def parse_item(self, tree):
item = super().parse_item(tree)
meta = tree.find(self.qname('contentMeta'))
organisation = meta.xpath('./iptc:subject[@type="cpnat:organisation"][@literal]', namespaces=NS)
if organisation:
item['abstract'] = format_maxlength('FOR: {}. {}'.format(
organisation[0].get('literal').upper().rstrip('.'),
get_text(item['body_html']).replace(' ', ' '),
), 200)
return item
def parse_item(self, tree):
item = super().parse_item(tree)
meta = tree.find(self.qname("contentMeta"))
organisation = meta.xpath(
'./iptc:subject[@type="cpnat:organisation"][@literal]',
namespaces=NS)
if organisation:
org_name = organisation[0].get("literal")
item["abstract"] = format_maxlength(
"FOR: {}. {}".format(
org_name.upper().rstrip("."),
get_text(item["body_html"]).replace(" ", " "),
),
200,
)
item.setdefault("subject", []).append({
"name": org_name,
"qcode": org_name,
"scheme": cp.ORGANISATION,
})
return item
def _format_keyword(self, content, keywords, glue):
if keywords:
etree.SubElement(content, "Keyword").text = format_maxlength(
glue.join(keywords), 150
)
def _format_item(self, root, item, pub_seq_num, service, services) -> None:
if is_picture(item):
D2P1 = "http://www.w3.org/2001/XMLSchema-instance"
content = etree.SubElement(
root,
"ContentItem",
{"{%s}type" % D2P1: "PhotoContentItem"},
nsmap={
"d2p1": D2P1,
},
)
else:
content = etree.SubElement(root, "ContentItem")
extra = item.get("extra") or {}
# root system fields
etree.SubElement(root, "Reschedule").text = "false"
etree.SubElement(root, "IsRegional").text = "false"
etree.SubElement(root, "CanAutoRoute").text = "true"
etree.SubElement(root, "PublishID").text = str(pub_seq_num)
etree.SubElement(root, "Username")
etree.SubElement(root, "UseLocalsOut").text = "false"
etree.SubElement(root, "UserProfileID").text = "0"
etree.SubElement(root, "PublishOrder").text = "0"
etree.SubElement(root, "NewCycle").text = "false"
etree.SubElement(root, "OnlineResend").text = "false"
# item system fields
etree.SubElement(content, "AutoSaveID").text = "0"
etree.SubElement(content, "Type").text = "0"
etree.SubElement(content, "MediaType").text = "0"
etree.SubElement(content, "Status").text = "0"
if is_picture(item):
etree.SubElement(root, "Services").text = "Pictures"
self._format_subject_code(root, item, "PscCodes", cp.DESTINATIONS)
if root.find("PscCodes") is None:
etree.SubElement(root, "PscCodes").text = "Online"
elif service:
etree.SubElement(root, "Services").text = "Print"
etree.SubElement(root, "PscCodes").text = service
else:
self._format_subject_code(root, item, "PscCodes", cp.DESTINATIONS)
self._format_services(root, item)
is_broadcast = cp.is_broadcast(item)
# content system fields
orig = self._get_original_item(item)
seq_id = "{:08d}".format(pub_seq_num % 100000000)
item_id = "{:08d}".format(orig["unique_id"] % 100000000)
etree.SubElement(content, "Name")
etree.SubElement(content, "Cachable").text = "false"
etree.SubElement(content, "FileName").text = filename(orig)
etree.SubElement(content, "NewsCompID").text = item_id
etree.SubElement(content, "SystemSlug").text = slug(orig)
etree.SubElement(content, "ContentItemID").text = seq_id
etree.SubElement(content, "ProfileID").text = "204"
etree.SubElement(content, "SysContentType").text = "0"
if is_picture(item):
etree.SubElement(content, "PhotoContentItemID").text = item_id
if extra.get(cp.FILENAME):
etree.SubElement(content, "OrigTransRef").text = extra[cp.FILENAME]
if service:
etree.SubElement(content, "Note").text = ",".join(services)
# timestamps
firstpublished = item.get("firstpublished") or item["versioncreated"]
etree.SubElement(root, "PublishDateTime").text = self._format_datetime(
firstpublished
)
try:
etree.SubElement(content, "EmbargoTime").text = self._format_datetime(
item[SCHEDULE_SETTINGS]["utc_embargo"],
local=True,
)
except KeyError:
etree.SubElement(content, "EmbargoTime").text = self._format_datetime(
item.get("embargoed"), local=True
)
etree.SubElement(content, "CreatedDateTime").text = self._format_datetime(
firstpublished
) # SDCP-380
etree.SubElement(content, "UpdatedDateTime").text = self._format_datetime(
item["versioncreated"], rel=True
)
# obvious
etree.SubElement(content, "ContentType").text = (
"Photo" if is_picture(item) else item["type"].capitalize()
)
# SDCP-309
etree.SubElement(content, "Headline").text = format_maxlength(
extra.get(cp.HEADLINE2) or item.get("headline"), OUTPUT_LENGTH_LIMIT
)
if not is_picture(item):
etree.SubElement(content, "Headline2").text = format_maxlength(
item.get("headline"), OUTPUT_LENGTH_LIMIT
)
etree.SubElement(content, "SlugProper").text = item.get("slugline")
etree.SubElement(content, "Credit").text = self._format_credit(item)
etree.SubElement(content, "Source").text = item.get("source")
content_html = self._format_content(item, is_broadcast)
etree.SubElement(content, "DirectoryText").text = self._format_text(
item.get("abstract")
)
etree.SubElement(content, "ContentText").text = self._format_html(content_html)
etree.SubElement(content, "Language").text = (
"2" if "fr" in item.get("language", "") else "1"
)
if item["type"] == "text" and content_html:
content.find("DirectoryText").text = format_maxlength(
get_text(content_html, "html", lf_on_block=False).replace("\n", " "),
200,
)
word_count = str(get_word_count(content_html))
etree.SubElement(content, "Length").text = word_count
etree.SubElement(content, "WordCount").text = word_count
etree.SubElement(content, "BreakWordCount").text = word_count
if item.get("keywords") and item.get("source") == globenewswire.SOURCE:
etree.SubElement(content, "Stocks").text = ",".join(item["keywords"])
self._format_category_index(content, item)
self._format_genre(content, item)
self._format_urgency(content, item.get("urgency"), item["language"])
self._format_keyword(
content,
item.get("keywords"),
", " if item.get("type") == "picture" else ",",
)
self._format_dateline(content, item.get("dateline"))
self._format_writethru(content, item)
if item.get("byline"):
etree.SubElement(content, "Byline").text = item["byline"]
if is_picture(item):
self._format_picture_metadata(content, item)
else:
etree.SubElement(content, "EditorNote").text = item.get("ednote")
if extra.get(cp.UPDATE):
etree.SubElement(content, "UpdateNote").text = extra[cp.UPDATE]
if extra.get(cp.CORRECTION):
etree.SubElement(content, "Corrections").text = extra[cp.CORRECTION]
if item.get("associations"):
self._format_associations(content, item)
def _format_item(self, root, item, pub_seq_num, service, services):
if is_picture(item):
D2P1 = 'http://www.w3.org/2001/XMLSchema-instance'
content = etree.SubElement(root,
'ContentItem',
{'{%s}type' % D2P1: 'PhotoContentItem'},
nsmap={
'd2p1': D2P1,
})
else:
content = etree.SubElement(root, 'ContentItem')
extra = item.get('extra') or {}
# root system fields
etree.SubElement(root, 'Reschedule').text = 'false'
etree.SubElement(root, 'IsRegional').text = 'false'
etree.SubElement(root, 'CanAutoRoute').text = 'true'
etree.SubElement(root, 'PublishID').text = str(pub_seq_num)
etree.SubElement(root, 'Username')
etree.SubElement(root, 'UseLocalsOut').text = 'false'
etree.SubElement(root, 'UserProfileID').text = '0'
etree.SubElement(root, 'PublishOrder').text = '0'
etree.SubElement(root, 'NewCycle').text = 'false'
etree.SubElement(root, 'OnlineResend').text = 'false'
# item system fields
etree.SubElement(content, 'AutoSaveID').text = '0'
etree.SubElement(content, 'Type').text = '0'
etree.SubElement(content, 'MediaType').text = '0'
etree.SubElement(content, 'Status').text = '0'
if is_picture(item):
etree.SubElement(root, 'Services').text = 'Pictures'
self._format_subject_code(root, item, 'PscCodes', 'destinations')
if root.find('PscCodes') is None:
etree.SubElement(root, 'PscCodes').text = 'Online'
elif service:
etree.SubElement(root, 'Services').text = 'Print'
etree.SubElement(root, 'PscCodes').text = service
else:
self._format_subject_code(root, item, 'PscCodes', 'destinations')
self._format_services(root, item)
# content system fields
seq_id = '{:08d}'.format(pub_seq_num % 100000000)
filename = self._format_filename(item)
etree.SubElement(content, 'Name')
etree.SubElement(content, 'Cachable').text = 'false'
etree.SubElement(content, 'FileName').text = filename
etree.SubElement(content, 'NewsCompID').text = seq_id
etree.SubElement(content, 'SystemSlug').text = filename
etree.SubElement(content, 'ContentItemID').text = seq_id
etree.SubElement(content, 'ProfileID').text = '204'
etree.SubElement(content, 'SysContentType').text = '0'
if is_picture(item):
etree.SubElement(content, 'PhotoContentItemID').text = seq_id
if extra.get(cp.FILENAME):
etree.SubElement(content, 'OrigTransRef').text = extra[cp.FILENAME]
if service:
etree.SubElement(content, 'Note').text = ','.join(services)
# timestamps
firstpublished = item.get('firstpublished') or item['versioncreated']
etree.SubElement(
root,
'PublishDateTime').text = self._format_datetime(firstpublished)
try:
etree.SubElement(content,
'EmbargoTime').text = self._format_datetime(
item[SCHEDULE_SETTINGS]['utc_embargo'],
local=True,
)
except KeyError:
etree.SubElement(content,
'EmbargoTime').text = self._format_datetime(
item.get('embargoed'), local=True)
etree.SubElement(content,
'CreatedDateTime').text = self._format_datetime(
item['firstcreated'])
etree.SubElement(content,
'UpdatedDateTime').text = self._format_datetime(
item['versioncreated'], rel=True)
# obvious
etree.SubElement(content, 'ContentType').text = 'Photo' if is_picture(
item) else item['type'].capitalize()
# SDCP-309
etree.SubElement(content, 'Headline').text = format_maxlength(
extra.get(cp.HEADLINE2) or item.get('headline'),
OUTPUT_LENGTH_LIMIT)
if not is_picture(item):
etree.SubElement(content, 'Headline2').text = format_maxlength(
item.get('headline'), OUTPUT_LENGTH_LIMIT)
etree.SubElement(content, 'SlugProper').text = item.get('slugline')
etree.SubElement(content, 'Credit').text = self._format_credit(item)
etree.SubElement(content, 'Source').text = item.get('source')
etree.SubElement(content, 'DirectoryText').text = self._format_text(
item.get('abstract'))
etree.SubElement(content, 'ContentText').text = self._format_html(
self._format_content(item))
etree.SubElement(
content,
'Language').text = '2' if 'fr' in item.get('language', '') else '1'
if item['type'] == 'text' and item.get('body_html'):
content.find('DirectoryText').text = format_maxlength(
get_text(item['body_html'], 'html',
lf_on_block=False).replace('\n', ' '), 200)
word_count = str(item['word_count'] if item.get('word_count') else
get_word_count(item['body_html']))
etree.SubElement(content, 'Length').text = word_count
etree.SubElement(content, 'WordCount').text = word_count
etree.SubElement(content, 'BreakWordCount').text = word_count
if item.get('keywords') and item.get('source') == globenewswire.SOURCE:
etree.SubElement(content,
'Stocks').text = ','.join(item['keywords'])
self._format_index(content, item)
self._format_category(content, item)
self._format_genre(content, item)
self._format_urgency(content, item.get('urgency'), item['language'])
self._format_keyword(content, item.get('keywords'),
', ' if item.get('type') == 'picture' else ',')
self._format_dateline(content, item.get('dateline'))
self._format_writethru(content, item.get('rewrite_sequence'),
item['language'])
if item.get('byline'):
etree.SubElement(content, 'Byline').text = item['byline']
if is_picture(item):
self._format_picture_metadata(content, item)
else:
etree.SubElement(content, 'EditorNote').text = item.get('ednote')
if extra.get(cp.UPDATE):
etree.SubElement(content, 'UpdateNote').text = extra[cp.UPDATE]
if extra.get(cp.CORRECTION):
etree.SubElement(content,
'Corrections').text = extra[cp.CORRECTION]
if item.get('associations'):
self._format_associations(content, item)