|
C
|
ca
|
2020-06-04 04:22:59
|
2020-06-04 04:22:59
|
|
D>
04:43:01 WARNING pupa: validation of Membership df404158-a61d-11ea-823a-0693d93ba8bb 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'
04:43:01 WARNING pupa: could not save RunPlan, no successful runs of ocd-jurisdiction/country:ca/province:ab/legislature yet
|
ca_ab
|
|
2020-06-04 04:43:01
|
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 df404158-a61d-11ea-823a-0693d93ba8bb 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'
|
|
C
|
ca_ab_calgary
|
2020-06-04 04:09:36
|
2020-06-04 04:09:36
|
|
D>
04:30:30 WARNING pupa: could not save RunPlan, no successful runs of ocd-jurisdiction/country:ca/province:ab/executive yet
|
ca_ab_candidates
|
|
2020-06-04 04:30:30
|
pupa.exceptions.UnresolvedIdError: cannot resolve pseudo id to Post: ~{"label": "Strathcona-Sherwood Park", "organization__c…
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": "Strathcona-Sherwood Park", "organization__classification": "executive", "role": "MLA"}
|
|
C
|
ca_ab_edmonton
|
2020-06-04 04:27:50
|
2020-06-04 04:27:50
|
|
|
D>
|
ca_ab_grande_prairie
|
2020-05-15 04:13:50
|
2020-06-04 04:43:03
|
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
|
2020-06-04 04:01:52
|
2020-06-04 04:01:52
|
|
|
C
|
ca_ab_lethbridge
|
2020-06-04 04:45:23
|
2020-06-04 04:45:23
|
|
|
C
|
ca_ab_strathcona_county
|
2020-06-04 04:09:31
|
2020-06-04 04:09:31
|
|
|
C
|
ca_ab_wood_buffalo
|
2020-06-04 04:00:40
|
2020-06-04 04:00:40
|
|
|
C
|
ca_bc
|
2020-06-04 04:45:22
|
2020-06-04 04:45:22
|
|
|
C
|
ca_bc_abbotsford
|
2020-06-04 04:32:06
|
2020-06-04 04:32:06
|
|
|
C
|
ca_bc_burnaby
|
2020-06-04 04:39:55
|
2020-06-04 04:39:55
|
|
|
C
|
ca_bc_coquitlam
|
2020-06-04 04:01:14
|
2020-06-04 04:01:14
|
|
|
C
|
ca_bc_kelowna
|
2020-06-04 04:03:35
|
2020-06-04 04:03:35
|
|
|
C
|
ca_bc_langley
|
2020-06-04 04:43:02
|
2020-06-04 04:43:02
|
|
|
C
|
ca_bc_municipalities
|
2020-06-04 04:09:27
|
2020-06-04 04:09:28
|
|
|
C
|
ca_bc_municipalities_candidates
|
2020-06-04 04:03:19
|
2020-06-04 04:03:20
|
|
|
C
|
ca_bc_new_westminster
|
2020-06-04 04:23:31
|
2020-06-04 04:23:31
|
|
|
C
|
ca_bc_richmond
|
2020-06-04 04:38:33
|
2020-06-04 04:38:33
|
|
D>
04:30:22 WARNING pupa: could not save RunPlan, no successful runs of ocd-jurisdiction/country:ca/csd:5917021/legislature yet
|
ca_bc_saanich
|
|
2020-06-04 04:30:22
|
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
|
2020-06-04 04:23:30
|
2020-06-04 04:23:30
|
|
|
C
|
ca_bc_vancouver
|
2020-06-04 04:01:54
|
2020-06-04 04:01:54
|
|
|
D>
|
ca_bc_victoria
|
2020-04-28 04:01:47
|
2020-06-04 04:32:02
|
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
|
2020-06-04 04:01:49
|
2020-06-04 04:01:50
|
|
|
C
|
ca_mb
|
2020-06-04 04:10:56
|
2020-06-04 04:10:57
|
|
D>
04:28:09 WARNING pupa: could not save RunPlan, no successful runs of ocd-jurisdiction/country:ca/province:mb/executive yet
|
ca_mb_candidates
|
|
2020-06-04 04:28:09
|
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/6bb1d533-5af5-4b81-b769-ab6a4050aace', '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
|
2020-06-04 04:25:17
|
2020-06-04 04:25:17
|
|
|
D>
|
ca_municipalities
|
|
2020-06-04 04:37:28
|
pupa.exceptions.SameNameError: multiple people with same name "Michel Duval" in Jurisdiction - must provide birth_date to di…
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 "Michel Duval" in Jurisdiction - must provide birth_date to disambiguate
|
|
C
|
ca_nb
|
2020-06-04 04:38:19
|
2020-06-04 04:38:19
|
|
|
C
|
ca_nb_fredericton
|
2020-06-04 04:39:05
|
2020-06-04 04:39:05
|
|
D>
04:01:50 WARNING pupa: validation of CanadianPerson 1e76f26e-a618-11ea-823a-0693d93ba8bb 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
|
2020-06-04 04:01:50
|
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 1e76f26e-a618-11ea-823a-0693d93ba8bb 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
|
2020-06-04 04:27:35
|
2020-06-04 04:27:35
|
|
|
C
|
ca_nb_saint_john
|
2020-06-04 04:03:34
|
2020-06-04 04:03:34
|
|
|
C
|
ca_nl
|
2020-06-04 04:43:45
|
2020-06-04 04:43:45
|
|
|
C
|
ca_nl_st_john_s
|
2020-06-04 04:23:32
|
2020-06-04 04:23:32
|
|
|
C
|
ca_ns
|
2020-06-04 04:25:14
|
2020-06-04 04:25:14
|
|
|
C
|
ca_ns_cape_breton
|
2020-06-04 04:31:57
|
2020-06-04 04:31:57
|
|
|
C
|
ca_ns_halifax
|
2020-06-04 04:38:51
|
2020-06-04 04:38:51
|
|
|
C
|
ca_on
|
2020-06-04 04:30:21
|
2020-06-04 04:30:21
|
|
|
C
|
ca_on_ajax
|
2020-06-04 04:09:38
|
2020-06-04 04:09:38
|
|
|
C
|
ca_on_belleville
|
2020-06-04 04:42:53
|
2020-06-04 04:42:53
|
|
|
C
|
ca_on_brampton
|
2020-06-04 04:32:07
|
2020-06-04 04:32:07
|
|
|
C
|
ca_on_brantford
|
2020-06-04 04:42:50
|
2020-06-04 04:42:50
|
|
D>
04:30:33 WARNING scrapelib: sleeping for 10 seconds before retry
04:30:43 WARNING scrapelib: sleeping for 20 seconds before retry
04:31:03 WARNING scrapelib: sleeping for 40 seconds before retry
|
ca_on_burlington
|
2020-04-28 04:17:23
|
2020-06-04 04:31:43
|
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
|
|
C
|
ca_on_caledon
|
2020-06-04 04:03:31
|
2020-06-04 04:03:31
|
|
|
C
|
ca_on_cambridge
|
2020-06-04 04:32:03
|
2020-06-04 04:32:03
|
|
|
C
|
ca_on_chatham_kent
|
2020-06-04 04:32:21
|
2020-06-04 04:32:21
|
|
|
C
|
ca_on_fort_erie
|
2020-06-04 04:42:56
|
2020-06-04 04:42:56
|
|
|
C
|
ca_on_georgina
|
2020-06-04 04:28:12
|
2020-06-04 04:28:12
|
|
|
C
|
ca_on_greater_sudbury
|
2020-06-04 04:27:37
|
2020-06-04 04:27:37
|
|
|
C
|
ca_on_grimsby
|
2020-06-04 04:11:10
|
2020-06-04 04:11:10
|
|
|
C
|
ca_on_guelph
|
2020-06-04 04:11:14
|
2020-06-04 04:11:14
|
|
D>
04:32:27 WARNING pupa: could not save RunPlan, no successful runs of ocd-jurisdiction/country:ca/csd:3528018/legislature yet
|
ca_on_haldimand_county
|
|
2020-06-04 04:32:27
|
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>
04:03:32 WARNING pupa: could not save RunPlan, no successful runs of ocd-jurisdiction/country:ca/csd:3525005/legislature yet
|
ca_on_hamilton
|
|
2020-06-04 04:03:32
|
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>
04:09:33 WARNING pupa: could not save RunPlan, no successful runs of ocd-jurisdiction/country:ca/cd:3540/legislature yet
|
ca_on_huron
|
|
2020-06-04 04:09:33
|
pupa.exceptions.UnresolvedIdError: cannot resolve pseudo id to Post: ~{"label": "Huron (seat 12)", "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 12)", "organization__classification": "legislature", "role": "Councillor"}
|
|
C
|
ca_on_king
|
2020-06-04 04:00:56
|
2020-06-04 04:00:56
|
|
|
C
|
ca_on_kingston
|
2020-06-04 04:23:35
|
2020-06-04 04:23:35
|
|
|
C
|
ca_on_kitchener
|
2020-06-04 04:09:29
|
2020-06-04 04:09:29
|
|
|
C
|
ca_on_lambton
|
2020-06-04 04:42:52
|
2020-06-04 04:42:52
|
|
|
C
|
ca_on_lincoln
|
2020-06-04 04:39:56
|
2020-06-04 04:39:56
|
|
|
C
|
ca_on_london
|
2020-06-04 04:32:22
|
2020-06-04 04:32:22
|
|
D>
04:00:28 WARNING pupa: could not save RunPlan, no successful runs of ocd-jurisdiction/country:ca/csd:3519036/legislature yet
|
ca_on_markham
|
|
2020-06-04 04:00:28
|
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>
04:25:15 WARNING pupa: could not save RunPlan, no successful runs of ocd-jurisdiction/country:ca/csd:3524009/legislature yet
|
ca_on_milton
|
|
2020-06-04 04:25:15
|
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
|
2020-06-04 04:39:18
|
2020-06-04 04:39:18
|
|
|
C
|
ca_on_newmarket
|
2020-06-04 04:00:51
|
2020-06-04 04:00:51
|
|
|
C
|
ca_on_niagara
|
2020-06-04 04:00:50
|
2020-06-04 04:00:50
|
|
|
C
|
ca_on_niagara_on_the_lake
|
2020-06-04 04:42:54
|
2020-06-04 04:42:54
|
|
|
C
|
ca_on_north_dumfries
|
2020-06-04 04:11:17
|
2020-06-04 04:11:17
|
|
D>
04:32:25 WARNING pupa: validation of CanadianPerson 63edc3a0-a61c-11ea-823a-0693d93ba8bb 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
|
2020-06-04 04:32:25
|
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 63edc3a0-a61c-11ea-823a-0693d93ba8bb 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>
04:23:00 WARNING pupa: could not save RunPlan, no successful runs of ocd-jurisdiction/country:ca/csd:3518013/legislature yet
|
ca_on_oshawa
|
|
2020-06-04 04:23:00
|
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#b0ddd1c9dfc2f0dfc3d8d1c7d19ed3d1">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>
04:39:31 WARNING pupa: could not save RunPlan, no successful runs of ocd-jurisdiction/country:ca/csd:3506008/legislature yet
|
ca_on_ottawa
|
|
2020-06-04 04:39:31
|
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_on_peel
|
2020-06-04 04:39:58
|
2020-06-04 04:39:58
|
|
|
C
|
ca_on_pickering
|
2020-06-04 04:37:29
|
2020-06-04 04:37:29
|
|
|
C
|
ca_on_richmond_hill
|
2020-06-04 04:01:24
|
2020-06-04 04:01:24
|
|
|
C
|
ca_on_school_boards_english_public
|
2020-06-04 04:02:24
|
2020-06-04 04:02:24
|
|
|
C
|
ca_on_st_catharines
|
2020-06-04 04:39:56
|
2020-06-04 04:39:56
|
|
D>
04:09:34 WARNING pupa: could not save RunPlan, no successful runs of ocd-jurisdiction/country:ca/csd:3558004/legislature yet
|
ca_on_thunder_bay
|
|
2020-06-04 04:09:34
|
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
|
|
C
|
ca_on_toronto_candidates
|
2020-06-04 04:01:03
|
2020-06-04 04:01:03
|
|
|
C
|
ca_on_uxbridge
|
2020-06-04 04:00:57
|
2020-06-04 04:00:57
|
|
|
C
|
ca_on_vaughan
|
2020-06-04 04:11:09
|
2020-06-04 04:11:09
|
|
|
C
|
ca_on_waterloo
|
2020-06-04 04:02:26
|
2020-06-04 04:02:26
|
|
|
D>
|
ca_on_waterloo_region
|
2020-04-28 04:33:42
|
2020-06-04 04:30:24
|
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
|
2020-06-04 04:38:22
|
2020-06-04 04:38:22
|
|
|
C
|
ca_on_wellesley
|
2020-06-04 04:30:33
|
2020-06-04 04:30:33
|
|
|
C
|
ca_on_whitby
|
2020-06-04 04:25:27
|
2020-06-04 04:25:27
|
|
|
C
|
ca_on_whitchurch_stouffville
|
2020-06-04 04:02:27
|
2020-06-04 04:02:27
|
|
|
C
|
ca_on_windsor
|
2020-06-04 04:23:33
|
2020-06-04 04:23:33
|
|
D>
04:42:55 WARNING pupa: could not save RunPlan, no successful runs of ocd-jurisdiction/country:ca/province:pe/legislature yet
|
ca_pe
|
|
2020-06-04 04:42:55
|
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
|
2020-06-04 04:03:37
|
2020-06-04 04:03:38
|
|
|
C
|
ca_qc
|
2020-06-04 04:36:45
|
2020-06-04 04:36:46
|
|
|
C
|
ca_qc_beaconsfield
|
2020-06-04 04:00:59
|
2020-06-04 04:00:59
|
|
D>
04:30:32 WARNING pupa: could not save RunPlan, no successful runs of ocd-jurisdiction/country:ca/csd:2458007/legislature yet
|
ca_qc_brossard
|
|
2020-06-04 04:30:32
|
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
|
2020-06-04 04:23:01
|
2020-06-04 04:23:01
|
|
|
C
|
ca_qc_dollard_des_ormeaux
|
2020-06-04 04:42:56
|
2020-06-04 04:42:56
|
|
|
C
|
ca_qc_dorval
|
2020-06-04 04:40:01
|
2020-06-04 04:40:01
|
|
D>
04:43:47 WARNING pupa: could not save RunPlan, no successful runs of ocd-jurisdiction/country:ca/csd:2481017/legislature yet
|
ca_qc_gatineau
|
|
2020-06-04 04:43:47
|
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_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
|
2020-06-04 04:11:16
|
2020-06-04 04:11:16
|
|
|
C
|
ca_qc_laval
|
2020-06-04 04:09:40
|
2020-06-04 04:09:40
|
|
|
C
|
ca_qc_levis
|
2020-06-04 04:00:46
|
2020-06-04 04:00:46
|
|
D>
04:28:05 WARNING pupa: could not save RunPlan, no successful runs of ocd-jurisdiction/country:ca/csd:2458227/legislature yet
|
ca_qc_longueuil
|
|
2020-06-04 04:28:05
|
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_longueuil/people.py", line 29, in scrape
detail_url = tr.xpath('./td[2]/a/@href')[0]
IndexError: list index out of range
|
D>
04:40:26 WARNING scrapelib: got Exceeded 30 redirects. sleeping for 10 seconds before retry
04:41:01 WARNING scrapelib: got Exceeded 30 redirects. sleeping for 20 seconds before retry
04:41:46 WARNING scrapelib: got Exceeded 30 redirects. sleeping for 40 seconds before retry
04:42:49 WARNING pupa: could not save RunPlan, no successful runs of ocd-jurisdiction/country:ca/csd:2467045/legislature yet
|
ca_qc_mercier
|
|
2020-06-04 04:42:49
|
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>
04:11:12 WARNING pupa: could not save RunPlan, no successful runs of ocd-jurisdiction/country:ca/csd:2466023/legislature yet
|
ca_qc_montreal
|
|
2020-06-04 04:11:12
|
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
|
2020-06-04 04:37:30
|
2020-06-04 04:37:30
|
|
|
C
|
ca_qc_pointe_claire
|
2020-06-04 04:30:28
|
2020-06-04 04:30:28
|
|
|
C
|
ca_qc_quebec
|
2020-06-04 04:00:48
|
2020-06-04 04:00:48
|
|
|
C
|
ca_qc_saguenay
|
2020-06-04 04:32:01
|
2020-06-04 04:32:01
|
|
|
C
|
ca_qc_sainte_anne_de_bellevue
|
2020-06-04 04:30:25
|
2020-06-04 04:30:25
|
|
|
C
|
ca_qc_saint_jean_sur_richelieu
|
2020-06-04 04:39:45
|
2020-06-04 04:39:45
|
|
|
C
|
ca_qc_saint_jerome
|
2020-06-04 04:10:58
|
2020-06-04 04:10:58
|
|
|
C
|
ca_qc_senneville
|
2020-06-04 04:38:21
|
2020-06-04 04:38:21
|
|
D>
04:00:41 WARNING pupa: could not save RunPlan, no successful runs of ocd-jurisdiction/country:ca/csd:2443027/legislature yet
|
ca_qc_sherbrooke
|
|
2020-06-04 04:00:41
|
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>
04:23:21 WARNING pupa: could not save RunPlan, no successful runs of ocd-jurisdiction/country:ca/csd:2464008/legislature yet
|
ca_qc_terrebonne
|
|
2020-06-04 04:23:21
|
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
|
2020-06-04 04:09:57
|
2020-06-04 04:09:57
|
|
|
C
|
ca_qc_westmount
|
2020-06-04 04:32:24
|
2020-06-04 04:32:24
|
|
D>
04:00:43 WARNING pupa: validation of Membership f613a808-a617-11ea-823a-0693d93ba8bb failed: 1 validation errors:
Value '307' for field '' does not match regular expression '\A1 \d{3} \d{3}-\d{4}(?: x\d+)?\Z'
04:00:43 WARNING pupa: could not save RunPlan, no successful runs of ocd-jurisdiction/country:ca/province:sk/legislature yet
|
ca_sk
|
|
2020-06-04 04:00:43
|
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 f613a808-a617-11ea-823a-0693d93ba8bb 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
|
2020-06-04 04:39:30
|
2020-06-04 04:39:30
|
|
|
C
|
ca_sk_saskatoon
|
2020-06-04 04:00:26
|
2020-06-04 04:00:26
|
|