043a\u0443\u043d\u0434\u044b', [u'\u043d\u0435\u0441\u043a\u043e\u043b\u044c\u043a\u043e \u0441\u0435\u043a\u0443\u043d\u0434'])]}, u'fr': {u'units': {u'week': (u'semaine', u'semaines'), u'hour': (u'heure', u'heures'), u'month': (u'mois', u'mois'), u'year': (u'an', u'ann\xe9e', u'ann\xe9es'), u'day': (u'jour', u'jours'), u'minute': (u'minute', u'minutes')}, u'word_replacements': [(u'2 jour', [u'avant-hier']), (u'1 jour', [u'hier']), (u'0 jours', [u"aujourd'hui"]), (u'1', [u'un', u'une'])]}, u'en': {u'units': {u'week': (u'week', u'weeks'), u'hour': (u'hour', u'hours'), u'month': (u'month', u'months'), u'second': (u'second', u'seconds'), u'year': (u'year', u'years'), u'day': (u'day', u'days'), u'minute': (u'minute', u'minutes')}, u'word_replacements': [(u'2 days', [u'the day before yesterday']), (u'1 day', [u'yesterday']), (u'0 days', [u'today']), (u'1', [u'an', u'a', u'one']), (u'\\1 hour\\2', [u'(\\d+)\\s*hr(s?)']), (u'\\1 minute\\2', [u'(\\d+)\\s*min(s?)']), (u'\\1 second\\2', [u'(\\d+)\\s*sec(s?)'])]}, u'cn': {u'units': {u'week': (u'\u5468', u'\u661f\u671f'), u'hour': (u'\u5c0f\u65f6',), u'month': (u'\u6708', u'\u4e2a\u6708'), u'year': (u'\u5e74',), u'day': (u'\u5929',), u'minute': (u'\u5206', u'\u5206\u949f')}, u'word_replacements': [(u'1\u5929', [u'\u6628\u5929']), (u'2\u5929', [u'\u524d\u5929'])], u'no_word_spacing': True}, u'pt': {u'units': {u'week': (u'semana', u'semanas'), u'hour': (u'hora', u'horas'), u'month': (u'm\xeas', u'meses'), u'second': (u'segunda', u'segundos'), u'year': (u'ano', u'anos'), u'day': (u'dia', u'dias'), u'minute': (u'minuto', u'minutos')}, u'word_replacements': [(u'2 dias', [u'anteontem']), (u'1 dia', [u'ontem']), (u'0 dias', [u'hoje']), (u'1', [u'um', u'uma']), (u'44 segundos', [u'alguns segundos'])]}, u'cs': {u'units': {u'week': (u't\xfdden', u't\xfddn\u016f'), u'hour': (u'hodina', u'hodin', u'hodiny', u'hodinami'), u'month': (u'm\u011bs\xedc', u'm\u011bs\xedc\u016f', u'm\u011bs\xedce'), u'year': (u'rok', u'rok\u016f'), u'day': (u'den', u'dn\u016f', u'dny'), u'minute': (u'minuta', u'minut')}}, u'de': {u'units': {u'week': (u'Woche', u'Wochen'), u'hour': (u'Stunde', u'Stunden'), u'month': (u'Monat', u'Monate'), u'year': (u'Jahr', u'Jahre'), u'day': (u'Tag', u'Tage'), u'minute': (u'Minute', u'Minuten')}, u'word_replacements': [(u'2 Tag', [u'vorgestern']), (u'1 Tag', [u'gestern']), (u'0 Tage', [u'Heute']), (u'vor \\1 Stunden', [u'vor (\\d+)\\s*h']), (u'vor \\1 Minuten', [u'vor (\\d+)\\s*m']), (u'1', [u'einer', u'einem'])]}, u'tr': {u'units': {u'week': (u'hafta', u'hafta'), u'hour': (u'saat', u'saat'), u'month': (u'ay', u'ay'), u'year': (u'y\u0131l', u'y\u0131l'), u'day': (u'g\xfcn', u'g\xfcn'), u'minute': (u'dakika', u'dakika')}, u'word_replacements': [(u'1 g\xfcn', [u'd\xfcn'])]}, u'it': {u'units': {u'week': (u'settimana', u'settimane'), u'hour': (u'ora', u'ore'), u'month': (u'mese', u'mesi'), u'year': (u'anno', u'anni'), u'day': (u'giorno', u'giorni'), u'minute': (u'minuto', u'minuti')}, u'word_replacements': [(u'0 giorni', [u'oggi']), (u'1 giorno', [u'ieri'])]}, u'es': {u'units': {u'week': (u'semana', u'semanas'), u'hour': (u'hora', u'horas'), u'month': (u'mes', u'meses'), u'year': (u'a\xf1o', u'a\xf1os'), u'day': (u'd\xeda', u'd\xedas'), u'minute': (u'minuto', u'minutos')}, u'word_replacements': [(u'2 d\xeda', [u'anteayer']), (u'1 d\xeda', [u'ayer']), (u'0 d\xeda', [u'hoy']), (u'1', [u'un', u'una'])]}}

parse(date_string)

try_lang(date_string, lang)

dateparser.freshness_date_parser.flatten(iterable)

dateparser.timezones module

dateparser.timezones.convert_to_local_tz(datetime_obj, datetime_tz_offset)

dateparser.timezones.get_local_tz_offset()

dateparser.timezones.pop_tz_offset_from_string(date_string)

Module contents