def parse(self, filename, provider=None):
try:
item = {}
self.set_item_defaults(item, provider)
with open(filename, 'r', encoding='latin-1') as f:
lines = f.readlines()
header = False
body = False
for line in lines:
if self.START_OF_MESSAGE in line and not header:
item['guid'] = filename + str(uuid.uuid4())
header = True
continue
if header:
if line == '\n':
continue
if line[0] in self.header_map:
if self.header_map[line[0]]:
item[self.header_map[line[0]]] = line[1:-1]
continue
if line[0] == self.CATEGORY:
item[self.ITEM_ANPA_CATEGORY] = [{'qcode': line[1]}]
continue
if line[0] == self.FORMAT:
if line[1] == self.TEXT:
item[ITEM_TYPE] = CONTENT_TYPE.TEXT
continue
if line[1] == self.TABULAR:
item[FORMAT] = FORMATS.PRESERVED
continue
continue
if line[0] == self.GENRE:
genre = line[1:-1]
if genre:
genre_map = get_resource_service('vocabularies').find_one(req=None, _id='genre')
item['genre'] = [x for x in genre_map.get('items', []) if
x['qcode'] == genre and x['is_active']]
continue
if line[0] == self.IPTC:
iptc_code = line[1:-1]
if iptc_code.isdigit():
item[self.ITEM_SUBJECT] = [{'qcode': iptc_code, 'name': subject_codes[iptc_code]}]
continue
header = False
body = True
item['body_html'] = line
else:
if self.END_OF_MESSAGE in line:
break
if body:
item['body_html'] = item.get('body_html', '') + line
if item.get(FORMAT) == FORMATS.PRESERVED:
item['body_html'] = '<pre>' + html.escape(item['body_html']) + '</pre>'
return self.post_process_item(item, provider)
except Exception as ex:
raise AAPParserError.ZCZCParserError(exception=ex, provider=provider)
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())
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:
pass
register_feeding_service_error(
'file',
AAPParserError.ZCZCParserError().get_error_description())