item['body_html'] = '<pre>' + '\n'.join(lines[lines_to_remove:])
# if the concatenation of the slugline and take key contain the phrase 'Brief Form' change the category to
# h
if (item.get(self.ITEM_SLUGLINE, '') + item.get(self.ITEM_TAKE_KEY, '')).lower().find('brief form') >= 0:
item[self.ITEM_ANPA_CATEGORY] = [{'qcode': 'h'}]
# Another exception
if 'NZ/AUST FIELDS' in item.get('body_html', ''):
item[self.ITEM_ANPA_CATEGORY] = [{'qcode': 'h'}]
# if the item has been marked as convert to HTML then we need to use the racing reformat macro
# to convert it.
if lines[0] and lines[0].find('HH ') != -1:
racing_reformat_macro(item)
genre_map = get_resource_service('vocabularies').find_one(req=None, _id='genre')
if genre_map:
item['genre'] = [x for x in genre_map.get('items', []) if
x['qcode'] == 'Racing Data' and x['is_active']]
return item
except Exception as ex:
logger.exception(ex)
try:
register_feed_parser(ZCZCRacingParser.NAME, ZCZCRacingParser())
except AlreadyExistsError as ex:
pass
register_feeding_service_error('file', AAPParserError.ZCZCParserError().get_error_description())
date = date_parser(dateline, fuzzy=True).replace(tzinfo=utc)
item['dateline']['date'] = date
item['dateline']['source'] = source[:-4].strip()
item['dateline']['text'] = dateline.strip()
# Attempt to set the city data to the dateline.location key
cities = app.locators.find_cities()
for city in dateline.replace(' and ', ',').split(','):
located = [c for c in cities if c['city'].lower() == city.strip().lower()]
if len(located) > 0:
item['dateline']['located'] = located[0]
break
if 'located' not in item['dateline']:
city = dateline.split(',')[0]
item['dateline']['located'] = {
'city_code': city,
'city': city,
'tz': 'UTC',
'dateline': 'city'
}
try:
register_feed_parser(AsiaNetFeedParser.NAME, AsiaNetFeedParser())
except AlreadyExistsError as ex:
pass
register_feeding_service_error('file', AAPParserError.AsiaNetParserError().get_error_description())
def set_item_defaults(self, item, filename):
item['guid'] = filename + ':' + str(uuid.uuid4())
item['urgency'] = 5
item['pubstatus'] = 'usable'
item['versioncreated'] = utcnow()
item[ITEM_TYPE] = CONTENT_TYPE.TEXT
item['anpa_category'] = [{'qcode': 'f'}]
item['subject'] = [{'qcode': '04000000', 'name': subject_codes['04000000']}]
item[FORMAT] = FORMATS.HTML
def datetime(self, string):
"""
Convert the date string parsed from the source file to a datetime, assumes that the
time is local to Sydney Australia
:param string:
:return:
"""
# 06 June 2016 14:00:00
local_dt = datetime.datetime.strptime(string, '%d %B %Y %H:%M:%S')
local_tz = pytz.timezone('Australia/Sydney')
aus_dt = local_tz.localize(local_dt, is_dst=None)
return aus_dt.astimezone(pytz.utc)
try:
register_feed_parser(NewsBitesFeedParser.NAME, NewsBitesFeedParser())
except AlreadyExistsError as ex:
pass
register_feeding_service_error('file', AAPParserError.NewsBitesParserError().get_error_description())
