def fetch_stage(self, harvest_object):
# Check harvest object status
status = self._get_object_extra(harvest_object,'status')
if status == 'delete':
# No need to fetch anything, just pass to the import stage
return True
# We need to fetch the remote document
# Get location
url = self._get_object_extra(harvest_object, 'waf_location')
if not url:
self._save_object_error(
'No location defined for object {0}'.format(harvest_object.id),
harvest_object)
return False
# Get contents
try:
content = self._get_content_as_unicode(url)
except Exception as e:
msg = 'Could not harvest WAF link {0}: {1}'.format(url, e)
self._save_object_error(msg, harvest_object)
return False
# Check if it is an ISO document
document_format = guess_standard(content)
if document_format == 'iso':
harvest_object.content = content
harvest_object.save()
else:
extra = HOExtra(
object=harvest_object,
key='original_document',
value=content)
extra.save()
extra = HOExtra(
object=harvest_object,
key='original_format',
value=document_format)
extra.save()
return True
def add_status():
records = open('wafurls.txt')
results = open('wafurlsstatus.txt', 'w+')
headers = 'count,count_with_date,server,status_code,error,standard,id,unapproved,url'
results.write(headers + '\n')
writer = csv.DictWriter(
results, headers.split(',')
)
for row in records:
row_dict = dict(zip('id unapproved url'.split(),row.split()))
try:
response = requests.get(row_dict['url'], timeout=60)
content = response.content
server = str(response.headers.get('server'))
if server == 'Microsoft-IIS/7.5':
scraper = 'iis'
elif 'apache' in server.lower() or 'nginx' in server.lower() or not response.headers.get('server'):
scraper = 'apache'
else:
scraper = 'other'
row_dict['status_code'] = str(response.status_code)
row_dict['server'] = server
if content and response.status_code == 200:
extracted_waf = extract_waf(content,row_dict['url'], scraper)
row_dict['count'] = str(len(extracted_waf))
row_dict['count_with_date'] = str(len([i for i in extracted_waf if i[1]]))
if extracted_waf:
try:
content_doc = requests.get(extracted_waf[0][0], timeout=60).content
standard = guess_standard(content_doc)
row_dict['standard'] = standard
except Exception, e:
print 'Error guessing format. Error is', e
else:
row_dict['count'] = "0"
row_dict['count_with_date'] = "0"
def add_status():
records = open('wafurls.txt')
results = open('wafurlsstatus.txt', 'w+')
headers = 'count,count_with_date,server,status_code,error,standard,id,unapproved,url'
results.write(headers + '\n')
writer = csv.DictWriter(results, headers.split(','))
for row in records:
row_dict = dict(zip('id unapproved url'.split(), row.split()))
try:
response = requests.get(row_dict['url'], timeout=60)
content = response.content
server = str(response.headers.get('server'))
if server == 'Microsoft-IIS/7.5':
scraper = 'iis'
elif 'apache' in server.lower() or 'nginx' in server.lower(
) or not response.headers.get('server'):
scraper = 'apache'
else:
scraper = 'other'
row_dict['status_code'] = str(response.status_code)
row_dict['server'] = server
if content and response.status_code == 200:
extracted_waf = extract_waf(content, row_dict['url'], scraper)
row_dict['count'] = str(len(extracted_waf))
row_dict['count_with_date'] = str(
len([i for i in extracted_waf if i[1]]))
if extracted_waf:
try:
content_doc = requests.get(extracted_waf[0][0],
timeout=60).content
standard = guess_standard(content_doc)
row_dict['standard'] = standard
except Exception, e:
print 'Error guessing format. Error is', e
else:
row_dict['count'] = "0"
row_dict['count_with_date'] = "0"
if not url:
self._save_object_error(
u'No location defined for object {0}'.format(harvest_object.id),
harvest_object)
return False
# Get contents
try:
content = self._get_content_as_unicode(url)
except Exception, e:
msg = u'Could not harvest WAF link {0}: {1}'.format(url, e)
self._save_object_error(msg, harvest_object)
return False
# Check if it is an ISO document
document_format = guess_standard(content)
if document_format == u'iso':
harvest_object.content = content
harvest_object.save()
else:
extra = HOExtra(
object=harvest_object,
key=u'original_document',
value=content)
extra.save()
extra = HOExtra(
object=harvest_object,
key=u'original_format',
value=document_format)
extra.save()
class GeoDataGovGeoportalHarvester(CSWHarvester, GeoDataGovHarvester):
'''
A Harvester for CSW servers, with customizations for geo.data.gov
'''
def info(self):
return {
'name': 'geoportal',
'title': 'Geoportal Server',
'description': 'A Geoportal Server CSW endpoint',
}
def output_schema(self):
return 'csw'
def fetch_stage(self, harvest_object):
log = logging.getLogger(__name__ + '.geoportal.fetch')
log.debug('CswHarvester fetch_stage for object: %s', harvest_object.id)
url = harvest_object.source.url
identifier = harvest_object.guid
parts = urlparse.urlparse(url)
url = urlparse.urlunparse((parts.scheme, parts.netloc, '/'.join(
parts.path.rstrip('/').split('/')[:-2]), None, None, None))
url = url.rstrip('/') + '/rest/document?id=%s' % identifier
try:
response = requests.get(url)
content = response.content
except Exception, e:
self._save_object_error(
'Error getting the record with GUID %s from %s' %
(identifier, url), harvest_object)
return False
try:
# Save the fetch contents in the HarvestObject
# Contents come from csw_client already declared and encoded as utf-8
# Remove original XML declaration
content = re.sub('<\?xml(.*)\?>', '', content)
document_format = guess_standard(content)
if document_format == 'iso':
harvest_object.content = content
harvest_object.save()
elif document_format == 'fgdc':
extra = HOExtra(object=harvest_object,
key='original_document',
value=content)
extra.save()
extra = HOExtra(object=harvest_object,
key='original_format',
value=document_format)
extra.save()
else:
harvest_object.report_status = 'ignored'
harvest_object.save()
return False
except Exception, e:
self._save_object_error('Error saving the harvest object for GUID %s [%r]' % \
(identifier, e), harvest_object)
return False
if not url:
self._save_object_error(
'No location defined for object {0}'.format(harvest_object.id),
harvest_object)
return False
# Get contents
try:
content = self._get_content_as_unicode(url)
except Exception, e:
msg = 'Could not harvest WAF link {0}: {1}'.format(url, e)
self._save_object_error(msg, harvest_object)
return False
# Check if it is an ISO document
document_format = guess_standard(content)
if document_format == 'iso':
harvest_object.content = content
harvest_object.save()
else:
extra = HOExtra(
object=harvest_object,
key='original_document',
value=content)
extra.save()
extra = HOExtra(
object=harvest_object,
key='original_format',
value=document_format)
extra.save()
class DocHarvester(SpatialHarvester, SingletonPlugin):
'''A Harvester for individual spatial metadata documents
TODO: Move to new logic
'''
implements(IHarvester)
def info(self):
''' '''
return {
u'name': u'single-doc',
u'title': u'Single spatial metadata document',
u'description': u'A single spatial metadata document'
}
def get_original_url(self, harvest_object_id):
'''
:param harvest_object_id:
'''
obj = model.Session.query(HarvestObject).filter(
HarvestObject.id == harvest_object_id).first()
if not obj:
return None
return obj.source.url
def gather_stage(self, harvest_job):
'''
:param harvest_job:
'''
log = logging.getLogger(__name__ + u'.individual.gather')
log.debug(u'DocHarvester gather_stage for job: %r', harvest_job)
self.harvest_job = harvest_job
# Get source URL
url = harvest_job.source.url
self._set_source_config(harvest_job.source.config)
# Get contents
try:
content = self._get_content_as_unicode(url)
except Exception, e:
self._save_gather_error(u'Unable to get content for URL: %s: %r' % (url, e),
harvest_job)
return None
existing_object = model.Session.query(HarvestObject.guid,
HarvestObject.package_id).filter(
HarvestObject.current is True).filter(
HarvestObject.harvest_source_id == harvest_job.source.id).first()
def create_extras(url, status):
'''
:param url:
:param status:
'''
return [HOExtra(key=u'doc_location', value=url),
HOExtra(key=u'status', value=status)]
if not existing_object:
guid = hashlib.md5(url.encode(u'utf8', u'ignore')).hexdigest()
harvest_object = HarvestObject(job=harvest_job,
extras=create_extras(url,
u'new'),
guid=guid
)
else:
harvest_object = HarvestObject(job=harvest_job,
extras=create_extras(url,
u'change'),
guid=existing_object.guid,
package_id=existing_object.package_id
)
harvest_object.add()
# Check if it is an ISO document
document_format = guess_standard(content)
if document_format == u'iso':
harvest_object.content = content
else:
extra = HOExtra(
object=harvest_object,
key=u'original_document',
value=content)
extra.save()
extra = HOExtra(
object=harvest_object,
key=u'original_format',
value=document_format)
extra.save()
harvest_object.save()
return [harvest_object.id]
def gather_stage(self, harvest_job):
log = logging.getLogger(__name__ + '.individual.gather')
log.debug('DocHarvester gather_stage for job: %r', harvest_job)
self.harvest_job = harvest_job
# Get source URL
url = harvest_job.source.url
self._set_source_config(harvest_job.source.config)
# Get contents
try:
content = self._get_content_as_unicode(url)
except Exception as e:
self._save_gather_error('Unable to get content for URL: %s: %r' % \
(url, e),harvest_job)
return None
existing_object = model.Session.query(HarvestObject.guid, HarvestObject.package_id).\
filter(HarvestObject.current==True).\
filter(HarvestObject.harvest_source_id==harvest_job.source.id).\
first()
def create_extras(url, status):
return [
HOExtra(key='doc_location', value=url),
HOExtra(key='status', value=status)
]
if not existing_object:
guid = hashlib.md5(url.encode('utf8', 'ignore')).hexdigest()
harvest_object = HarvestObject(job=harvest_job,
extras=create_extras(url, 'new'),
guid=guid)
else:
harvest_object = HarvestObject(
job=harvest_job,
extras=create_extras(url, 'change'),
guid=existing_object.guid,
package_id=existing_object.package_id)
harvest_object.add()
# Check if it is an ISO document
document_format = guess_standard(content)
if document_format == 'iso':
harvest_object.content = content
else:
extra = HOExtra(object=harvest_object,
key='original_document',
value=content)
extra.save()
extra = HOExtra(object=harvest_object,
key='original_format',
value=document_format)
extra.save()
harvest_object.save()
return [harvest_object.id]
