def parse(self, file_path, provider=None):
try:
item = {
'guid': '{}-{}'.format(file_path, uuid.uuid4()),
'pubstatus': 'usable',
'versioncreated': utcnow(),
ITEM_TYPE: CONTENT_TYPE.TEXT,
FORMAT: FORMATS.HTML,
}
with open(file_path, 'r', encoding='windows-1252') as f:
data = f.read().replace('\r', '')
header, dateline_data, body_data = data.split('\n\n', 2)
self._process_header(item, header)
start_of_body = 'MEDIA RELEASE '
source, data = data.split(start_of_body, 1)
data = start_of_body + data
item['anpa_category'] = [{'qcode': 'j'}]
item['original_source'] = 'AsiaNet'
body_html = to_ascii(html.escape(data)).replace('\n\n',
'</p><p>').replace(
'\n', ' ')
item['body_html'] = '<p>' + body_html + '</p>'
item['word_count'] = get_word_count(item['body_html'])
return item
except Exception as e:
raise AAPParserError.AsiaNetParserError(file_path, e)
def parse(self, file_path, provider=None):
try:
item = {
'guid': '{}-{}'.format(file_path, uuid.uuid4()),
'pubstatus': 'usable',
'versioncreated': utcnow(),
ITEM_TYPE: CONTENT_TYPE.TEXT,
FORMAT: FORMATS.PRESERVED,
}
with open(file_path, 'r', encoding='windows-1252') as f:
data = f.read().replace('\r', '')
header, dateline_data, data = data.split('\n\n', 2)
self._process_header(item, header)
self._process_dateline(item, dateline_data)
item['original_source'] = 'AsiaNet'
item['word_count'] = get_text_word_count(data)
item['body_html'] = '<pre>' + html.escape(data) + '</pre>'
return item
except Exception as e:
raise AAPParserError.AsiaNetParserError(file_path, e)
:param dict item: The item where the data will be stored
:param str header: The header of the file
"""
source = 'anpa_take_key'
for line in header.split('\n'):
if line.lower().startswith('media release'):
break
if source not in item:
item[source] = line
else:
item[source] += line
# Clean up the header entries
item['anpa_take_key'] = item['anpa_take_key'][8:].replace('\n',
'').strip()
item['headline'] = 'Media Release: ' + item.get('anpa_take_key', '')
item['slugline'] = 'AAP Medianet'
self._truncate_headers(item)
try:
register_feed_parser(AsiaNetFeedParser.NAME, AsiaNetFeedParser())
except AlreadyExistsError:
pass
register_feeding_service_error(
'file',
AAPParserError.AsiaNetParserError().get_error_description())