def save_url(self, filename, data, file_path):
save_content_response = save_content(data['url'], file_path)
if save_content_response.errors:
return self.SaveUrlResult(errors=save_content_response.errors,
warnings=save_content_response.warnings)
additional = []
if not self.sample:
with open(file_path) as f:
json_data = json.load(f)
if 'links' in json_data and 'next' in json_data[
'links'] and json_data['links']['next']:
additional.append({
'url':
json_data['links']['next'],
'filename':
'page-%s.json' %
hashlib.md5(json_data['links']['next'].encode(
'utf-8')).hexdigest(),
'data_type':
'release_package',
# We set priority the same so that all the requests for one year are done at the same time.
# Because of how this pages using cursors, it's probably best to get them as fast as possible.
'priority':
data['priority'],
})
return self.SaveUrlResult(additional_files=additional,
warnings=save_content_response.warnings)
def save_url(self, filename, data, file_path):
save_content_response = save_content(data['url'], file_path)
if save_content_response.errors:
return self.SaveUrlResult(errors=save_content_response.errors,
warnings=save_content_response.warnings)
additional = []
if data['data_type'] == 'record_package':
with open(file_path) as f:
json_data = json.load(f)
if 'packages' in json_data:
for url in json_data['packages']:
additional.append({
'url':
url,
'filename':
'packages-%s.json' %
hashlib.md5(url.encode('utf-8')).hexdigest(),
'data_type':
'release_package',
})
return self.SaveUrlResult(additional_files=additional,
warnings=save_content_response.warnings)
def save_url(self, filename, data, file_path):
if data['data_type'] == 'meta':
response, errors = util.get_url_request(data['url'], verify_ssl=False)
if errors:
return self.SaveUrlResult(errors=errors)
data = json.loads(response.text)
additional = []
if "data" in data.keys():
# Sometimes it's a dict, sometimes it's a list.
if isinstance(data['data'], dict):
data['data'] = data['data'].values()
for data_item in data["data"]:
if not self.sample or (self.sample and len(additional) < 10):
additional.append({
'url': data_item['uri'],
'filename': '{}.json'.format(data_item['ocid']),
'data_type': 'release',
'priority': 1,
})
return self.SaveUrlResult(additional_files=additional)
else:
save_content_response = util.save_content(data['url'], file_path, verify_ssl=False)
return self.SaveUrlResult(errors=save_content_response.errors, warnings=save_content_response.warnings)
def save_url(self, filename, data, file_path):
if data['data_type'] == 'release_package':
save_content_response = save_content(data['url'], file_path)
if save_content_response.errors:
return self.SaveUrlResult(
errors=save_content_response.errors,
warnings=save_content_response.warnings)
additional = []
with open(file_path) as f:
json_data = json.load(f)
page = int(filename.split('-')[1])
if 'next_page' in json_data and 'uri' in json_data[
'next_page'] and (not self.sample or page < 3):
page += 1
additional.append({
'url': json_data['next_page']['uri'],
'filename': 'page-%d-.json' % page,
'data_type': 'release_package',
})
return self.SaveUrlResult(additional_files=additional,
warnings=save_content_response.warnings)
def save_url(self, filename, data, file_path):
save_content_response = save_content(data['url'], file_path+'-temp.tar.gz', replace_control_codes=False)
if save_content_response.errors:
return self.SaveUrlResult(errors=save_content_response.errors, warnings=save_content_response.warnings)
with tarfile.open(file_path+'-temp.tar.gz', "r:gz") as tar:
with tar.extractfile(tar.getnames()[0]) as readfp:
with open(file_path, "wb") as writefp:
while True:
buf = readfp.read(1024 ^ 2)
if buf:
writefp.write(buf)
else:
break
return self.SaveUrlResult()
def save_url(self, filename, data, file_path):
save_content_response = save_content(data['url'], file_path)
if save_content_response.errors:
return self.SaveUrlResult(errors=save_content_response.errors, warnings=save_content_response.warnings)
additional = []
if data['data_type'] == 'meta':
with open(file_path) as f:
json_data = json.load(f)
for item in json_data:
if not self.sample or (self.sample and len(additional) < 10):
additional.append({
'url': item,
'filename': 'release-%s.json' % item.split('/')[-1],
'data_type': 'release',
})
return self.SaveUrlResult(additional_files=additional, warnings=save_content_response.warnings)
def save_url(self, file_name, data, file_path):
save_content_response = save_content(data['url'], file_path)
return self.SaveUrlResult(errors=save_content_response.errors,
warnings=save_content_response.warnings)
def save_url(self, filename, data, file_path):
save_content_response = save_content(data['url'], file_path)
if save_content_response.errors:
return self.SaveUrlResult(errors=save_content_response.errors,
warnings=save_content_response.warnings)
additional = []
if data['data_type'] == 'meta':
with open(file_path) as f:
json_data = json.load(f)
page = int(filename.split('-')[3])
type = filename.split('-')[1]
if 'links' in json_data and 'next' in json_data['links'] and (
not self.sample or page < 3):
page += 1
additional.append({
'url':
json_data['links']['next'],
'filename':
'type-%s-page-%d-.json' % (type, page),
'data_type':
'meta',
'priority':
10,
})
count = 0
for release in json_data['releases']:
if not self.sample or count < 3:
stage_urls = []
if type == 'planning':
uuid = release['tender']['plannedProcurementUUID']
stage_urls.append(
'https://tenders.nsw.gov.au/?event=public.api.planning.view'
'&PlannedProcurementUUID=%s' % uuid)
if type == 'tender':
uuid = release['tender']['RFTUUID']
stage_urls.append(
'https://tenders.nsw.gov.au/?event=public.api.tender.view&RFTUUID=%s'
% uuid)
if type == 'contract':
for award in release['awards']:
uuid = award['CNUUID']
stage_urls.append(
'https://tenders.nsw.gov.au/?event=public.api.contract.view&CNUUID=%s'
% uuid)
count += 1
for url in stage_urls:
additional.append({
'url':
url,
'filename':
'packages-%s.json' %
hashlib.md5(url.encode('utf-8')).hexdigest(),
'data_type':
'release_package',
'priority':
1,
})
return self.SaveUrlResult(additional_files=additional,
warnings=save_content_response.warnings)
