|
C
|
ca
|
2020-04-01 04:13:15
|
2020-04-01 04:13:16
|
|
D>
23:51:36 WARNING pupa: validation of Membership b8ebb478-7473-11ea-92d0-96aba9d62532 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'
|
ca_ab
|
2020-01-21 04:28:37
|
2020-04-01 23:51:36
|
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 b8ebb478-7473-11ea-92d0-96aba9d62532 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
|
2020-04-01 04:14:15
|
2020-04-01 04:14:15
|
|
D>
04:27:28 WARNING pupa: could not save RunPlan, no successful runs of ocd-jurisdiction/country:ca/province:ab/executive yet
|
ca_ab_candidates
|
|
2020-04-01 04:27:28
|
pupa.exceptions.UnresolvedIdError: cannot resolve pseudo id to Post: ~{"label": "St. Albert", "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": "St. Albert", "organization__classification": "executive", "role": "MLA"}
|
|
C
|
ca_ab_edmonton
|
2020-04-01 04:28:04
|
2020-04-01 04:28:04
|
|
|
C
|
ca_ab_grande_prairie
|
2020-04-01 04:43:55
|
2020-04-01 04:43:55
|
|
|
C
|
ca_ab_grande_prairie_county_no_1
|
2020-04-01 04:24:18
|
2020-04-01 04:24:18
|
|
|
C
|
ca_ab_lethbridge
|
2020-04-01 04:15:05
|
2020-04-01 04:15:05
|
|
|
C
|
ca_ab_strathcona_county
|
2020-04-01 04:24:00
|
2020-04-01 04:24:01
|
|
|
C
|
ca_ab_wood_buffalo
|
2020-04-01 04:22:30
|
2020-04-01 04:22:30
|
|
|
C
|
ca_bc
|
2020-04-01 04:29:46
|
2020-04-01 04:29:46
|
|
|
C
|
ca_bc_abbotsford
|
2020-04-01 04:01:17
|
2020-04-01 04:01:17
|
|
|
C
|
ca_bc_burnaby
|
2020-04-01 04:24:13
|
2020-04-01 04:24:13
|
|
|
C
|
ca_bc_coquitlam
|
2020-04-01 04:14:13
|
2020-04-01 04:14:13
|
|
|
C
|
ca_bc_kelowna
|
2020-04-01 04:35:29
|
2020-04-01 04:35:29
|
|
|
C
|
ca_bc_langley
|
2020-04-01 04:23:00
|
2020-04-01 04:23:00
|
|
|
D>
|
ca_bc_municipalities
|
2020-04-01 04:41:24
|
2020-04-01 13:33:22
|
SystemExit: 1
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_bc_municipalities/people.py", line 122, in scrape
municipal_page = self.lxmlize(record_url + '&pn=' + str(i))
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 87, in request
self._throttle()
File "/app/.heroku/python/lib/python3.6/site-packages/scrapelib/__init__.py", line 63, in _throttle
time.sleep(diff)
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_bc_municipalities_candidates
|
2020-04-01 04:22:04
|
2020-04-01 04:22:10
|
|
|
C
|
ca_bc_new_westminster
|
2020-04-01 04:24:15
|
2020-04-01 04:24:15
|
|
|
C
|
ca_bc_richmond
|
2020-04-01 04:19:47
|
2020-04-01 04:19:47
|
|
|
D>
|
ca_bc_saanich
|
2019-10-03 04:03:10
|
2020-04-01 04:15:24
|
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
|
2020-04-01 04:19:56
|
2020-04-01 04:19:56
|
|
|
C
|
ca_bc_vancouver
|
2020-04-01 04:41:53
|
2020-04-01 04:41:53
|
|
|
C
|
ca_bc_victoria
|
2020-04-01 04:29:57
|
2020-04-01 04:29:57
|
|
|
C
|
ca_candidates
|
2020-04-01 04:19:27
|
2020-04-01 04:19:27
|
|
D>
04:27:23 WARNING pupa: could not save RunPlan, no successful runs of ocd-jurisdiction/country:ca/province:mb/legislature yet
|
ca_mb
|
|
2020-04-01 04:27:23
|
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 209, in do_import
report.update(post_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': 'Fort Rouge', 'role': 'MLA', 'organization_id': 'ocd-organization/703e09f5-1e02-46ac-9702-74f167eb0800', 'division_id': 'ocd-division/country:ca/province:mb/ed:fort_rouge', 'start_date': '', 'end_date': '', 'extras': {}} (already imported as MLA - Fort Rouge - Legislative Assembly of Manitoba)
obj1 sources: []
obj2 sources: []
|
D>
04:22:57 WARNING pupa: could not save RunPlan, no successful runs of ocd-jurisdiction/country:ca/province:mb/executive yet
|
ca_mb_candidates
|
|
2020-04-01 04:22:57
|
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/a81b88e2-4bc0-4920-a5cf-6ee3de976404', 'person_name': 'Kevin Nichols', 'organization_id': 'ocd-organization/609ddf79-2e1b-4506-aa6c-45fddca8056f', 'post_id': None, 'on_behalf_of_id': None, 'start_date': '', 'end_date': '', 'extras': {}} (already imported as Kevin Nichols in Green Party (member))
obj1 sources: []
obj2 sources: []
|
|
C
|
ca_mb_winnipeg
|
2020-04-01 13:33:45
|
2020-04-01 13:33:46
|
|
|
D>
|
ca_municipalities
|
|
2020-04-01 18:13:57
|
pupa.exceptions.SameNameError: multiple people with same name "Christian Martin" in Jurisdiction - must provide birth_date t…
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 "Christian Martin" in Jurisdiction - must provide birth_date to disambiguate
|
|
C
|
ca_nb
|
2020-04-01 04:25:38
|
2020-04-01 04:25:38
|
|
|
C
|
ca_nb_fredericton
|
2020-04-01 04:22:46
|
2020-04-01 04:22:46
|
|
|
C
|
ca_nb_moncton
|
2020-04-01 04:13:22
|
2020-04-01 04:13:22
|
|
|
D>
|
ca_nb_municipalities
|
2020-02-28 04:17:00
|
2020-04-01 04:35:26
|
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_nb_municipalities/people.py", line 71, in scrape
division_name = re.sub(r'\ASt\b\.?', 'Saint', page.xpath('//h1/text()')[0].split(' - ', 1)[1])
IndexError: list index out of range
|
|
C
|
ca_nb_saint_john
|
2020-04-01 16:16:02
|
2020-04-01 16:16:02
|
|
|
C
|
ca_nl
|
2020-04-01 04:14:59
|
2020-04-01 04:14:59
|
|
|
C
|
ca_nl_st_john_s
|
2020-04-01 04:35:43
|
2020-04-01 04:35:43
|
|
|
C
|
ca_ns
|
2020-04-01 04:43:53
|
2020-04-01 04:43:53
|
|
|
C
|
ca_ns_cape_breton
|
2020-04-01 04:18:50
|
2020-04-01 04:18:50
|
|
|
C
|
ca_ns_halifax
|
2020-04-01 04:18:34
|
2020-04-01 04:18:35
|
|
|
D>
|
ca_on
|
2019-11-01 04:10:28
|
2020-04-01 10:41:34
|
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_on/people.py", line 23, in scrape
assert len(members), 'No members found'
AssertionError: No members found
|
|
C
|
ca_on_ajax
|
2020-04-01 04:18:16
|
2020-04-01 04:18:16
|
|
|
C
|
ca_on_belleville
|
2020-04-01 04:19:36
|
2020-04-01 04:19:36
|
|
|
C
|
ca_on_brampton
|
2020-04-01 04:13:27
|
2020-04-01 04:13:27
|
|
|
C
|
ca_on_brantford
|
2020-04-01 04:23:50
|
2020-04-01 04:23:50
|
|
|
C
|
ca_on_burlington
|
2020-04-01 04:19:34
|
2020-04-01 04:19:34
|
|
|
C
|
ca_on_caledon
|
2020-04-01 04:30:10
|
2020-04-01 04:30:10
|
|
|
C
|
ca_on_cambridge
|
2020-04-01 04:26:14
|
2020-04-01 04:26:14
|
|
|
C
|
ca_on_chatham_kent
|
2020-04-01 04:26:11
|
2020-04-01 04:26:11
|
|
|
C
|
ca_on_fort_erie
|
2020-04-01 04:18:36
|
2020-04-01 04:18:36
|
|
|
C
|
ca_on_georgina
|
2020-04-01 04:23:40
|
2020-04-01 04:23:40
|
|
|
C
|
ca_on_greater_sudbury
|
2020-04-01 04:27:31
|
2020-04-01 04:27:31
|
|
|
C
|
ca_on_grimsby
|
2020-04-01 04:26:22
|
2020-04-01 04:26:22
|
|
|
C
|
ca_on_guelph
|
2020-04-01 04:01:20
|
2020-04-01 04:01:20
|
|
D>
04:22:13 WARNING pupa: could not save RunPlan, no successful runs of ocd-jurisdiction/country:ca/csd:3528018/legislature yet
|
ca_on_haldimand_county
|
|
2020-04-01 04:22:13
|
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>
|
ca_on_hamilton
|
2019-11-07 04:29:50
|
2020-04-01 07:19:18
|
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>
11:22:20 WARNING pupa: could not save RunPlan, no successful runs of ocd-jurisdiction/country:ca/cd:3540/legislature yet
|
ca_on_huron
|
|
2020-04-01 11:22:20
|
pupa.exceptions.UnresolvedIdError: cannot resolve pseudo id to Post: ~{"label": "South Huron (seat 2)", "organization__class…
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": "South Huron (seat 2)", "organization__classification": "legislature", "role": "Councillor"}
|
|
C
|
ca_on_king
|
2020-04-01 04:29:54
|
2020-04-01 04:29:54
|
|
|
C
|
ca_on_kingston
|
2020-04-01 04:15:10
|
2020-04-01 04:15:10
|
|
|
C
|
ca_on_kitchener
|
2020-04-01 04:23:47
|
2020-04-01 04:23:47
|
|
|
C
|
ca_on_lambton
|
2020-04-01 04:27:34
|
2020-04-01 04:27:34
|
|
|
C
|
ca_on_lincoln
|
2020-04-01 04:34:50
|
2020-04-01 04:34:50
|
|
|
C
|
ca_on_london
|
2020-04-01 04:35:32
|
2020-04-01 04:35:32
|
|
D>
04:23:43 WARNING pupa: could not save RunPlan, no successful runs of ocd-jurisdiction/country:ca/csd:3519036/legislature yet
|
ca_on_markham
|
|
2020-04-01 04:23:43
|
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>
|
ca_on_milton
|
2019-11-20 04:20:40
|
2020-04-01 14:54:48
|
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
|
2020-04-01 16:17:02
|
2020-04-01 16:17:02
|
|
|
C
|
ca_on_newmarket
|
2020-04-01 04:13:23
|
2020-04-01 04:13:23
|
|
|
C
|
ca_on_niagara
|
2020-04-01 04:15:27
|
2020-04-01 04:15:27
|
|
|
C
|
ca_on_niagara_on_the_lake
|
2020-04-01 04:13:18
|
2020-04-01 04:13:18
|
|
|
C
|
ca_on_north_dumfries
|
2020-04-01 04:24:27
|
2020-04-01 04:24:27
|
|
|
C
|
ca_on_oakville
|
2020-04-01 04:15:25
|
2020-04-01 04:15:25
|
|
|
D>
|
ca_on_oshawa
|
2020-01-15 04:59:21
|
2020-04-01 04:15:06
|
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#5d303c24322f1d322e353c2a3c733e3c">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>
|
ca_on_ottawa
|
2019-09-24 04:29:39
|
2020-04-01 04:13:17
|
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
|
2020-04-01 04:01:07
|
2020-04-01 04:01:07
|
|
|
C
|
ca_on_pickering
|
2020-04-01 04:19:31
|
2020-04-01 04:19:31
|
|
|
C
|
ca_on_richmond_hill
|
2020-04-01 04:24:43
|
2020-04-01 04:24:43
|
|
|
C
|
ca_on_school_boards_english_public
|
2020-04-01 04:23:32
|
2020-04-01 04:23:35
|
|
|
C
|
ca_on_st_catharines
|
2020-04-01 04:13:28
|
2020-04-01 04:13:28
|
|
D>
04:18:13 WARNING pupa: could not save RunPlan, no successful runs of ocd-jurisdiction/country:ca/csd:3558004/legislature yet
|
ca_on_thunder_bay
|
|
2020-04-01 04:18:13
|
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
|
2020-04-01 04:20:00
|
2020-04-01 04:20:00
|
|
|
C
|
ca_on_uxbridge
|
2020-04-01 04:24:21
|
2020-04-01 04:24:21
|
|
|
C
|
ca_on_vaughan
|
2020-04-01 13:32:29
|
2020-04-01 13:32:29
|
|
|
C
|
ca_on_waterloo
|
2020-04-01 04:41:58
|
2020-04-01 04:41:58
|
|
|
C
|
ca_on_waterloo_region
|
2020-04-01 04:19:09
|
2020-04-01 04:19:09
|
|
|
C
|
ca_on_welland
|
2020-04-01 04:14:01
|
2020-04-01 04:14:01
|
|
|
C
|
ca_on_wellesley
|
2020-04-01 04:35:38
|
2020-04-01 04:35:38
|
|
|
C
|
ca_on_whitby
|
2020-04-01 04:13:53
|
2020-04-01 04:13:53
|
|
|
C
|
ca_on_whitchurch_stouffville
|
2020-04-01 04:15:03
|
2020-04-01 04:15:03
|
|
|
C
|
ca_on_windsor
|
2020-04-01 04:13:25
|
2020-04-01 04:13:25
|
|
D>
04:30:12 WARNING pupa: could not save RunPlan, no successful runs of ocd-jurisdiction/country:ca/province:pe/legislature yet
|
ca_pe
|
|
2020-04-01 04:30:12
|
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
|
2020-04-01 04:26:17
|
2020-04-01 04:26:17
|
|
|
C
|
ca_qc
|
2020-04-01 04:34:46
|
2020-04-01 04:34:47
|
|
|
C
|
ca_qc_beaconsfield
|
2020-04-01 04:13:57
|
2020-04-01 04:13:57
|
|
D>
04:14:03 WARNING pupa: could not save RunPlan, no successful runs of ocd-jurisdiction/country:ca/csd:2458007/legislature yet
|
ca_qc_brossard
|
|
2020-04-01 04:14:03
|
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
|
2020-04-01 04:24:24
|
2020-04-01 04:24:24
|
|
|
C
|
ca_qc_dollard_des_ormeaux
|
2020-04-01 04:20:59
|
2020-04-01 04:20:59
|
|
|
C
|
ca_qc_dorval
|
2020-04-01 04:01:24
|
2020-04-01 04:01:24
|
|
|
D>
|
ca_qc_gatineau
|
2020-03-16 04:32:00
|
2020-04-01 22:28:48
|
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
|
2020-04-01 04:15:08
|
2020-04-01 04:15:08
|
|
|
C
|
ca_qc_laval
|
2020-04-01 21:48:06
|
2020-04-01 21:48:06
|
|
|
C
|
ca_qc_levis
|
2020-04-01 04:28:09
|
2020-04-01 04:28:09
|
|
|
D>
|
ca_qc_longueuil
|
2020-02-19 04:39:10
|
2020-04-01 04:27:49
|
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>
04:15:51 WARNING scrapelib: got Exceeded 30 redirects. sleeping for 10 seconds before retry
04:16:24 WARNING scrapelib: got Exceeded 30 redirects. sleeping for 20 seconds before retry
04:17:07 WARNING scrapelib: got Exceeded 30 redirects. sleeping for 40 seconds before retry
04:18:12 WARNING pupa: could not save RunPlan, no successful runs of ocd-jurisdiction/country:ca/csd:2467045/legislature yet
|
ca_qc_mercier
|
|
2020-04-01 04:18:12
|
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>
23:33:16 WARNING pupa: could not save RunPlan, no successful runs of ocd-jurisdiction/country:ca/csd:2466023/legislature yet
|
ca_qc_montreal
|
|
2020-04-01 23:33:16
|
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
|
2020-04-01 04:41:58
|
2020-04-01 04:41:58
|
|
|
C
|
ca_qc_pointe_claire
|
2020-04-01 04:14:00
|
2020-04-01 04:14:00
|
|
|
C
|
ca_qc_quebec
|
2020-04-01 15:32:25
|
2020-04-01 15:32:25
|
|
|
C
|
ca_qc_saguenay
|
2020-04-01 04:01:13
|
2020-04-01 04:01:13
|
|
|
C
|
ca_qc_sainte_anne_de_bellevue
|
2020-04-01 04:29:49
|
2020-04-01 04:29:49
|
|
|
C
|
ca_qc_saint_jean_sur_richelieu
|
2020-04-01 23:07:03
|
2020-04-01 23:07:03
|
|
|
C
|
ca_qc_saint_jerome
|
2020-04-01 04:20:02
|
2020-04-01 04:20:02
|
|
|
C
|
ca_qc_senneville
|
2020-04-01 04:19:33
|
2020-04-01 04:19:33
|
|
|
D>
|
ca_qc_sherbrooke
|
2020-03-03 04:31:40
|
2020-04-01 04:41:32
|
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_sherbrooke/people.py", line 11, in scrape
assert len(councillors), 'No councillors found'
AssertionError: No councillors found
|
D>
06:23:04 WARNING pupa: could not save RunPlan, no successful runs of ocd-jurisdiction/country:ca/csd:2464008/legislature yet
|
ca_qc_terrebonne
|
|
2020-04-01 06:23:04
|
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
|
2020-04-01 04:19:07
|
2020-04-01 04:19:07
|
|
|
C
|
ca_qc_westmount
|
2020-04-01 04:19:30
|
2020-04-01 04:19:30
|
|
D>
04:35:40 WARNING pupa: validation of Membership 3e0d71fc-73d2-11ea-a9c6-3e171211d7d0 failed: 1 validation errors:
Value '307' for field '' does not match regular expression '\A1 \d{3} \d{3}-\d{4}(?: x\d+)?\Z'
04:35:40 WARNING pupa: could not save RunPlan, no successful runs of ocd-jurisdiction/country:ca/province:sk/legislature yet
|
ca_sk
|
|
2020-04-01 04:35:40
|
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 3e0d71fc-73d2-11ea-a9c6-3e171211d7d0 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
|
2020-04-01 12:01:19
|
2020-04-01 12:01:19
|
|
|
C
|
ca_sk_saskatoon
|
2020-04-01 04:41:51
|
2020-04-01 04:41:51
|
|