|
C
|
ca
|
2020-07-05 04:15:54
|
2020-07-05 04:15:55
|
|
D>
04:18:34 WARNING pupa: validation of Membership 97ac497e-be76-11ea-92f7-3ec7af0fe542 failed: 2 validation errors:
Value '<a href=tel:587.493.2050">587.493.2050</a>"' for field '' does not match regular expression '\A1 \d{3} \d{3}-\d{4}(?: x\d+)?\Z'
Value '<a href=tel:587.493.9562">587.493.9562</a>"' for field '' does not match regular expression '\A1 \d{3} \d{3}-\d{4}(?: x\d+)?\Z'
04:18:34 WARNING pupa: could not save RunPlan, no successful runs of ocd-jurisdiction/country:ca/province:ab/legislature yet
|
ca_ab
|
|
2020-07-05 04:18:34
|
Value '<a href=tel:587.493.9562">587.493.9562</a>"' for field '' does not match regular expression '\A1 \d{3} \d{3}-\d{4}(?:…
Traceback (most recent call last):
File "/app/.heroku/src/pupa/pupa/scrape/base.py", line 175, in validate
validator.validate(self.as_dict(), schema)
File "/app/.heroku/python/lib/python3.6/site-packages/validictory/validator.py", line 620, in validate
raise MultipleValidationError(self._errors)
validictory.validator.MultipleValidationError: 2 validation errors:
Value '<a href=tel:587.493.2050">587.493.2050</a>"' for field '' does not match regular expression '\A1 \d{3} \d{3}-\d{4}(?: x\d+)?\Z'
Value '<a href=tel:587.493.9562">587.493.9562</a>"' for field '' does not match regular expression '\A1 \d{3} \d{3}-\d{4}(?: x\d+)?\Z'
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "/app/reports/utils.py", line 71, in scrape_people
report.report = subcommand.handle(args, other)
File "/app/.heroku/src/pupa/pupa/cli/commands/update.py", line 260, in handle
return self.do_handle(args, other, juris)
File "/app/.heroku/src/pupa/pupa/cli/commands/update.py", line 305, in do_handle
report['scrape'] = self.do_scrape(juris, args, scrapers)
File "/app/.heroku/src/pupa/pupa/cli/commands/update.py", line 173, in do_scrape
report[scraper_name] = scraper.do_scrape(**scrape_args)
File "/app/.heroku/src/pupa/pupa/scrape/base.py", line 104, in do_scrape
self.save_object(obj)
File "/app/.heroku/src/pupa/pupa/scrape/base.py", line 93, in save_object
self.save_object(obj)
File "/app/.heroku/src/pupa/pupa/scrape/base.py", line 89, in save_object
raise ve
File "/app/.heroku/src/pupa/pupa/scrape/base.py", line 85, in save_object
obj.validate()
File "/app/.heroku/src/pupa/pupa/scrape/base.py", line 178, in validate
self.__class__.__name__, self._id, ve)
pupa.exceptions.ScrapeValueError: validation of Membership 97ac497e-be76-11ea-92f7-3ec7af0fe542 failed: 2 validation errors:
Value '<a href=tel:587.493.2050">587.493.2050</a>"' for field '' does not match regular expression '\A1 \d{3} \d{3}-\d{4}(?: x\d+)?\Z'
Value '<a href=tel:587.493.9562">587.493.9562</a>"' for field '' does not match regular expression '\A1 \d{3} \d{3}-\d{4}(?: x\d+)?\Z'
|
|
D>
|
ca_ab_calgary
|
2020-06-22 04:42:14
|
2020-07-05 04:30:25
|
AssertionError: No councillors found
Traceback (most recent call last):
File "/app/reports/utils.py", line 71, in scrape_people
report.report = subcommand.handle(args, other)
File "/app/.heroku/src/pupa/pupa/cli/commands/update.py", line 260, in handle
return self.do_handle(args, other, juris)
File "/app/.heroku/src/pupa/pupa/cli/commands/update.py", line 305, in do_handle
report['scrape'] = self.do_scrape(juris, args, scrapers)
File "/app/.heroku/src/pupa/pupa/cli/commands/update.py", line 173, in do_scrape
report[scraper_name] = scraper.do_scrape(**scrape_args)
File "/app/.heroku/src/pupa/pupa/scrape/base.py", line 99, in do_scrape
for obj in self.scrape(**kwargs) or []:
File "/app/scrapers/ca_ab_calgary/people.py", line 14, in scrape
assert len(councillors), 'No councillors found'
AssertionError: No councillors found
|
D>
04:22:13 WARNING pupa: could not save RunPlan, no successful runs of ocd-jurisdiction/country:ca/province:ab/executive yet
|
ca_ab_candidates
|
|
2020-07-05 04:22:13
|
pupa.exceptions.UnresolvedIdError: cannot resolve pseudo id to Post: ~{"label": "Calgary-Bow", "organization__classification…
Traceback (most recent call last):
File "/app/reports/utils.py", line 71, in scrape_people
report.report = subcommand.handle(args, other)
File "/app/.heroku/src/pupa/pupa/cli/commands/update.py", line 260, in handle
return self.do_handle(args, other, juris)
File "/app/.heroku/src/pupa/pupa/cli/commands/update.py", line 307, in do_handle
report['import'] = self.do_import(juris, args)
File "/app/.heroku/src/pupa/pupa/cli/commands/update.py", line 211, in do_import
report.update(membership_importer.import_directory(datadir))
File "/app/.heroku/src/pupa/pupa/importers/base.py", line 190, in import_directory
return self.import_data(json_stream())
File "/app/.heroku/src/pupa/pupa/importers/base.py", line 227, in import_data
obj_id, what = self.import_item(data)
File "/app/.heroku/src/pupa/pupa/importers/base.py", line 247, in import_item
data = self.prepare_for_db(data)
File "/app/.heroku/src/pupa/pupa/importers/memberships.py", line 50, in prepare_for_db
data['post_id'] = self.post_importer.resolve_json_id(data['post_id'])
File "/app/.heroku/src/pupa/pupa/importers/base.py", line 165, in resolve_json_id
raise UnresolvedIdError(errmsg)
pupa.exceptions.UnresolvedIdError: cannot resolve pseudo id to Post: ~{"label": "Calgary-Bow", "organization__classification": "executive", "role": "MLA"}
|
|
C
|
ca_ab_edmonton
|
2020-07-05 04:30:50
|
2020-07-05 04:30:50
|
|
|
D>
|
ca_ab_grande_prairie
|
2020-05-15 04:13:50
|
2020-07-05 04:21:23
|
KeyError: 'name'
Traceback (most recent call last):
File "/app/reports/utils.py", line 71, in scrape_people
report.report = subcommand.handle(args, other)
File "/app/.heroku/src/pupa/pupa/cli/commands/update.py", line 260, in handle
return self.do_handle(args, other, juris)
File "/app/.heroku/src/pupa/pupa/cli/commands/update.py", line 305, in do_handle
report['scrape'] = self.do_scrape(juris, args, scrapers)
File "/app/.heroku/src/pupa/pupa/cli/commands/update.py", line 173, in do_scrape
report[scraper_name] = scraper.do_scrape(**scrape_args)
File "/app/.heroku/src/pupa/pupa/scrape/base.py", line 99, in do_scrape
for obj in self.scrape(**kwargs) or []:
File "/app/scrapers/utils.py", line 375, in scrape
if not self.is_valid_row(row):
File "/app/scrapers/utils.py", line 336, in is_valid_row
return row['name'] not in empty
KeyError: 'name'
|
|
C
|
ca_ab_grande_prairie_county_no_1
|
2020-07-05 04:24:22
|
2020-07-05 04:24:22
|
|
|
C
|
ca_ab_lethbridge
|
2020-07-05 04:22:06
|
2020-07-05 04:22:06
|
|
|
C
|
ca_ab_strathcona_county
|
2020-07-05 04:04:01
|
2020-07-05 04:04:01
|
|
|
C
|
ca_ab_wood_buffalo
|
2020-07-05 04:43:15
|
2020-07-05 04:43:15
|
|
|
C
|
ca_bc
|
2020-07-05 04:23:52
|
2020-07-05 04:23:52
|
|
|
C
|
ca_bc_abbotsford
|
2020-07-05 04:19:43
|
2020-07-05 04:19:43
|
|
|
C
|
ca_bc_burnaby
|
2020-07-05 04:31:27
|
2020-07-05 04:31:27
|
|
|
C
|
ca_bc_coquitlam
|
2020-07-05 04:30:36
|
2020-07-05 04:30:36
|
|
|
C
|
ca_bc_kelowna
|
2020-07-05 04:21:32
|
2020-07-05 04:21:32
|
|
|
C
|
ca_bc_langley
|
2020-07-05 04:21:36
|
2020-07-05 04:21:36
|
|
|
C
|
ca_bc_municipalities
|
2020-07-05 04:37:45
|
2020-07-05 04:37:46
|
|
|
C
|
ca_bc_municipalities_candidates
|
2020-07-05 04:46:10
|
2020-07-05 04:46:11
|
|
|
C
|
ca_bc_new_westminster
|
2020-07-05 04:00:56
|
2020-07-05 04:00:56
|
|
|
C
|
ca_bc_richmond
|
2020-07-05 04:38:24
|
2020-07-05 04:38:24
|
|
D>
04:29:21 WARNING pupa: could not save RunPlan, no successful runs of ocd-jurisdiction/country:ca/csd:5917021/legislature yet
|
ca_bc_saanich
|
|
2020-07-05 04:29:21
|
pupa.exceptions.ScrapeError: no objects returned from SaanichPersonScraper scrape
Traceback (most recent call last):
File "/app/reports/utils.py", line 71, in scrape_people
report.report = subcommand.handle(args, other)
File "/app/.heroku/src/pupa/pupa/cli/commands/update.py", line 260, in handle
return self.do_handle(args, other, juris)
File "/app/.heroku/src/pupa/pupa/cli/commands/update.py", line 305, in do_handle
report['scrape'] = self.do_scrape(juris, args, scrapers)
File "/app/.heroku/src/pupa/pupa/cli/commands/update.py", line 173, in do_scrape
report[scraper_name] = scraper.do_scrape(**scrape_args)
File "/app/.heroku/src/pupa/pupa/scrape/base.py", line 108, in do_scrape
raise ScrapeError('no objects returned from {} scrape'.format(self.__class__.__name__))
pupa.exceptions.ScrapeError: no objects returned from SaanichPersonScraper scrape
|
|
C
|
ca_bc_surrey
|
2020-07-05 04:20:57
|
2020-07-05 04:20:57
|
|
|
C
|
ca_bc_vancouver
|
2020-07-05 04:24:26
|
2020-07-05 04:24:26
|
|
|
D>
|
ca_bc_victoria
|
2020-04-28 04:01:47
|
2020-07-05 04:28:35
|
KeyError: 'primary role'
Traceback (most recent call last):
File "/app/reports/utils.py", line 71, in scrape_people
report.report = subcommand.handle(args, other)
File "/app/.heroku/src/pupa/pupa/cli/commands/update.py", line 260, in handle
return self.do_handle(args, other, juris)
File "/app/.heroku/src/pupa/pupa/cli/commands/update.py", line 305, in do_handle
report['scrape'] = self.do_scrape(juris, args, scrapers)
File "/app/.heroku/src/pupa/pupa/cli/commands/update.py", line 173, in do_scrape
report[scraper_name] = scraper.do_scrape(**scrape_args)
File "/app/.heroku/src/pupa/pupa/scrape/base.py", line 99, in do_scrape
for obj in self.scrape(**kwargs) or []:
File "/app/scrapers/utils.py", line 394, in scrape
role = row['primary role']
KeyError: 'primary role'
|
|
C
|
ca_candidates
|
2020-07-05 04:24:17
|
2020-07-05 04:24:18
|
|
|
C
|
ca_mb
|
2020-07-05 04:20:48
|
2020-07-05 04:20:48
|
|
D>
04:46:19 WARNING pupa: could not save RunPlan, no successful runs of ocd-jurisdiction/country:ca/province:mb/executive yet
|
ca_mb_candidates
|
|
2020-07-05 04:46:19
|
obj2 sources: []
Traceback (most recent call last):
File "/app/reports/utils.py", line 71, in scrape_people
report.report = subcommand.handle(args, other)
File "/app/.heroku/src/pupa/pupa/cli/commands/update.py", line 260, in handle
return self.do_handle(args, other, juris)
File "/app/.heroku/src/pupa/pupa/cli/commands/update.py", line 307, in do_handle
report['import'] = self.do_import(juris, args)
File "/app/.heroku/src/pupa/pupa/cli/commands/update.py", line 211, in do_import
report.update(membership_importer.import_directory(datadir))
File "/app/.heroku/src/pupa/pupa/importers/base.py", line 190, in import_directory
return self.import_data(json_stream())
File "/app/.heroku/src/pupa/pupa/importers/base.py", line 227, in import_data
obj_id, what = self.import_item(data)
File "/app/.heroku/src/pupa/pupa/importers/base.py", line 265, in import_item
raise DuplicateItemError(data, obj, related.get('sources', []))
pupa.exceptions.DuplicateItemError: attempt to import data that would conflict with data already in the import: {'label': '', 'role': 'member', 'person_id': 'ocd-person/fc19ee4a-e7ac-49b9-93b3-80765b32b621', 'person_name': 'Roger Schellenberg', 'organization_id': 'ocd-organization/67542c34-abf0-433c-b234-f7bc4bbe46a4', 'post_id': None, 'on_behalf_of_id': None, 'start_date': '', 'end_date': '', 'extras': {}} (already imported as Roger Schellenberg in Green Party (member))
obj1 sources: []
obj2 sources: []
|
|
C
|
ca_mb_winnipeg
|
2020-07-05 04:31:46
|
2020-07-05 04:31:46
|
|
|
D>
|
ca_municipalities
|
|
2020-07-05 04:47:32
|
pupa.exceptions.SameNameError: multiple people with same name "Luc Desjardins" in Jurisdiction - must provide birth_date to …
Traceback (most recent call last):
File "/app/reports/utils.py", line 71, in scrape_people
report.report = subcommand.handle(args, other)
File "/app/.heroku/src/pupa/pupa/cli/commands/update.py", line 260, in handle
return self.do_handle(args, other, juris)
File "/app/.heroku/src/pupa/pupa/cli/commands/update.py", line 307, in do_handle
report['import'] = self.do_import(juris, args)
File "/app/.heroku/src/pupa/pupa/cli/commands/update.py", line 207, in do_import
report.update(person_importer.import_directory(datadir))
File "/app/.heroku/src/pupa/pupa/importers/base.py", line 190, in import_directory
return self.import_data(json_stream())
File "/app/.heroku/src/pupa/pupa/importers/base.py", line 226, in import_data
for json_id, data in self._prepare_imports(data_items):
File "/app/.heroku/src/pupa/pupa/importers/people.py", line 33, in _prepare_imports
raise SameNameError(name)
pupa.exceptions.SameNameError: multiple people with same name "Luc Desjardins" in Jurisdiction - must provide birth_date to disambiguate
|
|
C
|
ca_nb
|
2020-07-05 04:30:16
|
2020-07-05 04:30:16
|
|
|
C
|
ca_nb_fredericton
|
2020-07-05 04:31:04
|
2020-07-05 04:31:04
|
|
D>
05:59:38 WARNING pupa: validation of CanadianPerson b61554ce-be84-11ea-b1b1-ca1a4e1784d8 failed: 1 validation errors:
Value 'Paulette Th�riault' for field '<obj>.name' does not match regular expression 'regex.Regex('\\A(?!(?:Chair|Commissioner|Conseiller|Councillor|Deputy|Dr|Hon|M|Maire|Mayor|Miss|Mme|Mr|Mrs|Ms|Regional|Warden)\\b)(?:(?:(?:\\p{Lu}\\.)+|\\p{Lu}+|(?:Jr|Rev|Sr|St)\\.|da|de|den|der|la|van|von|[("](?:\\p{Lu}+|\\p{Lu}\\p{Ll}*(?:-\\p{Lu}\\p{Ll}*)*)[)"]|(?:D\'|d\'|De|de|Des|Di|Du|L\'|La|Le|Mac|Mc|O\'|San|Van|Vander?|vanden)?\\p{Lu}\\p{Ll}+|\\p{Lu}\\p{Ll}+Anne?|Marie\\p{Lu}\\p{Ll}+|Ch\'ng|Prud\'homme|D!ONNE|IsaBelle)(?:\'|-| - | ))+(?:(?:\\p{Lu}\\.)+|\\p{Lu}+|(?:Jr|Rev|Sr|St)\\.|da|de|den|der|la|van|von|[("](?:\\p{Lu}+|\\p{Lu}\\p{Ll}*(?:-\\p{Lu}\\p{Ll}*)*)[)"]|(?:D\'|d\'|De|de|Des|Di|Du|L\'|La|Le|Mac|Mc|O\'|San|Van|Vander?|vanden)?\\p{Lu}\\p{Ll}+|\\p{Lu}\\p{Ll}+Anne?|Marie\\p{Lu}\\p{Ll}+|Ch\'ng|Prud\'homme|D!ONNE|IsaBelle)\\Z', flags=regex.V0)'
|
ca_nb_moncton
|
2020-04-28 04:17:29
|
2020-07-05 05:59:38
|
Value 'Paulette Th�riault' for field '<obj>.name' does not match regular expression 'regex.Regex('\\A(?!(?:Chair|Commissio…
Traceback (most recent call last):
File "/app/.heroku/src/pupa/pupa/scrape/base.py", line 175, in validate
validator.validate(self.as_dict(), schema)
File "/app/.heroku/python/lib/python3.6/site-packages/validictory/validator.py", line 620, in validate
raise MultipleValidationError(self._errors)
validictory.validator.MultipleValidationError: 1 validation errors:
Value 'Paulette Th�riault' for field '<obj>.name' does not match regular expression 'regex.Regex('\\A(?!(?:Chair|Commissioner|Conseiller|Councillor|Deputy|Dr|Hon|M|Maire|Mayor|Miss|Mme|Mr|Mrs|Ms|Regional|Warden)\\b)(?:(?:(?:\\p{Lu}\\.)+|\\p{Lu}+|(?:Jr|Rev|Sr|St)\\.|da|de|den|der|la|van|von|[("](?:\\p{Lu}+|\\p{Lu}\\p{Ll}*(?:-\\p{Lu}\\p{Ll}*)*)[)"]|(?:D\'|d\'|De|de|Des|Di|Du|L\'|La|Le|Mac|Mc|O\'|San|Van|Vander?|vanden)?\\p{Lu}\\p{Ll}+|\\p{Lu}\\p{Ll}+Anne?|Marie\\p{Lu}\\p{Ll}+|Ch\'ng|Prud\'homme|D!ONNE|IsaBelle)(?:\'|-| - | ))+(?:(?:\\p{Lu}\\.)+|\\p{Lu}+|(?:Jr|Rev|Sr|St)\\.|da|de|den|der|la|van|von|[("](?:\\p{Lu}+|\\p{Lu}\\p{Ll}*(?:-\\p{Lu}\\p{Ll}*)*)[)"]|(?:D\'|d\'|De|de|Des|Di|Du|L\'|La|Le|Mac|Mc|O\'|San|Van|Vander?|vanden)?\\p{Lu}\\p{Ll}+|\\p{Lu}\\p{Ll}+Anne?|Marie\\p{Lu}\\p{Ll}+|Ch\'ng|Prud\'homme|D!ONNE|IsaBelle)\\Z', flags=regex.V0)'
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "/app/reports/utils.py", line 71, in scrape_people
report.report = subcommand.handle(args, other)
File "/app/.heroku/src/pupa/pupa/cli/commands/update.py", line 260, in handle
return self.do_handle(args, other, juris)
File "/app/.heroku/src/pupa/pupa/cli/commands/update.py", line 305, in do_handle
report['scrape'] = self.do_scrape(juris, args, scrapers)
File "/app/.heroku/src/pupa/pupa/cli/commands/update.py", line 173, in do_scrape
report[scraper_name] = scraper.do_scrape(**scrape_args)
File "/app/.heroku/src/pupa/pupa/scrape/base.py", line 104, in do_scrape
self.save_object(obj)
File "/app/.heroku/src/pupa/pupa/scrape/base.py", line 89, in save_object
raise ve
File "/app/.heroku/src/pupa/pupa/scrape/base.py", line 85, in save_object
obj.validate()
File "/app/.heroku/src/pupa/pupa/scrape/base.py", line 178, in validate
self.__class__.__name__, self._id, ve)
pupa.exceptions.ScrapeValueError: validation of CanadianPerson b61554ce-be84-11ea-b1b1-ca1a4e1784d8 failed: 1 validation errors:
Value 'Paulette Th�riault' for field '<obj>.name' does not match regular expression 'regex.Regex('\\A(?!(?:Chair|Commissioner|Conseiller|Councillor|Deputy|Dr|Hon|M|Maire|Mayor|Miss|Mme|Mr|Mrs|Ms|Regional|Warden)\\b)(?:(?:(?:\\p{Lu}\\.)+|\\p{Lu}+|(?:Jr|Rev|Sr|St)\\.|da|de|den|der|la|van|von|[("](?:\\p{Lu}+|\\p{Lu}\\p{Ll}*(?:-\\p{Lu}\\p{Ll}*)*)[)"]|(?:D\'|d\'|De|de|Des|Di|Du|L\'|La|Le|Mac|Mc|O\'|San|Van|Vander?|vanden)?\\p{Lu}\\p{Ll}+|\\p{Lu}\\p{Ll}+Anne?|Marie\\p{Lu}\\p{Ll}+|Ch\'ng|Prud\'homme|D!ONNE|IsaBelle)(?:\'|-| - | ))+(?:(?:\\p{Lu}\\.)+|\\p{Lu}+|(?:Jr|Rev|Sr|St)\\.|da|de|den|der|la|van|von|[("](?:\\p{Lu}+|\\p{Lu}\\p{Ll}*(?:-\\p{Lu}\\p{Ll}*)*)[)"]|(?:D\'|d\'|De|de|Des|Di|Du|L\'|La|Le|Mac|Mc|O\'|San|Van|Vander?|vanden)?\\p{Lu}\\p{Ll}+|\\p{Lu}\\p{Ll}+Anne?|Marie\\p{Lu}\\p{Ll}+|Ch\'ng|Prud\'homme|D!ONNE|IsaBelle)\\Z', flags=regex.V0)'
|
|
C
|
ca_nb_municipalities
|
2020-07-05 04:18:24
|
2020-07-05 04:18:25
|
|
|
C
|
ca_nb_saint_john
|
2020-07-05 04:38:09
|
2020-07-05 04:38:09
|
|
|
D>
|
ca_nl
|
2020-07-05 04:29:20
|
2020-07-05 05:58:33
|
SystemExit: 1
Traceback (most recent call last):
File "/app/.heroku/python/lib/python3.6/site-packages/urllib3/connectionpool.py", line 377, in _make_request
httplib_response = conn.getresponse(buffering=True)
TypeError: getresponse() got an unexpected keyword argument 'buffering'
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "/app/.heroku/python/lib/python3.6/site-packages/urllib3/contrib/pyopenssl.py", line 297, in recv_into
return self.connection.recv_into(*args, **kwargs)
File "/app/.heroku/python/lib/python3.6/site-packages/OpenSSL/SSL.py", line 1840, in recv_into
self._raise_ssl_error(self._ssl, result)
File "/app/.heroku/python/lib/python3.6/site-packages/OpenSSL/SSL.py", line 1646, in _raise_ssl_error
raise WantReadError()
OpenSSL.SSL.WantReadError
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "/app/reports/utils.py", line 71, in scrape_people
report.report = subcommand.handle(args, other)
File "/app/.heroku/src/pupa/pupa/cli/commands/update.py", line 260, in handle
return self.do_handle(args, other, juris)
File "/app/.heroku/src/pupa/pupa/cli/commands/update.py", line 305, in do_handle
report['scrape'] = self.do_scrape(juris, args, scrapers)
File "/app/.heroku/src/pupa/pupa/cli/commands/update.py", line 173, in do_scrape
report[scraper_name] = scraper.do_scrape(**scrape_args)
File "/app/.heroku/src/pupa/pupa/scrape/base.py", line 99, in do_scrape
for obj in self.scrape(**kwargs) or []:
File "/app/scrapers/ca_nl/people.py", line 29, in scrape
detail = self.lxmlize(detail_url, user_agent=CUSTOM_USER_AGENT)
File "/app/scrapers/utils.py", line 180, in lxmlize
response = self.get(url, cookies=cookies)
File "/app/scrapers/utils.py", line 172, in get
return super().get(*args, verify=SSL_VERIFY, **kwargs)
File "/app/.heroku/python/lib/python3.6/site-packages/requests/sessions.py", line 537, in get
return self.request('GET', url, **kwargs)
File "/app/.heroku/python/lib/python3.6/site-packages/scrapelib/__init__.py", line 286, in request
**kwargs)
File "/app/.heroku/python/lib/python3.6/site-packages/scrapelib/cache.py", line 66, in request
resp = super(CachingSession, self).request(method, url, **kwargs)
File "/app/.heroku/python/lib/python3.6/site-packages/scrapelib/__init__.py", line 88, in request
return super(ThrottledSession, self).request(method, url, **kwargs)
File "/app/.heroku/python/lib/python3.6/site-packages/scrapelib/__init__.py", line 153, in request
resp = super(RetrySession, self).request(method, url, **kwargs)
File "/app/.heroku/python/lib/python3.6/site-packages/requests/sessions.py", line 524, in request
resp = self.send(prep, **send_kwargs)
File "/app/.heroku/python/lib/python3.6/site-packages/requests/sessions.py", line 659, in send
history = [resp for resp in gen] if allow_redirects else []
File "/app/.heroku/python/lib/python3.6/site-packages/requests/sessions.py", line 659, in <listcomp>
history = [resp for resp in gen] if allow_redirects else []
File "/app/.heroku/python/lib/python3.6/site-packages/requests/sessions.py", line 238, in resolve_redirects
**adapter_kwargs
File "/app/.heroku/python/lib/python3.6/site-packages/requests/sessions.py", line 637, in send
r = adapter.send(request, **kwargs)
File "/app/.heroku/python/lib/python3.6/site-packages/requests/adapters.py", line 449, in send
timeout=timeout
File "/app/.heroku/python/lib/python3.6/site-packages/urllib3/connectionpool.py", line 600, in urlopen
chunked=chunked)
File "/app/.heroku/python/lib/python3.6/site-packages/urllib3/connectionpool.py", line 380, in _make_request
httplib_response = conn.getresponse()
File "/app/.heroku/python/lib/python3.6/http/client.py", line 1354, in getresponse
response.begin()
File "/app/.heroku/python/lib/python3.6/http/client.py", line 307, in begin
version, status, reason = self._read_status()
File "/app/.heroku/python/lib/python3.6/http/client.py", line 268, in _read_status
line = str(self.fp.readline(_MAXLINE + 1), "iso-8859-1")
File "/app/.heroku/python/lib/python3.6/socket.py", line 586, in readinto
return self._sock.recv_into(b)
File "/app/.heroku/python/lib/python3.6/site-packages/urllib3/contrib/pyopenssl.py", line 309, in recv_into
if not util.wait_for_read(self.socket, self.socket.gettimeout()):
File "/app/.heroku/python/lib/python3.6/site-packages/urllib3/util/wait.py", line 143, in wait_for_read
return wait_for_socket(sock, read=True, timeout=timeout)
File "/app/.heroku/python/lib/python3.6/site-packages/urllib3/util/wait.py", line 104, in poll_wait_for_socket
return bool(_retry_on_intr(do_poll, timeout))
File "/app/.heroku/python/lib/python3.6/site-packages/urllib3/util/wait.py", line 42, in _retry_on_intr
return fn(timeout)
File "/app/.heroku/python/lib/python3.6/site-packages/urllib3/util/wait.py", line 102, in do_poll
return poll_obj.poll(t)
File "/app/.heroku/python/lib/python3.6/site-packages/gunicorn/workers/base.py", line 196, in handle_abort
sys.exit(1)
SystemExit: 1
|
|
C
|
ca_nl_st_john_s
|
2020-07-05 04:01:27
|
2020-07-05 04:01:27
|
|
|
C
|
ca_ns
|
2020-07-05 04:44:58
|
2020-07-05 04:44:58
|
|
|
D>
|
ca_ns_cape_breton
|
2020-06-23 04:20:44
|
2020-07-05 04:18:47
|
IndexError: list index out of range
Traceback (most recent call last):
File "/app/reports/utils.py", line 71, in scrape_people
report.report = subcommand.handle(args, other)
File "/app/.heroku/src/pupa/pupa/cli/commands/update.py", line 260, in handle
return self.do_handle(args, other, juris)
File "/app/.heroku/src/pupa/pupa/cli/commands/update.py", line 305, in do_handle
report['scrape'] = self.do_scrape(juris, args, scrapers)
File "/app/.heroku/src/pupa/pupa/cli/commands/update.py", line 173, in do_scrape
report[scraper_name] = scraper.do_scrape(**scrape_args)
File "/app/.heroku/src/pupa/pupa/scrape/base.py", line 99, in do_scrape
for obj in self.scrape(**kwargs) or []:
File "/app/scrapers/ca_ns_cape_breton/people.py", line 26, in scrape
phone = contact_nodes[0].split(':')[1]
IndexError: list index out of range
|
|
C
|
ca_ns_halifax
|
2020-07-05 04:01:47
|
2020-07-05 04:01:47
|
|
|
C
|
ca_on
|
2020-07-05 04:03:57
|
2020-07-05 04:03:57
|
|
|
C
|
ca_on_ajax
|
2020-07-05 04:21:15
|
2020-07-05 04:21:15
|
|
|
C
|
ca_on_belleville
|
2020-07-05 04:21:04
|
2020-07-05 04:21:04
|
|
|
C
|
ca_on_brampton
|
2020-07-05 04:22:02
|
2020-07-05 04:22:02
|
|
|
C
|
ca_on_brantford
|
2020-07-05 04:46:23
|
2020-07-05 04:46:23
|
|
D>
04:24:47 WARNING scrapelib: sleeping for 10 seconds before retry
04:24:57 WARNING scrapelib: sleeping for 20 seconds before retry
04:25:17 WARNING scrapelib: sleeping for 40 seconds before retry
|
ca_on_burlington
|
2020-04-28 04:17:23
|
2020-07-05 04:25:57
|
scrapelib.HTTPError: 500 while retrieving https://opendata.arcgis.com/datasets/f2c404c667904f03be38443cbd474cd3_0.csv
Traceback (most recent call last):
File "/app/reports/utils.py", line 71, in scrape_people
report.report = subcommand.handle(args, other)
File "/app/.heroku/src/pupa/pupa/cli/commands/update.py", line 260, in handle
return self.do_handle(args, other, juris)
File "/app/.heroku/src/pupa/pupa/cli/commands/update.py", line 305, in do_handle
report['scrape'] = self.do_scrape(juris, args, scrapers)
File "/app/.heroku/src/pupa/pupa/cli/commands/update.py", line 173, in do_scrape
report[scraper_name] = scraper.do_scrape(**scrape_args)
File "/app/.heroku/src/pupa/pupa/scrape/base.py", line 99, in do_scrape
for obj in self.scrape(**kwargs) or []:
File "/app/scrapers/utils.py", line 367, in scrape
reader = self.csv_reader(self.csv_url, delimiter=self.delimiter, header=True, encoding=self.encoding, skip_rows=self.skip_rows, data=data)
File "/app/scrapers/utils.py", line 215, in csv_reader
response = self.get(url, **kwargs)
File "/app/scrapers/utils.py", line 172, in get
return super().get(*args, verify=SSL_VERIFY, **kwargs)
File "/app/.heroku/python/lib/python3.6/site-packages/requests/sessions.py", line 537, in get
return self.request('GET', url, **kwargs)
File "/app/.heroku/python/lib/python3.6/site-packages/scrapelib/__init__.py", line 292, in request
raise HTTPError(resp)
scrapelib.HTTPError: 500 while retrieving https://opendata.arcgis.com/datasets/f2c404c667904f03be38443cbd474cd3_0.csv
|
|
D>
|
ca_on_caledon
|
2020-06-04 04:03:31
|
2020-07-05 04:24:29
|
IndexError: list index out of range
Traceback (most recent call last):
File "/app/reports/utils.py", line 71, in scrape_people
report.report = subcommand.handle(args, other)
File "/app/.heroku/src/pupa/pupa/cli/commands/update.py", line 260, in handle
return self.do_handle(args, other, juris)
File "/app/.heroku/src/pupa/pupa/cli/commands/update.py", line 305, in do_handle
report['scrape'] = self.do_scrape(juris, args, scrapers)
File "/app/.heroku/src/pupa/pupa/cli/commands/update.py", line 173, in do_scrape
report[scraper_name] = scraper.do_scrape(**scrape_args)
File "/app/.heroku/src/pupa/pupa/scrape/base.py", line 99, in do_scrape
for obj in self.scrape(**kwargs) or []:
File "/app/scrapers/ca_on_caledon/people.py", line 10, in scrape
node = page.xpath('//td[@rowspan="2"]')[0]
IndexError: list index out of range
|
|
C
|
ca_on_cambridge
|
2020-07-05 04:18:48
|
2020-07-05 04:18:48
|
|
|
C
|
ca_on_chatham_kent
|
2020-07-05 04:31:42
|
2020-07-05 04:31:42
|
|
|
C
|
ca_on_fort_erie
|
2020-07-05 04:30:19
|
2020-07-05 04:30:19
|
|
|
C
|
ca_on_georgina
|
2020-07-05 04:37:48
|
2020-07-05 04:37:48
|
|
|
C
|
ca_on_greater_sudbury
|
2020-07-05 04:31:17
|
2020-07-05 04:31:17
|
|
|
C
|
ca_on_grimsby
|
2020-07-05 04:20:59
|
2020-07-05 04:20:59
|
|
|
C
|
ca_on_guelph
|
2020-07-05 04:45:03
|
2020-07-05 04:45:03
|
|
D>
04:24:20 WARNING pupa: could not save RunPlan, no successful runs of ocd-jurisdiction/country:ca/csd:3528018/legislature yet
|
ca_on_haldimand_county
|
|
2020-07-05 04:24:20
|
AssertionError: No councillors found
Traceback (most recent call last):
File "/app/reports/utils.py", line 71, in scrape_people
report.report = subcommand.handle(args, other)
File "/app/.heroku/src/pupa/pupa/cli/commands/update.py", line 260, in handle
return self.do_handle(args, other, juris)
File "/app/.heroku/src/pupa/pupa/cli/commands/update.py", line 305, in do_handle
report['scrape'] = self.do_scrape(juris, args, scrapers)
File "/app/.heroku/src/pupa/pupa/cli/commands/update.py", line 173, in do_scrape
report[scraper_name] = scraper.do_scrape(**scrape_args)
File "/app/.heroku/src/pupa/pupa/scrape/base.py", line 99, in do_scrape
for obj in self.scrape(**kwargs) or []:
File "/app/scrapers/ca_on_haldimand_county/people.py", line 13, in scrape
assert len(councillors), 'No councillors found'
AssertionError: No councillors found
|
D>
04:21:02 WARNING pupa: could not save RunPlan, no successful runs of ocd-jurisdiction/country:ca/csd:3525005/legislature yet
|
ca_on_hamilton
|
|
2020-07-05 04:21:02
|
Exception: No email pattern in ["javascript:void(location.href='mailto:'+String.fromCharCode(109,97,121,111,114,64,104,97,10…
Traceback (most recent call last):
File "/app/reports/utils.py", line 71, in scrape_people
report.report = subcommand.handle(args, other)
File "/app/.heroku/src/pupa/pupa/cli/commands/update.py", line 260, in handle
return self.do_handle(args, other, juris)
File "/app/.heroku/src/pupa/pupa/cli/commands/update.py", line 305, in do_handle
report['scrape'] = self.do_scrape(juris, args, scrapers)
File "/app/.heroku/src/pupa/pupa/cli/commands/update.py", line 173, in do_scrape
report[scraper_name] = scraper.do_scrape(**scrape_args)
File "/app/.heroku/src/pupa/pupa/scrape/base.py", line 99, in do_scrape
for obj in self.scrape(**kwargs) or []:
File "/app/scrapers/ca_on_hamilton/people.py", line 11, in scrape
yield self.mayor_data(mayor_url)
File "/app/scrapers/ca_on_hamilton/people.py", line 47, in mayor_data
email = self.get_email(info_node)
File "/app/scrapers/utils.py", line 135, in get_email
raise Exception('No email pattern in {}'.format(matches))
Exception: No email pattern in ["javascript:void(location.href='mailto:'+String.fromCharCode(109,97,121,111,114,64,104,97,109,105,108,116,111,110,46,99,97))"]
|
D>
04:01:22 WARNING pupa: could not save RunPlan, no successful runs of ocd-jurisdiction/country:ca/cd:3540/legislature yet
|
ca_on_huron
|
|
2020-07-05 04:01:22
|
pupa.exceptions.UnresolvedIdError: cannot resolve pseudo id to Post: ~{"label": "Huron (seat 14)", "organization__classifica…
Traceback (most recent call last):
File "/app/reports/utils.py", line 71, in scrape_people
report.report = subcommand.handle(args, other)
File "/app/.heroku/src/pupa/pupa/cli/commands/update.py", line 260, in handle
return self.do_handle(args, other, juris)
File "/app/.heroku/src/pupa/pupa/cli/commands/update.py", line 307, in do_handle
report['import'] = self.do_import(juris, args)
File "/app/.heroku/src/pupa/pupa/cli/commands/update.py", line 211, in do_import
report.update(membership_importer.import_directory(datadir))
File "/app/.heroku/src/pupa/pupa/importers/base.py", line 190, in import_directory
return self.import_data(json_stream())
File "/app/.heroku/src/pupa/pupa/importers/base.py", line 227, in import_data
obj_id, what = self.import_item(data)
File "/app/.heroku/src/pupa/pupa/importers/base.py", line 247, in import_item
data = self.prepare_for_db(data)
File "/app/.heroku/src/pupa/pupa/importers/memberships.py", line 50, in prepare_for_db
data['post_id'] = self.post_importer.resolve_json_id(data['post_id'])
File "/app/.heroku/src/pupa/pupa/importers/base.py", line 165, in resolve_json_id
raise UnresolvedIdError(errmsg)
pupa.exceptions.UnresolvedIdError: cannot resolve pseudo id to Post: ~{"label": "Huron (seat 14)", "organization__classification": "legislature", "role": "Councillor"}
|
|
C
|
ca_on_king
|
2020-07-05 04:18:29
|
2020-07-05 04:18:29
|
|
|
C
|
ca_on_kingston
|
2020-07-05 04:21:21
|
2020-07-05 04:21:22
|
|
|
C
|
ca_on_kitchener
|
2020-07-05 04:30:18
|
2020-07-05 04:30:18
|
|
|
C
|
ca_on_lambton
|
2020-07-05 04:21:35
|
2020-07-05 04:21:35
|
|
|
C
|
ca_on_lincoln
|
2020-07-05 04:24:28
|
2020-07-05 04:24:28
|
|
|
C
|
ca_on_london
|
2020-07-05 04:21:11
|
2020-07-05 04:21:11
|
|
D>
04:00:54 WARNING pupa: could not save RunPlan, no successful runs of ocd-jurisdiction/country:ca/csd:3519036/legislature yet
|
ca_on_markham
|
|
2020-07-05 04:00:54
|
IndexError: list index out of range
Traceback (most recent call last):
File "/app/reports/utils.py", line 71, in scrape_people
report.report = subcommand.handle(args, other)
File "/app/.heroku/src/pupa/pupa/cli/commands/update.py", line 260, in handle
return self.do_handle(args, other, juris)
File "/app/.heroku/src/pupa/pupa/cli/commands/update.py", line 305, in do_handle
report['scrape'] = self.do_scrape(juris, args, scrapers)
File "/app/.heroku/src/pupa/pupa/cli/commands/update.py", line 173, in do_scrape
report[scraper_name] = scraper.do_scrape(**scrape_args)
File "/app/.heroku/src/pupa/pupa/scrape/base.py", line 99, in do_scrape
for obj in self.scrape(**kwargs) or []:
File "/app/scrapers/ca_on_markham/people.py", line 12, in scrape
mayor_url = page.xpath('//a[contains(text(), "Office of the Mayor")]/@href')[0]
IndexError: list index out of range
|
D>
04:24:34 WARNING pupa: could not save RunPlan, no successful runs of ocd-jurisdiction/country:ca/csd:3524009/legislature yet
|
ca_on_milton
|
|
2020-07-05 04:24:34
|
AssertionError: No councillors found
Traceback (most recent call last):
File "/app/reports/utils.py", line 71, in scrape_people
report.report = subcommand.handle(args, other)
File "/app/.heroku/src/pupa/pupa/cli/commands/update.py", line 260, in handle
return self.do_handle(args, other, juris)
File "/app/.heroku/src/pupa/pupa/cli/commands/update.py", line 305, in do_handle
report['scrape'] = self.do_scrape(juris, args, scrapers)
File "/app/.heroku/src/pupa/pupa/cli/commands/update.py", line 173, in do_scrape
report[scraper_name] = scraper.do_scrape(**scrape_args)
File "/app/.heroku/src/pupa/pupa/scrape/base.py", line 99, in do_scrape
for obj in self.scrape(**kwargs) or []:
File "/app/scrapers/ca_on_milton/people.py", line 13, in scrape
assert len(councillors), 'No councillors found'
AssertionError: No councillors found
|
|
C
|
ca_on_mississauga
|
2020-07-05 04:01:09
|
2020-07-05 04:01:09
|
|
|
C
|
ca_on_newmarket
|
2020-07-05 04:28:37
|
2020-07-05 04:28:37
|
|
|
C
|
ca_on_niagara
|
2020-07-05 04:29:25
|
2020-07-05 04:29:25
|
|
|
C
|
ca_on_niagara_on_the_lake
|
2020-07-05 04:45:01
|
2020-07-05 04:45:01
|
|
|
C
|
ca_on_north_dumfries
|
2020-07-05 04:22:08
|
2020-07-05 04:22:08
|
|
D>
04:29:22 WARNING pupa: validation of CanadianPerson 19c567c8-be78-11ea-92f7-3ec7af0fe542 failed: 1 validation errors:
Value 'Sean Oâ\x80\x99Meara' for field '<obj>.name' does not match regular expression 'regex.Regex('\\A(?!(?:Chair|Commissioner|Conseiller|Councillor|Deputy|Dr|Hon|M|Maire|Mayor|Miss|Mme|Mr|Mrs|Ms|Regional|Warden)\\b)(?:(?:(?:\\p{Lu}\\.)+|\\p{Lu}+|(?:Jr|Rev|Sr|St)\\.|da|de|den|der|la|van|von|[("](?:\\p{Lu}+|\\p{Lu}\\p{Ll}*(?:-\\p{Lu}\\p{Ll}*)*)[)"]|(?:D\'|d\'|De|de|Des|Di|Du|L\'|La|Le|Mac|Mc|O\'|San|Van|Vander?|vanden)?\\p{Lu}\\p{Ll}+|\\p{Lu}\\p{Ll}+Anne?|Marie\\p{Lu}\\p{Ll}+|Ch\'ng|Prud\'homme|D!ONNE|IsaBelle)(?:\'|-| - | ))+(?:(?:\\p{Lu}\\.)+|\\p{Lu}+|(?:Jr|Rev|Sr|St)\\.|da|de|den|der|la|van|von|[("](?:\\p{Lu}+|\\p{Lu}\\p{Ll}*(?:-\\p{Lu}\\p{Ll}*)*)[)"]|(?:D\'|d\'|De|de|Des|Di|Du|L\'|La|Le|Mac|Mc|O\'|San|Van|Vander?|vanden)?\\p{Lu}\\p{Ll}+|\\p{Lu}\\p{Ll}+Anne?|Marie\\p{Lu}\\p{Ll}+|Ch\'ng|Prud\'homme|D!ONNE|IsaBelle)\\Z', flags=regex.V0)'
|
ca_on_oakville
|
2020-04-28 04:21:24
|
2020-07-05 04:29:22
|
Value 'Sean Oâ\x80\x99Meara' for field '<obj>.name' does not match regular expression 'regex.Regex('\\A(?!(?:Chair|Commissio…
Traceback (most recent call last):
File "/app/.heroku/src/pupa/pupa/scrape/base.py", line 175, in validate
validator.validate(self.as_dict(), schema)
File "/app/.heroku/python/lib/python3.6/site-packages/validictory/validator.py", line 620, in validate
raise MultipleValidationError(self._errors)
validictory.validator.MultipleValidationError: 1 validation errors:
Value 'Sean Oâ\x80\x99Meara' for field '<obj>.name' does not match regular expression 'regex.Regex('\\A(?!(?:Chair|Commissioner|Conseiller|Councillor|Deputy|Dr|Hon|M|Maire|Mayor|Miss|Mme|Mr|Mrs|Ms|Regional|Warden)\\b)(?:(?:(?:\\p{Lu}\\.)+|\\p{Lu}+|(?:Jr|Rev|Sr|St)\\.|da|de|den|der|la|van|von|[("](?:\\p{Lu}+|\\p{Lu}\\p{Ll}*(?:-\\p{Lu}\\p{Ll}*)*)[)"]|(?:D\'|d\'|De|de|Des|Di|Du|L\'|La|Le|Mac|Mc|O\'|San|Van|Vander?|vanden)?\\p{Lu}\\p{Ll}+|\\p{Lu}\\p{Ll}+Anne?|Marie\\p{Lu}\\p{Ll}+|Ch\'ng|Prud\'homme|D!ONNE|IsaBelle)(?:\'|-| - | ))+(?:(?:\\p{Lu}\\.)+|\\p{Lu}+|(?:Jr|Rev|Sr|St)\\.|da|de|den|der|la|van|von|[("](?:\\p{Lu}+|\\p{Lu}\\p{Ll}*(?:-\\p{Lu}\\p{Ll}*)*)[)"]|(?:D\'|d\'|De|de|Des|Di|Du|L\'|La|Le|Mac|Mc|O\'|San|Van|Vander?|vanden)?\\p{Lu}\\p{Ll}+|\\p{Lu}\\p{Ll}+Anne?|Marie\\p{Lu}\\p{Ll}+|Ch\'ng|Prud\'homme|D!ONNE|IsaBelle)\\Z', flags=regex.V0)'
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "/app/reports/utils.py", line 71, in scrape_people
report.report = subcommand.handle(args, other)
File "/app/.heroku/src/pupa/pupa/cli/commands/update.py", line 260, in handle
return self.do_handle(args, other, juris)
File "/app/.heroku/src/pupa/pupa/cli/commands/update.py", line 305, in do_handle
report['scrape'] = self.do_scrape(juris, args, scrapers)
File "/app/.heroku/src/pupa/pupa/cli/commands/update.py", line 173, in do_scrape
report[scraper_name] = scraper.do_scrape(**scrape_args)
File "/app/.heroku/src/pupa/pupa/scrape/base.py", line 104, in do_scrape
self.save_object(obj)
File "/app/.heroku/src/pupa/pupa/scrape/base.py", line 89, in save_object
raise ve
File "/app/.heroku/src/pupa/pupa/scrape/base.py", line 85, in save_object
obj.validate()
File "/app/.heroku/src/pupa/pupa/scrape/base.py", line 178, in validate
self.__class__.__name__, self._id, ve)
pupa.exceptions.ScrapeValueError: validation of CanadianPerson 19c567c8-be78-11ea-92f7-3ec7af0fe542 failed: 1 validation errors:
Value 'Sean Oâ\x80\x99Meara' for field '<obj>.name' does not match regular expression 'regex.Regex('\\A(?!(?:Chair|Commissioner|Conseiller|Councillor|Deputy|Dr|Hon|M|Maire|Mayor|Miss|Mme|Mr|Mrs|Ms|Regional|Warden)\\b)(?:(?:(?:\\p{Lu}\\.)+|\\p{Lu}+|(?:Jr|Rev|Sr|St)\\.|da|de|den|der|la|van|von|[("](?:\\p{Lu}+|\\p{Lu}\\p{Ll}*(?:-\\p{Lu}\\p{Ll}*)*)[)"]|(?:D\'|d\'|De|de|Des|Di|Du|L\'|La|Le|Mac|Mc|O\'|San|Van|Vander?|vanden)?\\p{Lu}\\p{Ll}+|\\p{Lu}\\p{Ll}+Anne?|Marie\\p{Lu}\\p{Ll}+|Ch\'ng|Prud\'homme|D!ONNE|IsaBelle)(?:\'|-| - | ))+(?:(?:\\p{Lu}\\.)+|\\p{Lu}+|(?:Jr|Rev|Sr|St)\\.|da|de|den|der|la|van|von|[("](?:\\p{Lu}+|\\p{Lu}\\p{Ll}*(?:-\\p{Lu}\\p{Ll}*)*)[)"]|(?:D\'|d\'|De|de|Des|Di|Du|L\'|La|Le|Mac|Mc|O\'|San|Van|Vander?|vanden)?\\p{Lu}\\p{Ll}+|\\p{Lu}\\p{Ll}+Anne?|Marie\\p{Lu}\\p{Ll}+|Ch\'ng|Prud\'homme|D!ONNE|IsaBelle)\\Z', flags=regex.V0)'
|
D>
04:46:22 WARNING pupa: could not save RunPlan, no successful runs of ocd-jurisdiction/country:ca/csd:3518013/legislature yet
|
ca_on_oshawa
|
|
2020-07-05 04:46:22
|
Exception: No email node in b'<td>\n<p class="DirectoryTitle">City of Oshawa<br/>Mayor<br/>Dan Carter</p>\n<p class="Standar…
Traceback (most recent call last):
File "/app/reports/utils.py", line 71, in scrape_people
report.report = subcommand.handle(args, other)
File "/app/.heroku/src/pupa/pupa/cli/commands/update.py", line 260, in handle
return self.do_handle(args, other, juris)
File "/app/.heroku/src/pupa/pupa/cli/commands/update.py", line 305, in do_handle
report['scrape'] = self.do_scrape(juris, args, scrapers)
File "/app/.heroku/src/pupa/pupa/cli/commands/update.py", line 173, in do_scrape
report[scraper_name] = scraper.do_scrape(**scrape_args)
File "/app/.heroku/src/pupa/pupa/scrape/base.py", line 99, in do_scrape
for obj in self.scrape(**kwargs) or []:
File "/app/scrapers/ca_on_oshawa/people.py", line 30, in scrape
p.add_contact('email', self.get_email(councillor))
File "/app/scrapers/utils.py", line 137, in get_email
raise Exception('No email node in {}'.format(etree.tostring(node)))
Exception: No email node in b'<td>\n<p class="DirectoryTitle">City of Oshawa<br/>Mayor<br/>Dan Carter</p>\n<p class="Standard DirectoryImage"><img title="Mayor Dan Carter" src="https://www.oshawa.ca/city-hall/resources/Councillor-Photos-2018-2022/Mayor-Carter.jpg" alt="Mayor Dan Carter" width="600" height="841"/></p>\n<p class="Standard">Phone: 905-436-5611</p>\n<ul>\n<li class="Standard"><a title="Email City of Oshawa Mayor, Dan Carter" href="https://www.oshawa.ca/cdn-cgi/l/email-protection#2f424e56405d6f405c474e584e014c4e">Email the Mayor</a></li>\n<li class="Standard"><a title="View Mayor Dan Carter\'s biography." href="https://www.oshawa.ca/city-hall/mayor-carter.asp">Biography</a></li>\n</ul>\n</td>\n'
|
D>
04:21:37 WARNING pupa: could not save RunPlan, no successful runs of ocd-jurisdiction/country:ca/csd:3506008/legislature yet
|
ca_on_ottawa
|
|
2020-07-05 04:21:37
|
KeyError: 'name'
Traceback (most recent call last):
File "/app/reports/utils.py", line 71, in scrape_people
report.report = subcommand.handle(args, other)
File "/app/.heroku/src/pupa/pupa/cli/commands/update.py", line 260, in handle
return self.do_handle(args, other, juris)
File "/app/.heroku/src/pupa/pupa/cli/commands/update.py", line 305, in do_handle
report['scrape'] = self.do_scrape(juris, args, scrapers)
File "/app/.heroku/src/pupa/pupa/cli/commands/update.py", line 173, in do_scrape
report[scraper_name] = scraper.do_scrape(**scrape_args)
File "/app/.heroku/src/pupa/pupa/scrape/base.py", line 99, in do_scrape
for obj in self.scrape(**kwargs) or []:
File "/app/scrapers/utils.py", line 375, in scrape
if not self.is_valid_row(row):
File "/app/scrapers/utils.py", line 336, in is_valid_row
return row['name'] not in empty
KeyError: 'name'
|
|
D>
|
ca_on_peel
|
2020-06-12 04:05:28
|
2020-07-05 04:01:28
|
scrapelib.HTTPError: 404 while retrieving https://data.peelregion.ca/media/43505/wards1822_csv.csv
Traceback (most recent call last):
File "/app/reports/utils.py", line 71, in scrape_people
report.report = subcommand.handle(args, other)
File "/app/.heroku/src/pupa/pupa/cli/commands/update.py", line 260, in handle
return self.do_handle(args, other, juris)
File "/app/.heroku/src/pupa/pupa/cli/commands/update.py", line 305, in do_handle
report['scrape'] = self.do_scrape(juris, args, scrapers)
File "/app/.heroku/src/pupa/pupa/cli/commands/update.py", line 173, in do_scrape
report[scraper_name] = scraper.do_scrape(**scrape_args)
File "/app/.heroku/src/pupa/pupa/scrape/base.py", line 99, in do_scrape
for obj in self.scrape(**kwargs) or []:
File "/app/scrapers/utils.py", line 367, in scrape
reader = self.csv_reader(self.csv_url, delimiter=self.delimiter, header=True, encoding=self.encoding, skip_rows=self.skip_rows, data=data)
File "/app/scrapers/utils.py", line 215, in csv_reader
response = self.get(url, **kwargs)
File "/app/scrapers/utils.py", line 172, in get
return super().get(*args, verify=SSL_VERIFY, **kwargs)
File "/app/.heroku/python/lib/python3.6/site-packages/requests/sessions.py", line 537, in get
return self.request('GET', url, **kwargs)
File "/app/.heroku/python/lib/python3.6/site-packages/scrapelib/__init__.py", line 292, in request
raise HTTPError(resp)
scrapelib.HTTPError: 404 while retrieving https://data.peelregion.ca/media/43505/wards1822_csv.csv
|
|
C
|
ca_on_pickering
|
2020-07-05 04:31:44
|
2020-07-05 04:31:44
|
|
|
C
|
ca_on_richmond_hill
|
2020-07-05 04:01:19
|
2020-07-05 04:01:19
|
|
|
C
|
ca_on_school_boards_english_public
|
2020-07-05 04:19:20
|
2020-07-05 04:19:20
|
|
|
C
|
ca_on_st_catharines
|
2020-07-05 04:28:36
|
2020-07-05 04:28:36
|
|
D>
04:45:01 WARNING pupa: could not save RunPlan, no successful runs of ocd-jurisdiction/country:ca/csd:3558004/legislature yet
|
ca_on_thunder_bay
|
|
2020-07-05 04:45:01
|
scrapelib.HTTPError: 404 while retrieving https://www.thunderbay.ca/Common/PageNotFound.aspx?aspxerrorpath=/en/city-hall/may…
Traceback (most recent call last):
File "/app/reports/utils.py", line 71, in scrape_people
report.report = subcommand.handle(args, other)
File "/app/.heroku/src/pupa/pupa/cli/commands/update.py", line 260, in handle
return self.do_handle(args, other, juris)
File "/app/.heroku/src/pupa/pupa/cli/commands/update.py", line 305, in do_handle
report['scrape'] = self.do_scrape(juris, args, scrapers)
File "/app/.heroku/src/pupa/pupa/cli/commands/update.py", line 173, in do_scrape
report[scraper_name] = scraper.do_scrape(**scrape_args)
File "/app/.heroku/src/pupa/pupa/scrape/base.py", line 99, in do_scrape
for obj in self.scrape(**kwargs) or []:
File "/app/scrapers/ca_on_thunder_bay/people.py", line 9, in scrape
page = self.lxmlize(COUNCIL_PAGE)
File "/app/scrapers/utils.py", line 180, in lxmlize
response = self.get(url, cookies=cookies)
File "/app/scrapers/utils.py", line 172, in get
return super().get(*args, verify=SSL_VERIFY, **kwargs)
File "/app/.heroku/python/lib/python3.6/site-packages/requests/sessions.py", line 537, in get
return self.request('GET', url, **kwargs)
File "/app/.heroku/python/lib/python3.6/site-packages/scrapelib/__init__.py", line 292, in request
raise HTTPError(resp)
scrapelib.HTTPError: 404 while retrieving https://www.thunderbay.ca/Common/PageNotFound.aspx?aspxerrorpath=/en/city-hall/mayor-and-council.aspx
|
|
D>
|
ca_on_toronto
|
|
2020-07-05 04:21:32
|
ModuleNotFoundError: No module named 'ca_on_toronto.constants'
Traceback (most recent call last):
File "/app/reports/utils.py", line 66, in scrape_people
flush(module_name)
File "/app/reports/utils.py", line 84, in flush
jurisdiction_id = module_name_to_metadata(module_name)['jurisdiction_id']
File "/app/reports/utils.py", line 133, in module_name_to_metadata
module = importlib.import_module(module_name)
File "/app/.heroku/python/lib/python3.6/importlib/__init__.py", line 126, in import_module
return _bootstrap._gcd_import(name[level:], package, level)
File "<frozen importlib._bootstrap>", line 994, in _gcd_import
File "<frozen importlib._bootstrap>", line 971, in _find_and_load
File "<frozen importlib._bootstrap>", line 955, in _find_and_load_unlocked
File "<frozen importlib._bootstrap>", line 665, in _load_unlocked
File "<frozen importlib._bootstrap_external>", line 678, in exec_module
File "<frozen importlib._bootstrap>", line 219, in _call_with_frames_removed
File "/app/scrapers/ca_on_toronto/__init__.py", line 1, in <module>
from .jurisdiction import TorontoJurisdiction
File "/app/scrapers/ca_on_toronto/jurisdiction.py", line 3, in <module>
from .constants import TWO_LETTER_ORG_CODE_SCHEME
ModuleNotFoundError: No module named 'ca_on_toronto.constants'
|
|
C
|
ca_on_toronto_candidates
|
2020-07-05 04:24:33
|
2020-07-05 04:24:33
|
|
|
C
|
ca_on_uxbridge
|
2020-07-05 04:04:00
|
2020-07-05 04:04:00
|
|
|
C
|
ca_on_vaughan
|
2020-07-05 04:38:38
|
2020-07-05 04:38:38
|
|
|
C
|
ca_on_waterloo
|
2020-07-05 04:21:06
|
2020-07-05 04:21:06
|
|
|
D>
|
ca_on_waterloo_region
|
2020-04-28 04:33:42
|
2020-07-05 04:38:27
|
KeyError: 'district name'
Traceback (most recent call last):
File "/app/reports/utils.py", line 71, in scrape_people
report.report = subcommand.handle(args, other)
File "/app/.heroku/src/pupa/pupa/cli/commands/update.py", line 260, in handle
return self.do_handle(args, other, juris)
File "/app/.heroku/src/pupa/pupa/cli/commands/update.py", line 305, in do_handle
report['scrape'] = self.do_scrape(juris, args, scrapers)
File "/app/.heroku/src/pupa/pupa/cli/commands/update.py", line 173, in do_scrape
report[scraper_name] = scraper.do_scrape(**scrape_args)
File "/app/.heroku/src/pupa/pupa/scrape/base.py", line 99, in do_scrape
for obj in self.scrape(**kwargs) or []:
File "/app/scrapers/utils.py", line 380, in scrape
row[key] = corrections(row[key])
KeyError: 'district name'
|
|
C
|
ca_on_welland
|
2020-07-05 04:21:09
|
2020-07-05 04:21:09
|
|
|
C
|
ca_on_wellesley
|
2020-07-05 04:18:36
|
2020-07-05 04:18:36
|
|
|
C
|
ca_on_whitby
|
2020-07-05 04:31:15
|
2020-07-05 04:31:15
|
|
|
C
|
ca_on_whitchurch_stouffville
|
2020-07-05 04:37:51
|
2020-07-05 04:37:51
|
|
|
C
|
ca_on_windsor
|
2020-07-05 04:16:02
|
2020-07-05 04:16:02
|
|
D>
04:21:03 WARNING pupa: could not save RunPlan, no successful runs of ocd-jurisdiction/country:ca/province:pe/legislature yet
|
ca_pe
|
|
2020-07-05 04:21:03
|
AssertionError: No members found
Traceback (most recent call last):
File "/app/reports/utils.py", line 71, in scrape_people
report.report = subcommand.handle(args, other)
File "/app/.heroku/src/pupa/pupa/cli/commands/update.py", line 260, in handle
return self.do_handle(args, other, juris)
File "/app/.heroku/src/pupa/pupa/cli/commands/update.py", line 305, in do_handle
report['scrape'] = self.do_scrape(juris, args, scrapers)
File "/app/.heroku/src/pupa/pupa/cli/commands/update.py", line 173, in do_scrape
report[scraper_name] = scraper.do_scrape(**scrape_args)
File "/app/.heroku/src/pupa/pupa/scrape/base.py", line 99, in do_scrape
for obj in self.scrape(**kwargs) or []:
File "/app/scrapers/ca_pe/people.py", line 13, in scrape
assert len(members), 'No members found'
AssertionError: No members found
|
|
C
|
ca_pe_charlottetown
|
2020-07-05 04:22:16
|
2020-07-05 04:22:16
|
|
|
C
|
ca_qc
|
2020-07-05 04:43:01
|
2020-07-05 04:43:01
|
|
|
C
|
ca_qc_beaconsfield
|
2020-07-05 04:24:24
|
2020-07-05 04:24:24
|
|
D>
04:44:59 WARNING pupa: could not save RunPlan, no successful runs of ocd-jurisdiction/country:ca/csd:2458007/legislature yet
|
ca_qc_brossard
|
|
2020-07-05 04:44:59
|
AssertionError: No councillors found
Traceback (most recent call last):
File "/app/reports/utils.py", line 71, in scrape_people
report.report = subcommand.handle(args, other)
File "/app/.heroku/src/pupa/pupa/cli/commands/update.py", line 260, in handle
return self.do_handle(args, other, juris)
File "/app/.heroku/src/pupa/pupa/cli/commands/update.py", line 305, in do_handle
report['scrape'] = self.do_scrape(juris, args, scrapers)
File "/app/.heroku/src/pupa/pupa/cli/commands/update.py", line 173, in do_scrape
report[scraper_name] = scraper.do_scrape(**scrape_args)
File "/app/.heroku/src/pupa/pupa/scrape/base.py", line 99, in do_scrape
for obj in self.scrape(**kwargs) or []:
File "/app/scrapers/ca_qc_brossard/people.py", line 17, in scrape
assert len(councillors), 'No councillors found'
AssertionError: No councillors found
|
|
C
|
ca_qc_cote_saint_luc
|
2020-07-05 04:21:30
|
2020-07-05 04:21:30
|
|
|
C
|
ca_qc_dollard_des_ormeaux
|
2020-07-05 04:37:49
|
2020-07-05 04:37:49
|
|
|
C
|
ca_qc_dorval
|
2020-07-05 04:21:26
|
2020-07-05 04:21:26
|
|
D>
04:45:06 WARNING pupa: could not save RunPlan, no successful runs of ocd-jurisdiction/country:ca/csd:2481017/legislature yet
|
ca_qc_gatineau
|
|
2020-07-05 04:45:06
|
IndexError: list index out of range
Traceback (most recent call last):
File "/app/reports/utils.py", line 71, in scrape_people
report.report = subcommand.handle(args, other)
File "/app/.heroku/src/pupa/pupa/cli/commands/update.py", line 260, in handle
return self.do_handle(args, other, juris)
File "/app/.heroku/src/pupa/pupa/cli/commands/update.py", line 305, in do_handle
report['scrape'] = self.do_scrape(juris, args, scrapers)
File "/app/.heroku/src/pupa/pupa/cli/commands/update.py", line 173, in do_scrape
report[scraper_name] = scraper.do_scrape(**scrape_args)
File "/app/.heroku/src/pupa/pupa/scrape/base.py", line 99, in do_scrape
for obj in self.scrape(**kwargs) or []:
File "/app/scrapers/ca_qc_gatineau/people.py", line 19, in scrape
p = Person(primary_org='legislature', name=names[0], district='Gatineau', role='Maire')
IndexError: list index out of range
|
|
C
|
ca_qc_kirkland
|
2020-07-05 04:46:21
|
2020-07-05 04:46:21
|
|
|
C
|
ca_qc_laval
|
2020-07-05 04:21:19
|
2020-07-05 04:21:19
|
|
|
C
|
ca_qc_levis
|
2020-07-05 04:38:13
|
2020-07-05 04:38:13
|
|
D>
04:21:05 WARNING pupa: could not save RunPlan, no successful runs of ocd-jurisdiction/country:ca/csd:2458227/legislature yet
|
ca_qc_longueuil
|
|
2020-07-05 04:21:05
|
lxml.etree.XMLSyntaxError: line 2816: b'Element script embeds close tag'
Traceback (most recent call last):
File "/app/reports/utils.py", line 71, in scrape_people
report.report = subcommand.handle(args, other)
File "/app/.heroku/src/pupa/pupa/cli/commands/update.py", line 260, in handle
return self.do_handle(args, other, juris)
File "/app/.heroku/src/pupa/pupa/cli/commands/update.py", line 305, in do_handle
report['scrape'] = self.do_scrape(juris, args, scrapers)
File "/app/.heroku/src/pupa/pupa/cli/commands/update.py", line 173, in do_scrape
report[scraper_name] = scraper.do_scrape(**scrape_args)
File "/app/.heroku/src/pupa/pupa/scrape/base.py", line 99, in do_scrape
for obj in self.scrape(**kwargs) or []:
File "/app/scrapers/ca_qc_longueuil/people.py", line 9, in scrape
page = self.lxmlize(COUNCIL_PAGE, 'utf-8')
File "/app/scrapers/utils.py", line 190, in lxmlize
page = lxml.html.fromstring(text)
File "/app/.heroku/python/lib/python3.6/site-packages/lxml/html/__init__.py", line 706, in fromstring
doc = document_fromstring(html, parser=parser, base_url=base_url, **kw)
File "/app/.heroku/python/lib/python3.6/site-packages/lxml/html/__init__.py", line 600, in document_fromstring
value = etree.fromstring(html, parser, **kw)
File "lxml.etree.pyx", line 3032, in lxml.etree.fromstring (src/lxml/lxml.etree.c:68121)
File "parser.pxi", line 1786, in lxml.etree._parseMemoryDocument (src/lxml/lxml.etree.c:102470)
File "parser.pxi", line 1667, in lxml.etree._parseDoc (src/lxml/lxml.etree.c:101229)
File "parser.pxi", line 1035, in lxml.etree._BaseParser._parseUnicodeDoc (src/lxml/lxml.etree.c:96139)
File "parser.pxi", line 582, in lxml.etree._ParserContext._handleParseResultDoc (src/lxml/lxml.etree.c:91290)
File "parser.pxi", line 683, in lxml.etree._handleParseResult (src/lxml/lxml.etree.c:92476)
File "parser.pxi", line 631, in lxml.etree._raiseParseError (src/lxml/lxml.etree.c:91904)
File "<string>", line None
lxml.etree.XMLSyntaxError: line 2816: b'Element script embeds close tag'
|
D>
04:26:19 WARNING scrapelib: got Exceeded 30 redirects. sleeping for 10 seconds before retry
04:26:52 WARNING scrapelib: got Exceeded 30 redirects. sleeping for 20 seconds before retry
04:27:34 WARNING scrapelib: got Exceeded 30 redirects. sleeping for 40 seconds before retry
04:28:34 WARNING pupa: could not save RunPlan, no successful runs of ocd-jurisdiction/country:ca/csd:2467045/legislature yet
|
ca_qc_mercier
|
|
2020-07-05 04:28:34
|
requests.exceptions.TooManyRedirects: Exceeded 30 redirects.
Traceback (most recent call last):
File "/app/reports/utils.py", line 71, in scrape_people
report.report = subcommand.handle(args, other)
File "/app/.heroku/src/pupa/pupa/cli/commands/update.py", line 260, in handle
return self.do_handle(args, other, juris)
File "/app/.heroku/src/pupa/pupa/cli/commands/update.py", line 305, in do_handle
report['scrape'] = self.do_scrape(juris, args, scrapers)
File "/app/.heroku/src/pupa/pupa/cli/commands/update.py", line 173, in do_scrape
report[scraper_name] = scraper.do_scrape(**scrape_args)
File "/app/.heroku/src/pupa/pupa/scrape/base.py", line 99, in do_scrape
for obj in self.scrape(**kwargs) or []:
File "/app/scrapers/ca_qc_mercier/people.py", line 10, in scrape
page = self.lxmlize(COUNCIL_PAGE, user_agent=CUSTOM_USER_AGENT, encoding='windows-1252')
File "/app/scrapers/utils.py", line 180, in lxmlize
response = self.get(url, cookies=cookies)
File "/app/scrapers/utils.py", line 172, in get
return super().get(*args, verify=SSL_VERIFY, **kwargs)
File "/app/.heroku/python/lib/python3.6/site-packages/requests/sessions.py", line 537, in get
return self.request('GET', url, **kwargs)
File "/app/.heroku/python/lib/python3.6/site-packages/scrapelib/__init__.py", line 286, in request
**kwargs)
File "/app/.heroku/python/lib/python3.6/site-packages/scrapelib/cache.py", line 66, in request
resp = super(CachingSession, self).request(method, url, **kwargs)
File "/app/.heroku/python/lib/python3.6/site-packages/scrapelib/__init__.py", line 88, in request
return super(ThrottledSession, self).request(method, url, **kwargs)
File "/app/.heroku/python/lib/python3.6/site-packages/scrapelib/__init__.py", line 182, in request
raise exception_raised
File "/app/.heroku/python/lib/python3.6/site-packages/scrapelib/__init__.py", line 153, in request
resp = super(RetrySession, self).request(method, url, **kwargs)
File "/app/.heroku/python/lib/python3.6/site-packages/requests/sessions.py", line 524, in request
resp = self.send(prep, **send_kwargs)
File "/app/.heroku/python/lib/python3.6/site-packages/requests/sessions.py", line 659, in send
history = [resp for resp in gen] if allow_redirects else []
File "/app/.heroku/python/lib/python3.6/site-packages/requests/sessions.py", line 659, in <listcomp>
history = [resp for resp in gen] if allow_redirects else []
File "/app/.heroku/python/lib/python3.6/site-packages/requests/sessions.py", line 156, in resolve_redirects
raise TooManyRedirects('Exceeded %s redirects.' % self.max_redirects, response=resp)
requests.exceptions.TooManyRedirects: Exceeded 30 redirects.
|
D>
04:38:42 WARNING pupa: could not save RunPlan, no successful runs of ocd-jurisdiction/country:ca/csd:2466023/legislature yet
|
ca_qc_montreal
|
|
2020-07-05 04:38:42
|
pupa.exceptions.UnresolvedIdError: cannot resolve pseudo id to Post: ~{"label": "Jeanne-Mance", "organization__classificatio…
Traceback (most recent call last):
File "/app/reports/utils.py", line 71, in scrape_people
report.report = subcommand.handle(args, other)
File "/app/.heroku/src/pupa/pupa/cli/commands/update.py", line 260, in handle
return self.do_handle(args, other, juris)
File "/app/.heroku/src/pupa/pupa/cli/commands/update.py", line 307, in do_handle
report['import'] = self.do_import(juris, args)
File "/app/.heroku/src/pupa/pupa/cli/commands/update.py", line 211, in do_import
report.update(membership_importer.import_directory(datadir))
File "/app/.heroku/src/pupa/pupa/importers/base.py", line 190, in import_directory
return self.import_data(json_stream())
File "/app/.heroku/src/pupa/pupa/importers/base.py", line 227, in import_data
obj_id, what = self.import_item(data)
File "/app/.heroku/src/pupa/pupa/importers/base.py", line 247, in import_item
data = self.prepare_for_db(data)
File "/app/.heroku/src/pupa/pupa/importers/memberships.py", line 50, in prepare_for_db
data['post_id'] = self.post_importer.resolve_json_id(data['post_id'])
File "/app/.heroku/src/pupa/pupa/importers/base.py", line 165, in resolve_json_id
raise UnresolvedIdError(errmsg)
pupa.exceptions.UnresolvedIdError: cannot resolve pseudo id to Post: ~{"label": "Jeanne-Mance", "organization__classification": "legislature", "role": "Maire suppl\u00e9ant d'arrondissement"}
|
|
C
|
ca_qc_montreal_est
|
2020-07-05 04:30:23
|
2020-07-05 04:30:23
|
|
|
C
|
ca_qc_pointe_claire
|
2020-07-05 04:45:09
|
2020-07-05 04:45:09
|
|
|
C
|
ca_qc_quebec
|
2020-07-05 04:01:21
|
2020-07-05 04:01:21
|
|
|
C
|
ca_qc_saguenay
|
2020-07-05 04:16:00
|
2020-07-05 04:16:00
|
|
|
C
|
ca_qc_sainte_anne_de_bellevue
|
2020-07-05 04:19:47
|
2020-07-05 04:19:47
|
|
|
C
|
ca_qc_saint_jean_sur_richelieu
|
2020-07-05 04:22:00
|
2020-07-05 04:22:00
|
|
|
C
|
ca_qc_saint_jerome
|
2020-07-05 04:19:45
|
2020-07-05 04:19:45
|
|
|
C
|
ca_qc_senneville
|
2020-07-05 05:58:47
|
2020-07-05 05:58:48
|
|
D>
05:03:26 WARNING pupa: could not save RunPlan, no successful runs of ocd-jurisdiction/country:ca/csd:2443027/legislature yet
|
ca_qc_sherbrooke
|
|
2020-07-05 05:03:26
|
AssertionError: No councillors found
Traceback (most recent call last):
File "/app/reports/utils.py", line 71, in scrape_people
report.report = subcommand.handle(args, other)
File "/app/.heroku/src/pupa/pupa/cli/commands/update.py", line 260, in handle
return self.do_handle(args, other, juris)
File "/app/.heroku/src/pupa/pupa/cli/commands/update.py", line 305, in do_handle
report['scrape'] = self.do_scrape(juris, args, scrapers)
File "/app/.heroku/src/pupa/pupa/cli/commands/update.py", line 173, in do_scrape
report[scraper_name] = scraper.do_scrape(**scrape_args)
File "/app/.heroku/src/pupa/pupa/scrape/base.py", line 99, in do_scrape
for obj in self.scrape(**kwargs) or []:
File "/app/scrapers/ca_qc_sherbrooke/people.py", line 11, in scrape
assert len(councillors), 'No councillors found'
AssertionError: No councillors found
|
D>
04:19:40 WARNING pupa: could not save RunPlan, no successful runs of ocd-jurisdiction/country:ca/csd:2464008/legislature yet
|
ca_qc_terrebonne
|
|
2020-07-05 04:19:40
|
pupa.exceptions.UnresolvedIdError: cannot resolve pseudo id to Post: ~{"label": "District Maire", "organization__classificat…
Traceback (most recent call last):
File "/app/reports/utils.py", line 71, in scrape_people
report.report = subcommand.handle(args, other)
File "/app/.heroku/src/pupa/pupa/cli/commands/update.py", line 260, in handle
return self.do_handle(args, other, juris)
File "/app/.heroku/src/pupa/pupa/cli/commands/update.py", line 307, in do_handle
report['import'] = self.do_import(juris, args)
File "/app/.heroku/src/pupa/pupa/cli/commands/update.py", line 211, in do_import
report.update(membership_importer.import_directory(datadir))
File "/app/.heroku/src/pupa/pupa/importers/base.py", line 190, in import_directory
return self.import_data(json_stream())
File "/app/.heroku/src/pupa/pupa/importers/base.py", line 227, in import_data
obj_id, what = self.import_item(data)
File "/app/.heroku/src/pupa/pupa/importers/base.py", line 247, in import_item
data = self.prepare_for_db(data)
File "/app/.heroku/src/pupa/pupa/importers/memberships.py", line 50, in prepare_for_db
data['post_id'] = self.post_importer.resolve_json_id(data['post_id'])
File "/app/.heroku/src/pupa/pupa/importers/base.py", line 165, in resolve_json_id
raise UnresolvedIdError(errmsg)
pupa.exceptions.UnresolvedIdError: cannot resolve pseudo id to Post: ~{"label": "District Maire", "organization__classification": "legislature", "role": "Conseiller"}
|
|
C
|
ca_qc_trois_rivieres
|
2020-07-05 04:38:08
|
2020-07-05 04:38:08
|
|
|
C
|
ca_qc_westmount
|
2020-07-05 04:46:25
|
2020-07-05 04:46:25
|
|
D>
04:21:00 WARNING pupa: validation of Membership ee8a7aea-be76-11ea-92f7-3ec7af0fe542 failed: 1 validation errors:
Value '307' for field '' does not match regular expression '\A1 \d{3} \d{3}-\d{4}(?: x\d+)?\Z'
04:21:00 WARNING pupa: could not save RunPlan, no successful runs of ocd-jurisdiction/country:ca/province:sk/legislature yet
|
ca_sk
|
|
2020-07-05 04:21:00
|
Value '307' for field '' does not match regular expression '\A1 \d{3} \d{3}-\d{4}(?: x\d+)?\Z'
Traceback (most recent call last):
File "/app/.heroku/src/pupa/pupa/scrape/base.py", line 175, in validate
validator.validate(self.as_dict(), schema)
File "/app/.heroku/python/lib/python3.6/site-packages/validictory/validator.py", line 620, in validate
raise MultipleValidationError(self._errors)
validictory.validator.MultipleValidationError: 1 validation errors:
Value '307' for field '' does not match regular expression '\A1 \d{3} \d{3}-\d{4}(?: x\d+)?\Z'
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "/app/reports/utils.py", line 71, in scrape_people
report.report = subcommand.handle(args, other)
File "/app/.heroku/src/pupa/pupa/cli/commands/update.py", line 260, in handle
return self.do_handle(args, other, juris)
File "/app/.heroku/src/pupa/pupa/cli/commands/update.py", line 305, in do_handle
report['scrape'] = self.do_scrape(juris, args, scrapers)
File "/app/.heroku/src/pupa/pupa/cli/commands/update.py", line 173, in do_scrape
report[scraper_name] = scraper.do_scrape(**scrape_args)
File "/app/.heroku/src/pupa/pupa/scrape/base.py", line 104, in do_scrape
self.save_object(obj)
File "/app/.heroku/src/pupa/pupa/scrape/base.py", line 93, in save_object
self.save_object(obj)
File "/app/.heroku/src/pupa/pupa/scrape/base.py", line 89, in save_object
raise ve
File "/app/.heroku/src/pupa/pupa/scrape/base.py", line 85, in save_object
obj.validate()
File "/app/.heroku/src/pupa/pupa/scrape/base.py", line 178, in validate
self.__class__.__name__, self._id, ve)
pupa.exceptions.ScrapeValueError: validation of Membership ee8a7aea-be76-11ea-92f7-3ec7af0fe542 failed: 1 validation errors:
Value '307' for field '' does not match regular expression '\A1 \d{3} \d{3}-\d{4}(?: x\d+)?\Z'
|
|
C
|
ca_sk_regina
|
2020-07-05 04:24:46
|
2020-07-05 04:24:46
|
|
|
C
|
ca_sk_saskatoon
|
2020-07-05 04:22:04
|
2020-07-05 04:22:04
|
|