def body_hook(self, item, html):
"""Copy content to body_html
if img are found in the content, they are uploaded.
First image is used as feature media, then there are embeds
"""
if "img" in html:
content = sd_etree.parse_html(html, 'html')
for img in content.xpath('//img'):
src = img.get('src')
try:
key, media_data = self._add_image(item, src)
except Exception as e:
logger.error(e)
img.getparent().remove(img)
continue
_id = media_data['_id']
url = url_for_media(_id)
img.set("src", url)
if key == 'featuremedia':
# no need to embed the image for featuremedia
continue
embed_start = etree.Comment(embed_TPL.format('START', key))
embed_end = etree.Comment(embed_TPL.format('END', key))
img.addprevious(embed_start)
img.addnext(embed_end)
html = etree.tostring(content, encoding="unicode")
item['body_html'] = html
def import_rendition(guid, rendition_name, href, extract_metadata, trigger_events):
archive = superdesk.apps["archive"].find_one(req=None, guid=guid)
if not archive:
msg = "No document found in the media archive with this ID: %s" % guid
raise superdesk.SuperdeskError(payload=msg)
if rendition_name not in archive["renditions"]:
payload = "Invalid rendition name %s" % rendition_name
raise superdesk.SuperdeskError(payload=payload)
updates = {}
metadata = None
content, filename, content_type = download_file_from_url(href)
if extract_metadata:
file_type, ext = content_type.split("/")
metadata = process_file(content, file_type)
file_guid = app.media.put(content, filename, content_type, metadata)
# perform partial update
updates["renditions." + rendition_name + ".href"] = url_for_media(file_guid)
updates["renditions." + rendition_name + ".media"] = file_guid
result = superdesk.apps["archive"].update(id=guid, updates=updates, trigger_events=trigger_events)
return result
def attachments_hook(self, item, attachments):
"""Attachment are parsed at the end
if it's the first image found, it's used as feature media
else it's used as embed and put at the end of body_html
"""
for url in attachments:
try:
key, media_data = self._add_image(item, url)
except Exception as e:
logger.error(e)
continue
if key == 'featuremedia':
# no need to embed the image for featuremedia
continue
embed_start = "<!--" + embed_TPL.format('START', key) + "-->"
embed_end = "<!--" + embed_TPL.format('END', key) + "-->"
_id = media_data['_id']
new_url = url_for_media(_id)
img = '<img src={src} height="{height}" width="{width}">'.format(
src=quoteattr(new_url),
height=media_data['renditions']['original']['height'],
width=media_data['renditions']['original']['width'])
item[
'body_html'] += '<div>' + embed_start + img + embed_end + '</div>'
def import_rendition(guid, rendition_name, href, extract_metadata,
trigger_events):
archive = superdesk.apps['archive'].find_one(req=None, guid=guid)
if not archive:
msg = 'No document found in the media archive with this ID: %s' % guid
raise superdesk.SuperdeskError(payload=msg)
if rendition_name not in archive['renditions']:
payload = 'Invalid rendition name %s' % rendition_name
raise superdesk.SuperdeskError(payload=payload)
updates = {}
metadata = None
content, filename, content_type = download_file_from_url(href)
if extract_metadata:
file_type, ext = content_type.split('/')
metadata = process_file(content, file_type)
file_guid = app.media.put(content, filename, content_type, metadata)
# perform partial update
updates['renditions.' + rendition_name +
'.href'] = url_for_media(file_guid)
updates['renditions.' + rendition_name + '.media'] = file_guid
result = superdesk.apps['archive'].update(id=guid,
updates=updates,
trigger_events=trigger_events)
return result
def _save_cropped_image(self, file_stream, original, doc):
"""
Saves the cropped image and returns the crop dictionary
:param file_stream: cropped image stream
:param original: original rendition
:param doc: crop data
:return dict: Crop values
:raises SuperdeskApiError.internalError
"""
crop = {}
try:
file_name, content_type, metadata = process_file_from_stream(
file_stream, content_type=original.get('mimetype'))
file_stream.seek(0)
file_id = superdesk.app.media.put(file_stream,
filename=file_name,
content_type=content_type,
resource='upload',
metadata=metadata)
crop['media'] = file_id
crop['mimetype'] = content_type
crop['href'] = url_for_media(file_id, content_type)
crop['CropTop'] = doc.get('CropTop', None)
crop['CropLeft'] = doc.get('CropLeft', None)
crop['CropRight'] = doc.get('CropRight', None)
crop['CropBottom'] = doc.get('CropBottom', None)
return crop
except Exception as ex:
try:
superdesk.app.media.delete(file_id)
except:
pass
raise SuperdeskApiError.internalError(
'Generating crop failed: {}'.format(str(ex)))
def _save_cropped_image(self, file_stream, original, doc):
"""Saves the cropped image and returns the crop dictionary
:param file_stream: cropped image stream
:param original: original rendition
:param doc: crop data
:return dict: Crop values
:raises SuperdeskApiError.internalError
"""
crop = {}
try:
file_name, content_type, metadata = process_file_from_stream(
file_stream, content_type=original.get("mimetype")
)
file_stream.seek(0)
file_id = app.media.put(
file_stream, filename=file_name, content_type=content_type, resource="upload", metadata=metadata
)
crop["media"] = file_id
crop["mimetype"] = content_type
crop["href"] = url_for_media(file_id, content_type)
crop["CropTop"] = doc.get("CropTop", None)
crop["CropLeft"] = doc.get("CropLeft", None)
crop["CropRight"] = doc.get("CropRight", None)
crop["CropBottom"] = doc.get("CropBottom", None)
return crop
except Exception as ex:
try:
app.media.delete(file_id)
except Exception:
pass
raise SuperdeskApiError.internalError("Generating crop failed: {}".format(str(ex)), exception=ex)
def _save_cropped_image(self, file_stream, original, doc):
"""
Saves the cropped image and returns the crop dictionary
:param file_stream: cropped image stream
:param original: original rendition
:param doc: crop data
:return dict: Crop values
:raises SuperdeskApiError.internalError
"""
crop = {}
try:
file_name, content_type, metadata = process_file_from_stream(file_stream,
content_type=original.get('mimetype'))
file_stream.seek(0)
file_id = superdesk.app.media.put(file_stream, filename=file_name,
content_type=content_type,
resource='upload',
metadata=metadata)
crop['media'] = file_id
crop['mimetype'] = content_type
crop['href'] = url_for_media(file_id, content_type)
crop['CropTop'] = doc.get('CropTop', None)
crop['CropLeft'] = doc.get('CropLeft', None)
crop['CropRight'] = doc.get('CropRight', None)
crop['CropBottom'] = doc.get('CropBottom', None)
return crop
except Exception as ex:
try:
superdesk.app.media.delete(file_id)
except:
pass
raise SuperdeskApiError.internalError('Generating crop failed: {}'.format(str(ex)))
def import_rendition(guid, rendition_name, href, extract_metadata):
archive = superdesk.get_resource_service(ARCHIVE).find_one(req=None, guid=guid)
if not archive:
msg = 'No document found in the media archive with this ID: %s' % guid
raise superdesk.SuperdeskError(payload=msg)
if rendition_name not in archive['renditions']:
payload = 'Invalid rendition name %s' % rendition_name
raise superdesk.SuperdeskError(payload=payload)
updates = {}
metadata = None
content, filename, content_type = download_file_from_url(href)
if extract_metadata:
file_type, ext = content_type.split('/')
metadata = process_file(content, file_type)
file_guid = app.media.put(content, filename, content_type, metadata)
# perform partial update
updates['renditions.' + rendition_name + '.href'] = url_for_media(file_guid)
updates['renditions.' + rendition_name + '.media'] = file_guid
result = superdesk.get_resource_service(ARCHIVE).patch(guid, updates=updates)
return result
def zip_items(result_id, items_ids):
result_id = ObjectId(result_id)
archive_service = get_resource_service('archive')
vppzip_service = get_resource_service('verifiedpixel_zip')
results_service = get_resource_service('verification_results')
item = vppzip_service.find_one(_id=result_id, req=None)
vppzip_service.system_update(result_id, {'status': "processing"}, item)
items = list(archive_service.get_from_mongo(
req=ParsedRequest(), lookup={'_id': {'$in': items_ids}}))
verification_ids = [item['verification']['results'] for item in items]
verification_results = {
result['_id']: result for result in
list(results_service.get_from_mongo(
req=ParsedRequest(), lookup={'_id': {'$in': verification_ids}})
)
}
verification_data_object = StringIO()
verification_data = {}
zip_file_object = BytesIO()
zip_file = zipfile.ZipFile(zip_file_object, mode='w')
for item in items:
item_id = item['_id']
image = get_original_image(item, 'archive')[1]
zip_file.writestr(item_id, image)
item['verification']['results'] = verification_results[
item['verification']['results']
]
for field in ['_id', '_etag', '_created', '_updated']:
del item['verification']['results'][field]
verification_data[item_id] = item['verification']
json.dump(verification_data, verification_data_object)
zip_file.writestr('verification.json', verification_data_object.getvalue())
zip_file.close()
uploaded_zip_id = app.media.put(
zip_file_object.getvalue(), filename="{name}_{date}.zip".format(
name=items[0].get('slugline', None) or 'image' if len(items) == 1 else 'images',
date=datetime.now().isoformat()
),
content_type='application/zip',
resource=vppzip_service.datasource,
metadata={}
)
uploaded_zip_url = url_for_media(uploaded_zip_id)
item = vppzip_service.find_one(_id=result_id, req=None)
vppzip_service.system_update(result_id, {
"status": "done",
"result": uploaded_zip_url,
"result_id": uploaded_zip_id
}, item)
push_notification(
'verifiedpixel_zip:ready',
id=str(result_id),
url=uploaded_zip_url
)
def zip_items(result_id, items_ids):
archive_service = get_resource_service('archive')
vppzip_service = get_resource_service('verifiedpixel_zip')
results_service = get_resource_service('verification_results')
vppzip_service.patch(
result_id,
{'status': "processing"},
)
items = list(archive_service.get_from_mongo(
req=ParsedRequest(), lookup={'_id': {'$in': items_ids}}))
verification_ids = [item['verification']['results'] for item in items]
verification_results = {
result['_id']: result for result in
list(results_service.get_from_mongo(
req=ParsedRequest(), lookup={'_id': {'$in': verification_ids}})
)
}
verification_data_object = StringIO()
verification_data = {}
zip_file_object = BytesIO()
zip_file = zipfile.ZipFile(zip_file_object, mode='w')
for item in items:
item_id = item['_id']
image = get_original_image(item)[1]
zip_file.writestr(item_id, image)
item['verification']['results'] = verification_results[
item['verification']['results']
]
for field in ['_id', '_etag', '_created', '_updated']:
del item['verification']['results'][field]
verification_data[item_id] = item['verification']
json.dump(verification_data, verification_data_object)
zip_file.writestr('verification.json', verification_data_object.getvalue())
zip_file.close()
uploaded_zip_id = app.media.put(
zip_file_object.getvalue(), filename=str(items_ids),
content_type='application/zip',
resource=vppzip_service.datasource,
metadata={}
)
uploaded_zip_url = url_for_media(uploaded_zip_id)
vppzip_service.patch(result_id, {
"status": "done",
"result": uploaded_zip_url,
"result_id": uploaded_zip_id
})
def import_rendition(guid, rendition_name, href, trigger_events):
archive = superdesk.apps['archive'].find_one(req=None, guid=guid)
if not archive:
msg = 'No document found in the media archive with this ID: %s' % guid
raise superdesk.SuperdeskError(payload=msg)
if rendition_name not in archive['renditions']:
payload = 'Invalid rendition name %s' % rendition_name
raise superdesk.SuperdeskError(payload=payload)
file_guid = download_file_from_url(href)
updates = {}
# perform partial update
updates['renditions.' + rendition_name + '.href'] = url_for_media(file_guid)
result = superdesk.apps['archive'].update(id=guid, updates=updates, trigger_events=trigger_events)
return result
def prepare_href(self, href, mimetype=None):
return url_for_media(href, mimetype)
def prepare_href(self, href, mimetype=None):
return url_for_media(href, mimetype)
def prepare_href(self, href):
return url_for_media(href)
def prepare_href(self, href):
return url_for_media(href)
