def _save_url(self,
url,
bucket,
object_name,
num_retries,
seconds_between_retries,
retry_num=1):
try:
res = self._reuqests_get(url)
except RequestException as e:
if retry_num < num_retries:
logging.exception(e)
logging.info(
"retry {} / {}, waiting {} seconds before retrying...".
format(retry_num, num_retries, seconds_between_retries))
time.sleep(seconds_between_retries)
return self._save_url(url, bucket, object_name, num_retries,
seconds_between_retries, retry_num + 1)
else:
raise
if res.status_code == 200:
object_storage.write(self.s3, bucket, object_name, res.content)
return True
else:
return False
def _save_schema_html(self, save_schema):
object_name = save_schema.format(table_name=self._tablename,
ext="html")
bucket = self._parameters["schemas-bucket"]
object_storage.write(self.s3,
bucket,
object_name,
self._get_schema_html(),
public_bucket=True)
def _save_schema_json(self, save_schema):
object_name = save_schema.format(table_name=self._tablename,
ext="json")
bucket = self._parameters["schemas-bucket"]
object_storage.write(self.s3,
bucket,
object_name,
json.dumps(self._schema, indent=2),
public_bucket=True)
def _parse_doc_protocol(self, committee_id, meeting_id, bucket, protocol_object_name, parts_object_name, text_object_name):
logging.info("parsing doc protocol {} --> {}, {}".format(protocol_object_name, parts_object_name, text_object_name))
with object_storage.temp_download(self.s3, bucket, protocol_object_name) as protocol_filename:
try:
with CommitteeMeetingProtocol.get_from_filename(protocol_filename) as protocol:
object_storage.write(self.s3, bucket, text_object_name, protocol.text, public_bucket=True)
self._parse_protocol_parts(bucket, parts_object_name, protocol)
except (
AntiwordException, # see https://github.com/hasadna/knesset-data-pipelines/issues/15
subprocess.SubprocessError,
xml.etree.ElementTree.ParseError # see https://github.com/hasadna/knesset-data-pipelines/issues/32
):
logging.exception("committee {} meeting {}: failed to parse doc file, skipping".format(committee_id, meeting_id))
return False
return True
def _save_url(self, url, bucket, object_name, num_retries, seconds_between_retries, retry_num=1):
try:
res = self._reuqests_get(url)
except RequestException as e:
if retry_num < num_retries:
logging.exception(e)
logging.info("retry {} / {}, waiting {} seconds before retrying...".format(retry_num, num_retries, seconds_between_retries))
time.sleep(seconds_between_retries)
return self._save_url(url, bucket, object_name, num_retries, seconds_between_retries, retry_num+1)
else:
raise
if res.status_code == 200:
object_storage.write(self.s3, bucket, object_name, res.content, public_bucket=True)
return True
else:
return False
def filter_resources(datapackage, resources, parameters, stats):
tables = []
for resource_descriptor, resource_data in zip(datapackage["resources"], resources):
schema = resource_descriptor["schema"]
stats[resource_descriptor["name"]] = 0
tables.append(_get_schema_table(resource_descriptor["name"], schema["fields"], schema["primaryKey"]))
yield filter_resource(resource_descriptor, resource_data, stats)
html = """<html><head><meta charset="UTF-8"></head><body>{tables}</body></html>""".format(tables="".join(tables))
save_schema = parameters.get("save-schema", DEFAULT_SAVE_SCHEMA)
if save_schema:
save_schema_html = DEFAULT_SAVE_SCHEMA.format(table_name=datapackage["name"], ext="html")
save_schema_json = DEFAULT_SAVE_SCHEMA.format(table_name=datapackage["name"], ext="json")
s3 = object_storage.get_s3()
object_storage.write(s3, parameters["bucket"], save_schema_html, html, public_bucket=True)
object_storage.write(s3, parameters["bucket"], save_schema_json, json.dumps(datapackage["resources"], indent=2, ensure_ascii=False), public_bucket=True)
