|
C
|
ca
|
2020-01-25 04:25:00
|
2020-01-25 04:25:01
|
|
D>
04:40:49 WARNING pupa: validation of Membership dc1edb0e-3f2c-11ea-af90-52ea5878bcea 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
|
2020-01-25 04:40:49
|
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 dc1edb0e-3f2c-11ea-af90-52ea5878bcea failed: 2 validation errors:
Value '<a href=tel:587.493.2050">587.493.2050</a>"' for field '' does not match regular expression '\A1 \d{3} \d{3}-\d{4}(?: x\d+)?\Z'
Value '<a href=tel:587.493.9562">587.493.9562</a>"' for field '' does not match regular expression '\A1 \d{3} \d{3}-\d{4}(?: x\d+)?\Z'
|
|
D>
|
ca_ab_calgary
|
2019-12-10 04:05:11
|
2020-01-25 04:08:38
|
AssertionError: No councillors found
Traceback (most recent call last):
File "/app/reports/utils.py", line 71, in scrape_people
report.report = subcommand.handle(args, other)
File "/app/.heroku/src/pupa/pupa/cli/commands/update.py", line 260, in handle
return self.do_handle(args, other, juris)
File "/app/.heroku/src/pupa/pupa/cli/commands/update.py", line 305, in do_handle
report['scrape'] = self.do_scrape(juris, args, scrapers)
File "/app/.heroku/src/pupa/pupa/cli/commands/update.py", line 173, in do_scrape
report[scraper_name] = scraper.do_scrape(**scrape_args)
File "/app/.heroku/src/pupa/pupa/scrape/base.py", line 99, in do_scrape
for obj in self.scrape(**kwargs) or []:
File "/app/scrapers/ca_ab_calgary/people.py", line 12, in scrape
assert len(councillors), 'No councillors found'
AssertionError: No councillors found
|
D>
04:07:32 WARNING pupa: could not save RunPlan, no successful runs of ocd-jurisdiction/country:ca/province:ab/executive yet
|
ca_ab_candidates
|
|
2020-01-25 04:07:32
|
pupa.exceptions.UnresolvedIdError: cannot resolve pseudo id to Post: ~{"label": "West Yellowhead", "organization__classifi...
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": "West Yellowhead", "organization__classification": "executive", "role": "MLA"}
|
|
C
|
ca_ab_edmonton
|
2020-01-25 04:11:51
|
2020-01-25 04:11:51
|
|
D>
04:30:25 WARNING scrapelib: sleeping for 10 seconds before retry
04:30:35 WARNING scrapelib: sleeping for 20 seconds before retry
04:30:55 WARNING scrapelib: sleeping for 40 seconds before retry
04:31:35 WARNING pupa: could not save RunPlan, no successful runs of ocd-jurisdiction/country:ca/csd:4819012/legislature yet
|
ca_ab_grande_prairie
|
|
2020-01-25 04:31:35
|
scrapelib.HTTPError: 403 while retrieving https://data.cityofgp.com/api/views/kxpv-69sa/rows.csv?accessType=DOWNLOAD
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 217, in csv_reader
response = self.get(url, **kwargs)
File "/app/scrapers/utils.py", line 174, in get
return super(CanadianScraper, self).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: 403 while retrieving https://data.cityofgp.com/api/views/kxpv-69sa/rows.csv?accessType=DOWNLOAD
|
|
C
|
ca_ab_grande_prairie_county_no_1
|
2020-01-25 04:04:36
|
2020-01-25 04:04:36
|
|
|
C
|
ca_ab_lethbridge
|
2020-01-25 04:04:27
|
2020-01-25 04:04:27
|
|
|
C
|
ca_ab_strathcona_county
|
2020-01-25 04:34:39
|
2020-01-25 04:34:39
|
|
|
C
|
ca_ab_wood_buffalo
|
2020-01-25 04:12:10
|
2020-01-25 04:12:10
|
|
|
C
|
ca_bc
|
2020-01-25 04:10:28
|
2020-01-25 04:10:28
|
|
|
C
|
ca_bc_abbotsford
|
2020-01-25 04:40:29
|
2020-01-25 04:40:29
|
|
|
C
|
ca_bc_burnaby
|
2020-01-25 04:31:45
|
2020-01-25 04:31:45
|
|
|
C
|
ca_bc_coquitlam
|
2020-01-25 04:12:21
|
2020-01-25 04:12:21
|
|
|
C
|
ca_bc_kelowna
|
2020-01-25 04:04:34
|
2020-01-25 04:04:34
|
|
|
C
|
ca_bc_langley
|
2020-01-25 04:31:52
|
2020-01-25 04:31:52
|
|
|
D>
|
ca_bc_municipalities
|
2019-12-20 04:06:35
|
2020-01-25 04:40:27
|
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': 'Councillor', 'person_id': 'ocd-person/bfc1c215-6cdb-48b8-8667-5fd6bfa329a5', 'person_name': 'David Croal', 'organization_id': 'ocd-organization/ee0f670a-664a-418a-a53c-c6c88e219aee', 'post_id': 'ocd-post/ae268f01-ce80-43f5-89ce-6075c954cc86', 'on_behalf_of_id': None, 'start_date': '', 'end_date': '', 'extras': {'boundary_url': '/boundaries/census-subdivisions/5929005/'}} (already imported as David Croal in Gibsons Town Council (Councillor))
obj1 sources: []
obj2 sources: []
|
|
C
|
ca_bc_municipalities_candidates
|
2020-01-25 04:08:24
|
2020-01-25 04:08:26
|
|
|
C
|
ca_bc_new_westminster
|
2020-01-25 04:25:30
|
2020-01-25 04:25:30
|
|
|
C
|
ca_bc_richmond
|
2020-01-25 04:32:09
|
2020-01-25 04:32:09
|
|
|
D>
|
ca_bc_saanich
|
2019-10-03 04:03:10
|
2020-01-25 04:01:58
|
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
|
2020-01-25 04:04:14
|
2020-01-25 04:04:14
|
|
|
C
|
ca_bc_vancouver
|
2020-01-25 04:04:33
|
2020-01-25 04:04:33
|
|
|
C
|
ca_bc_victoria
|
2020-01-25 04:30:06
|
2020-01-25 04:30:06
|
|
|
C
|
ca_candidates
|
2020-01-25 04:30:01
|
2020-01-25 04:30:01
|
|
D>
04:30:21 WARNING pupa: could not save RunPlan, no successful runs of ocd-jurisdiction/country:ca/province:mb/legislature yet
|
ca_mb
|
|
2020-01-25 04:30:21
|
KeyError: 'IND LIB'
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_mb/people.py", line 31, in scrape
party = get_party(partycell.text)
File "/app/scrapers/ca_mb/people.py", line 14, in get_party
}[abbreviation]
KeyError: 'IND LIB'
|
D>
04:04:20 WARNING pupa: could not save RunPlan, no successful runs of ocd-jurisdiction/country:ca/province:mb/executive yet
|
ca_mb_candidates
|
|
2020-01-25 04:04:20
|
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/3997816c-42c3-47b1-a891-a9f7c749850c', 'person_name': 'James Beddome', '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 James Beddome in Green Party (member))
obj1 sources: []
obj2 sources: []
|
D>
04:25:27 WARNING pupa: could not save RunPlan, no successful runs of ocd-jurisdiction/country:ca/csd:4611040/legislature yet
|
ca_mb_winnipeg
|
|
2020-01-25 04:25:27
|
pupa.exceptions.UnresolvedIdError: cannot resolve pseudo id to Post: ~{"label": "Charleswood\u2014Tuxedo\u2014Westwood", "...
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": "Charleswood\u2014Tuxedo\u2014Westwood", "organization__classification": "legislature", "role": "Councillor"}
|
|
C
|
ca_nb
|
2020-01-25 04:11:18
|
2020-01-25 04:11:18
|
|
|
C
|
ca_nb_fredericton
|
2020-01-25 04:40:43
|
2020-01-25 04:40:43
|
|
|
C
|
ca_nb_moncton
|
2020-01-25 04:08:29
|
2020-01-25 04:08:29
|
|
|
C
|
ca_nb_municipalities
|
2020-01-25 04:34:37
|
2020-01-25 04:34:38
|
|
|
C
|
ca_nb_saint_john
|
2020-01-25 04:32:14
|
2020-01-25 04:32:14
|
|
|
C
|
ca_nl
|
2020-01-25 04:13:05
|
2020-01-25 04:13:06
|
|
|
C
|
ca_nl_st_john_s
|
2020-01-25 04:30:04
|
2020-01-25 04:30:04
|
|
D>
04:04:05 WARNING pupa: could not save RunPlan, no successful runs of ocd-jurisdiction/country:ca/province:ns/legislature yet
|
ca_ns
|
|
2020-01-25 04:04:05
|
KeyError: 'Independent'
Traceback (most recent call last):
File "/app/reports/utils.py", line 71, in scrape_people
report.report = subcommand.handle(args, other)
File "/app/.heroku/src/pupa/pupa/cli/commands/update.py", line 260, in handle
return self.do_handle(args, other, juris)
File "/app/.heroku/src/pupa/pupa/cli/commands/update.py", line 305, in do_handle
report['scrape'] = self.do_scrape(juris, args, scrapers)
File "/app/.heroku/src/pupa/pupa/cli/commands/update.py", line 173, in do_scrape
report[scraper_name] = scraper.do_scrape(**scrape_args)
File "/app/.heroku/src/pupa/pupa/scrape/base.py", line 99, in do_scrape
for obj in self.scrape(**kwargs) or []:
File "/app/scrapers/ca_ns/people.py", line 28, in scrape
party = self.PARTIES[party]
KeyError: 'Independent'
|
|
C
|
ca_ns_cape_breton
|
2020-01-25 04:02:12
|
2020-01-25 04:02:12
|
|
|
C
|
ca_ns_halifax
|
2020-01-25 04:11:37
|
2020-01-25 04:11:37
|
|
|
D>
|
ca_on
|
2019-11-01 04:10:28
|
2020-01-25 04:30:22
|
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
|
D>
04:40:50 WARNING pupa: could not save RunPlan, no successful runs of ocd-jurisdiction/country:ca/csd:3518005/legislature yet
|
ca_on_ajax
|
|
2020-01-25 04:40:50
|
scrapelib.HTTPError: 404 while retrieving https://www.ajax.ca/en/insidetownhall/mayorcouncillors.asp
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_ajax/people.py", line 10, in scrape
page = self.lxmlize(COUNCIL_PAGE)
File "/app/scrapers/utils.py", line 182, in lxmlize
response = self.get(url, cookies=cookies)
File "/app/scrapers/utils.py", line 174, in get
return super(CanadianScraper, self).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.ajax.ca/en/insidetownhall/mayorcouncillors.asp
|
|
C
|
ca_on_belleville
|
2020-01-25 04:13:29
|
2020-01-25 04:13:29
|
|
|
C
|
ca_on_brampton
|
2020-01-25 04:13:08
|
2020-01-25 04:13:08
|
|
|
C
|
ca_on_brantford
|
2020-01-25 04:04:25
|
2020-01-25 04:04:25
|
|
|
C
|
ca_on_burlington
|
2020-01-25 04:30:02
|
2020-01-25 04:30:02
|
|
|
C
|
ca_on_caledon
|
2020-01-25 04:07:42
|
2020-01-25 04:07:42
|
|
|
C
|
ca_on_cambridge
|
2020-01-25 04:34:40
|
2020-01-25 04:34:40
|
|
|
C
|
ca_on_chatham_kent
|
2020-01-25 04:08:53
|
2020-01-25 04:08:53
|
|
|
C
|
ca_on_fort_erie
|
2020-01-25 04:01:50
|
2020-01-25 04:01:50
|
|
|
C
|
ca_on_georgina
|
2020-01-25 04:04:24
|
2020-01-25 04:04:24
|
|
|
C
|
ca_on_greater_sudbury
|
2020-01-25 04:07:28
|
2020-01-25 04:07:28
|
|
|
C
|
ca_on_grimsby
|
2020-01-25 04:30:07
|
2020-01-25 04:30:07
|
|
|
C
|
ca_on_guelph
|
2020-01-25 04:30:25
|
2020-01-25 04:30:25
|
|
D>
04:07:47 WARNING pupa: could not save RunPlan, no successful runs of ocd-jurisdiction/country:ca/csd:3528018/legislature yet
|
ca_on_haldimand_county
|
|
2020-01-25 04:07:47
|
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
|
2020-01-25 04:31:47
|
Exception: No email pattern in ["javascript:void(location.href='mailto:'+String.fromCharCode(109,97,121,111,114,64,104,97,...
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 136, 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>
04:25:29 WARNING pupa: could not save RunPlan, no successful runs of ocd-jurisdiction/country:ca/cd:3540/legislature yet
|
ca_on_huron
|
|
2020-01-25 04:25:29
|
pupa.exceptions.UnresolvedIdError: cannot resolve pseudo id to Post: ~{"label": "North Huron (seat 1)", "organization__cla...
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": "North Huron (seat 1)", "organization__classification": "legislature", "role": "Councillor"}
|
|
C
|
ca_on_king
|
2020-01-25 04:11:54
|
2020-01-25 04:11:54
|
|
|
C
|
ca_on_kingston
|
2020-01-25 04:12:11
|
2020-01-25 04:12:11
|
|
|
C
|
ca_on_kitchener
|
2020-01-25 04:08:27
|
2020-01-25 04:08:27
|
|
|
C
|
ca_on_lambton
|
2020-01-25 04:08:55
|
2020-01-25 04:08:55
|
|
|
C
|
ca_on_lincoln
|
2020-01-25 04:01:52
|
2020-01-25 04:01:52
|
|
|
C
|
ca_on_london
|
2020-01-25 04:29:49
|
2020-01-25 04:29:49
|
|
D>
04:02:32 WARNING pupa: could not save RunPlan, no successful runs of ocd-jurisdiction/country:ca/csd:3519036/legislature yet
|
ca_on_markham
|
|
2020-01-25 04:02:32
|
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
|
2020-01-25 04:25:25
|
AssertionError: No councillors found
Traceback (most recent call last):
File "/app/reports/utils.py", line 71, in scrape_people
report.report = subcommand.handle(args, other)
File "/app/.heroku/src/pupa/pupa/cli/commands/update.py", line 260, in handle
return self.do_handle(args, other, juris)
File "/app/.heroku/src/pupa/pupa/cli/commands/update.py", line 305, in do_handle
report['scrape'] = self.do_scrape(juris, args, scrapers)
File "/app/.heroku/src/pupa/pupa/cli/commands/update.py", line 173, in do_scrape
report[scraper_name] = scraper.do_scrape(**scrape_args)
File "/app/.heroku/src/pupa/pupa/scrape/base.py", line 99, in do_scrape
for obj in self.scrape(**kwargs) or []:
File "/app/scrapers/ca_on_milton/people.py", line 13, in scrape
assert len(councillors), 'No councillors found'
AssertionError: No councillors found
|
D>
04:13:21 WARNING pupa: could not save RunPlan, no successful runs of ocd-jurisdiction/country:ca/csd:3521005/legislature yet
|
ca_on_mississauga
|
|
2020-01-25 04:13:21
|
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_mississauga/people.py", line 18, in scrape
yield self.mayor_data(MAYOR_PAGE)
File "/app/scrapers/ca_on_mississauga/people.py", line 41, in mayor_data
photo = page.xpath('//img[contains(@src, "mayor")]/@src')[0]
IndexError: list index out of range
|
|
C
|
ca_on_newmarket
|
2020-01-25 04:04:35
|
2020-01-25 04:04:35
|
|
|
C
|
ca_on_niagara
|
2020-01-25 04:01:51
|
2020-01-25 04:01:51
|
|
|
C
|
ca_on_niagara_on_the_lake
|
2020-01-25 04:07:45
|
2020-01-25 04:07:45
|
|
|
C
|
ca_on_north_dumfries
|
2020-01-25 04:13:06
|
2020-01-25 04:13:06
|
|
|
C
|
ca_on_oakville
|
2020-01-25 04:32:12
|
2020-01-25 04:32:12
|
|
|
D>
|
ca_on_oshawa
|
2020-01-15 04:59:21
|
2020-01-25 04:32:13
|
Exception: No email node in b'<td>\n<p class="DirectoryTitle">City of Oshawa<br/>Mayor<br/>Dan Carter</p>\n<p class="Stand...
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 138, 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#b6dbd7cfd9c4f6d9c5ded7c1d798d5d7">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
|
2020-01-25 04:07:48
|
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 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
|
2020-01-25 04:08:33
|
2020-01-25 04:08:33
|
|
|
C
|
ca_on_pickering
|
2020-01-25 04:32:11
|
2020-01-25 04:32:11
|
|
|
C
|
ca_on_richmond_hill
|
2020-01-25 04:01:36
|
2020-01-25 04:01:36
|
|
|
C
|
ca_on_school_boards_english_public
|
2020-01-25 04:34:56
|
2020-01-25 04:34:57
|
|
|
C
|
ca_on_st_catharines
|
2020-01-25 04:01:57
|
2020-01-25 04:01:57
|
|
D>
04:25:24 WARNING pupa: could not save RunPlan, no successful runs of ocd-jurisdiction/country:ca/csd:3558004/legislature yet
|
ca_on_thunder_bay
|
|
2020-01-25 04:25:24
|
scrapelib.HTTPError: 404 while retrieving https://www.thunderbay.ca/Common/PageNotFound.aspx?aspxerrorpath=/en/city-hall/m...
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 182, in lxmlize
response = self.get(url, cookies=cookies)
File "/app/scrapers/utils.py", line 174, in get
return super(CanadianScraper, self).get(*args, verify=SSL_VERIFY, **kwargs)
File "/app/.heroku/python/lib/python3.6/site-packages/requests/sessions.py", line 537, in get
return self.request('GET', url, **kwargs)
File "/app/.heroku/python/lib/python3.6/site-packages/scrapelib/__init__.py", line 292, in request
raise HTTPError(resp)
scrapelib.HTTPError: 404 while retrieving https://www.thunderbay.ca/Common/PageNotFound.aspx?aspxerrorpath=/en/city-hall/mayor-and-council.aspx
|
|
D>
|
ca_on_toronto
|
2019-10-29 04:37:49
|
2020-01-25 04:02:34
|
scrapelib.HTTPError: 404 while retrieving https://www.toronto.ca/ext/open_data/catalog/data_set_files/Councillor_Contact_D...
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 344, in scrape
binary = BytesIO(self.get(self.csv_url).content)
File "/app/scrapers/utils.py", line 174, in get
return super(CanadianScraper, self).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.toronto.ca/ext/open_data/catalog/data_set_files/Councillor_Contact_Data_December_2018.xlsx
|
|
C
|
ca_on_toronto_candidates
|
2020-01-25 04:04:30
|
2020-01-25 04:04:30
|
|
|
C
|
ca_on_uxbridge
|
2020-01-25 04:30:23
|
2020-01-25 04:30:23
|
|
|
C
|
ca_on_vaughan
|
2020-01-25 04:32:25
|
2020-01-25 04:32:25
|
|
|
C
|
ca_on_waterloo
|
2020-01-25 04:32:11
|
2020-01-25 04:32:11
|
|
|
C
|
ca_on_waterloo_region
|
2020-01-25 04:25:29
|
2020-01-25 04:25:29
|
|
|
C
|
ca_on_welland
|
2020-01-25 04:31:51
|
2020-01-25 04:31:51
|
|
|
C
|
ca_on_wellesley
|
2020-01-25 04:11:55
|
2020-01-25 04:11:55
|
|
|
C
|
ca_on_whitby
|
2020-01-25 04:04:46
|
2020-01-25 04:04:46
|
|
|
C
|
ca_on_whitchurch_stouffville
|
2020-01-25 04:13:30
|
2020-01-25 04:13:30
|
|
|
C
|
ca_on_windsor
|
2020-01-25 04:25:22
|
2020-01-25 04:25:22
|
|
D>
04:31:53 WARNING pupa: could not save RunPlan, no successful runs of ocd-jurisdiction/country:ca/province:pe/legislature yet
|
ca_pe
|
|
2020-01-25 04:31:53
|
scrapelib.HTTPError: 404 while retrieving https://www.assembly.pe.ca:443/current-members
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 10, in scrape
page = self.lxmlize(COUNCIL_PAGE)
File "/app/scrapers/utils.py", line 182, in lxmlize
response = self.get(url, cookies=cookies)
File "/app/scrapers/utils.py", line 174, in get
return super(CanadianScraper, self).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.assembly.pe.ca:443/current-members
|
D>
04:32:27 WARNING pupa: validation of CanadianPerson b139dba6-3f2b-11ea-af90-52ea5878bcea failed: 1 validation errors:
Value 'Jason Coady - Councillor Ward 8' 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_pe_charlottetown
|
2020-01-13 04:44:26
|
2020-01-25 04:32:27
|
Value 'Jason Coady - Councillor Ward 8' for field '<obj>.name' does not match regular expression 'regex.Regex('\\A(?!(?:Ch...
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 'Jason Coady - Councillor Ward 8' 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 b139dba6-3f2b-11ea-af90-52ea5878bcea failed: 1 validation errors:
Value 'Jason Coady - Councillor Ward 8' 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_qc
|
2020-01-25 04:29:47
|
2020-01-25 04:29:47
|
|
|
C
|
ca_qc_beaconsfield
|
2020-01-25 04:01:49
|
2020-01-25 04:01:49
|
|
D>
04:34:58 WARNING pupa: could not save RunPlan, no successful runs of ocd-jurisdiction/country:ca/csd:2458007/legislature yet
|
ca_qc_brossard
|
|
2020-01-25 04:34:58
|
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
|
D>
04:13:31 WARNING pupa: could not save RunPlan, no successful runs of ocd-jurisdiction/country:ca/csd:2466058/legislature yet
|
ca_qc_cote_saint_luc
|
|
2020-01-25 04:13:31
|
scrapelib.HTTPError: 404 while retrieving https://www.cotesaintluc.org/Administration
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_cote_saint_luc/people.py", line 12, in scrape
page = self.lxmlize(COUNCIL_PAGE, user_agent=CUSTOM_USER_AGENT)
File "/app/scrapers/utils.py", line 182, in lxmlize
response = self.get(url, cookies=cookies)
File "/app/scrapers/utils.py", line 174, in get
return super(CanadianScraper, self).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.cotesaintluc.org/Administration
|
|
C
|
ca_qc_dollard_des_ormeaux
|
2020-01-25 04:25:28
|
2020-01-25 04:25:28
|
|
|
C
|
ca_qc_dorval
|
2020-01-25 04:12:24
|
2020-01-25 04:12:24
|
|
D>
04:08:32 WARNING pupa: could not save RunPlan, no successful runs of ocd-jurisdiction/country:ca/csd:2481017/legislature yet
|
ca_qc_gatineau
|
|
2020-01-25 04:08:32
|
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
|
2020-01-25 04:01:47
|
2020-01-25 04:01:47
|
|
D>
04:31:58 WARNING pupa: validation of CanadianPerson a00ec0b2-3f2b-11ea-af90-52ea5878bcea failed: 1 validation errors:
Value ' ' for field '<obj>.image' does not match regular expression '\A(?:(?:ftp|https?)://|\Z)'
04:31:58 WARNING pupa: could not save RunPlan, no successful runs of ocd-jurisdiction/country:ca/csd:2465005/legislature yet
|
ca_qc_laval
|
|
2020-01-25 04:31:58
|
Value ' ' for field '<obj>.image' does not match regular expression '\A(?:(?:ftp|https?)://|\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 ' ' for field '<obj>.image' does not match regular expression '\A(?:(?:ftp|https?)://|\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 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 a00ec0b2-3f2b-11ea-af90-52ea5878bcea failed: 1 validation errors:
Value ' ' for field '<obj>.image' does not match regular expression '\A(?:(?:ftp|https?)://|\Z)'
|
|
C
|
ca_qc_levis
|
2020-01-25 04:01:56
|
2020-01-25 04:01:56
|
|
|
C
|
ca_qc_longueuil
|
2020-01-25 04:25:20
|
2020-01-25 04:25:20
|
|
D>
04:05:10 WARNING scrapelib: got Exceeded 30 redirects. sleeping for 10 seconds before retry
04:05:40 WARNING scrapelib: got Exceeded 30 redirects. sleeping for 20 seconds before retry
04:06:24 WARNING scrapelib: got Exceeded 30 redirects. sleeping for 40 seconds before retry
04:07:26 WARNING pupa: could not save RunPlan, no successful runs of ocd-jurisdiction/country:ca/csd:2467045/legislature yet
|
ca_qc_mercier
|
|
2020-01-25 04:07:26
|
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 182, in lxmlize
response = self.get(url, cookies=cookies)
File "/app/scrapers/utils.py", line 174, in get
return super(CanadianScraper, self).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>
04:13:26 WARNING pupa: could not save RunPlan, no successful runs of ocd-jurisdiction/country:ca/csd:2466023/legislature yet
|
ca_qc_montreal
|
|
2020-01-25 04:13:26
|
pupa.exceptions.UnresolvedIdError: cannot resolve pseudo id to Post: ~{"label": "Jeanne-Mance", "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": "Jeanne-Mance", "organization__classification": "legislature", "role": "Maire suppl\u00e9ant d'arrondissement"}
|
|
D>
|
ca_qc_montreal_est
|
2019-10-23 04:19:33
|
2020-01-25 04:08:37
|
Exception: No email node in b'<table style="width: 100%;">\n<tbody>\n<tr>\n<td style="background-color: #ffffff; width: 50...
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_montreal_est/people.py", line 26, in scrape
p.add_contact('email', self.get_email(councillor))
File "/app/scrapers/utils.py", line 138, in get_email
raise Exception('No email node in {}'.format(etree.tostring(node)))
Exception: No email node in b'<table style="width: 100%;">\n<tbody>\n<tr>\n<td style="background-color: #ffffff; width: 50%;"><a href="https://ville.montreal-est.qc.ca/wp-content/uploads/2015/12/francoise_lachapelle_conseillere_montreal_est.jpg"><img class="size-full wp-image-3208 aligncenter" src="https://ville.montreal-est.qc.ca/wp-content/uploads/2019/10/Poste_vacant_conseiller_site_web_197x300.jpg" alt="Poste-vacant" width="230" height="293"/></a></td>\n<td style="background-color: #ffffff; text-align: right; width: 50%;"><a href="https://ville.montreal-est.qc.ca/wp-content/uploads/2015/12/districts1.jpg" target="_blank"><img class="2 wp-image-580 size-medium aligncenter" src="https://ville.montreal-est.qc.ca/wp-content/uploads/2015/12/districts1-250x380.jpg" alt="" width="197" height="300" srcset="https://ville.montreal-est.qc.ca/wp-content/uploads/2015/12/districts1.jpg 250w, https://ville.montreal-est.qc.ca/wp-content/uploads/2015/12/districts1-120x182.jpg 120w" sizes="(max-width: 197px) 100vw, 197px"/></a></td>\n</tr>\n<tr>\n<td style="background-color: #f5f5f5; width: 50%;">\n<h3 style="text-align: center;"><span style="color: #0064bc;">Alain Dion</span></h3>\n<p style="text-align: center;">\n</p></td>\n<td style="background-color: #f5f5f5; width: 50%;">\n<h3 style="text-align: center;"><span style="color: #0064bc;">Conseiller district # 1</span></h3>\n<p style="text-align: center;"><span style="color: #0064bc;">Cliquez sur l’image pour agrandir</span></p>\n</td>\n</tr>\n</tbody>\n</table>\n'
|
|
C
|
ca_qc_pointe_claire
|
2020-01-25 04:13:23
|
2020-01-25 04:13:23
|
|
|
C
|
ca_qc_quebec
|
2020-01-25 04:29:48
|
2020-01-25 04:29:48
|
|
|
C
|
ca_qc_saguenay
|
2020-01-25 04:31:58
|
2020-01-25 04:31:58
|
|
|
C
|
ca_qc_sainte_anne_de_bellevue
|
2020-01-25 04:31:48
|
2020-01-25 04:31:48
|
|
D>
04:07:27 WARNING pupa: could not save RunPlan, no successful runs of ocd-jurisdiction/country:ca/csd:2456083/legislature yet
|
ca_qc_saint_jean_sur_richelieu
|
|
2020-01-25 04:07:27
|
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_saint_jean_sur_richelieu/people.py", line 13, in scrape
yield self.scrape_mayor(councillors[0])
IndexError: list index out of range
|
|
D>
|
ca_qc_saint_jerome
|
2019-12-12 04:24:28
|
2020-01-25 04:31:49
|
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_saint_jerome/people.py", line 12, in scrape
assert len(councillors), 'No councillors found'
AssertionError: No councillors found
|
|
C
|
ca_qc_senneville
|
2020-01-25 04:07:44
|
2020-01-25 04:07:44
|
|
|
D>
|
ca_qc_sherbrooke
|
2020-01-09 04:29:18
|
2020-01-25 04:02:30
|
pupa.exceptions.UnresolvedIdError: cannot resolve pseudo id to Post: ~{"label": "Lac Magog", "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": "Lac Magog", "organization__classification": "legislature", "role": "Conseiller"}
|
D>
04:04:21 WARNING pupa: could not save RunPlan, no successful runs of ocd-jurisdiction/country:ca/csd:2464008/legislature yet
|
ca_qc_terrebonne
|
|
2020-01-25 04:04:21
|
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_terrebonne/people.py", line 13, in scrape
district = councillor_elem.xpath('.//div[@class="fiche__category"]/text()')[0]
IndexError: list index out of range
|
D>
04:25:21 WARNING pupa: could not save RunPlan, no successful runs of ocd-jurisdiction/country:ca/csd:2437067/legislature yet
|
ca_qc_trois_rivieres
|
|
2020-01-25 04:25:21
|
scrapelib.HTTPError: 404 while retrieving https://www.v3r.net/a-propos-de-la-ville/vie-democratique/mairie
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_trois_rivieres/people.py", line 14, in scrape
page = self.lxmlize(MAYOR_URL)
File "/app/scrapers/utils.py", line 182, in lxmlize
response = self.get(url, cookies=cookies)
File "/app/scrapers/utils.py", line 174, in get
return super(CanadianScraper, self).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.v3r.net/a-propos-de-la-ville/vie-democratique/mairie
|
|
C
|
ca_qc_westmount
|
2020-01-25 04:11:57
|
2020-01-25 04:11:57
|
|
D>
04:25:32 WARNING pupa: validation of Membership b974122e-3f2a-11ea-af90-52ea5878bcea failed: 1 validation errors:
Value '307' for field '' does not match regular expression '\A1 \d{3} \d{3}-\d{4}(?: x\d+)?\Z'
04:25:32 WARNING pupa: could not save RunPlan, no successful runs of ocd-jurisdiction/country:ca/province:sk/legislature yet
|
ca_sk
|
|
2020-01-25 04:25:32
|
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 b974122e-3f2a-11ea-af90-52ea5878bcea failed: 1 validation errors:
Value '307' for field '' does not match regular expression '\A1 \d{3} \d{3}-\d{4}(?: x\d+)?\Z'
|
D>
04:25:23 WARNING pupa: could not save RunPlan, no successful runs of ocd-jurisdiction/country:ca/csd:4706027/legislature yet
|
ca_sk_regina
|
|
2020-01-25 04:25:23
|
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_sk_regina/people.py", line 14, in scrape
assert len(councillors), 'No councillors found'
AssertionError: No councillors found
|
|
C
|
ca_sk_saskatoon
|
2020-01-25 04:31:50
|
2020-01-25 04:31:50
|
|