|
C
|
ca
|
2025-10-13 04:22:50
|
2025-10-13 04:22:50
|
|
|
C
|
ca_ab
|
2025-10-13 04:34:53
|
2025-10-13 04:34:53
|
|
|
C
|
ca_ab_calgary
|
2025-10-13 04:35:08
|
2025-10-13 04:35:08
|
|
|
C
|
ca_ab_edmonton
|
2025-10-13 04:00:55
|
2025-10-13 04:00:55
|
|
|
C
|
ca_ab_grande_prairie
|
2025-10-13 14:49:34
|
2025-10-13 14:49:34
|
|
|
D>
|
ca_ab_grande_prairie_county_no_1
|
2025-07-15 04:33:22
|
2025-10-13 04:30:22
|
scrapelib.HTTPError: 404 while retrieving https://www.countygp.ab.ca/en/county-government/council.aspx
Traceback (most recent call last):
File "/app/reports/utils.py", line 73, in scrape_people
report.report = subcommand.handle(args, other)
File "/app/.heroku/python/lib/python3.10/site-packages/pupa/cli/commands/update.py", line 260, in handle
return self.do_handle(args, other, juris)
File "/app/.heroku/python/lib/python3.10/site-packages/pupa/cli/commands/update.py", line 305, in do_handle
report['scrape'] = self.do_scrape(juris, args, scrapers)
File "/app/.heroku/python/lib/python3.10/site-packages/pupa/cli/commands/update.py", line 173, in do_scrape
report[scraper_name] = scraper.do_scrape(**scrape_args)
File "/app/.heroku/python/lib/python3.10/site-packages/pupa/scrape/base.py", line 99, in do_scrape
for obj in self.scrape(**kwargs) or []:
File "/app/scrapers/ca_ab_grande_prairie_county_no_1/people.py", line 9, in scrape
page = self.lxmlize(COUNCIL_PAGE)
File "/app/scrapers/utils.py", line 217, in lxmlize
response = self.get(url, cookies=cookies, verify=verify)
File "/app/scrapers/utils.py", line 198, in get
return super().get(*args, verify=kwargs.pop("verify", SSL_VERIFY), **kwargs)
File "/app/.heroku/python/lib/python3.10/site-packages/requests/sessions.py", line 602, in get
return self.request("GET", url, **kwargs)
File "/app/.heroku/python/lib/python3.10/site-packages/scrapelib/__init__.py", line 619, in request
raise HTTPError(resp)
scrapelib.HTTPError: 404 while retrieving https://www.countygp.ab.ca/en/county-government/council.aspx
|
|
C
|
ca_ab_lethbridge
|
2025-10-13 04:03:12
|
2025-10-13 04:03:12
|
|
|
C
|
ca_ab_strathcona_county
|
2025-10-13 04:40:07
|
2025-10-13 04:40:07
|
|
|
D>
|
ca_ab_wood_buffalo
|
2025-09-30 04:10:18
|
2025-10-13 05:30:46
|
scrapelib.HTTPError: 404 while retrieving https://www.rmwb.ca/en/mayor-council-and-administration/councillors.aspx
Traceback (most recent call last):
File "/app/reports/utils.py", line 73, in scrape_people
report.report = subcommand.handle(args, other)
File "/app/.heroku/python/lib/python3.10/site-packages/pupa/cli/commands/update.py", line 260, in handle
return self.do_handle(args, other, juris)
File "/app/.heroku/python/lib/python3.10/site-packages/pupa/cli/commands/update.py", line 305, in do_handle
report['scrape'] = self.do_scrape(juris, args, scrapers)
File "/app/.heroku/python/lib/python3.10/site-packages/pupa/cli/commands/update.py", line 173, in do_scrape
report[scraper_name] = scraper.do_scrape(**scrape_args)
File "/app/.heroku/python/lib/python3.10/site-packages/pupa/scrape/base.py", line 99, in do_scrape
for obj in self.scrape(**kwargs) or []:
File "/app/scrapers/ca_ab_wood_buffalo/people.py", line 27, in scrape
page = self.lxmlize(COUNCIL_PAGE)
File "/app/scrapers/utils.py", line 217, in lxmlize
response = self.get(url, cookies=cookies, verify=verify)
File "/app/scrapers/utils.py", line 198, in get
return super().get(*args, verify=kwargs.pop("verify", SSL_VERIFY), **kwargs)
File "/app/.heroku/python/lib/python3.10/site-packages/requests/sessions.py", line 602, in get
return self.request("GET", url, **kwargs)
File "/app/.heroku/python/lib/python3.10/site-packages/scrapelib/__init__.py", line 619, in request
raise HTTPError(resp)
scrapelib.HTTPError: 404 while retrieving https://www.rmwb.ca/en/mayor-council-and-administration/councillors.aspx
|
|
C
|
ca_bc
|
2025-10-13 09:50:35
|
2025-10-13 09:50:35
|
|
|
C
|
ca_bc_abbotsford
|
2025-10-13 04:04:26
|
2025-10-13 04:04:26
|
|
|
C
|
ca_bc_burnaby
|
2025-10-13 04:02:00
|
2025-10-13 04:02:00
|
|
|
C
|
ca_bc_coquitlam
|
2025-10-13 04:07:20
|
2025-10-13 04:07:20
|
|
|
C
|
ca_bc_kelowna
|
2025-10-13 04:36:07
|
2025-10-13 04:36:07
|
|
|
C
|
ca_bc_langley
|
2025-10-13 04:37:30
|
2025-10-13 04:37:30
|
|
|
C
|
ca_bc_langley_city
|
2025-10-13 04:03:14
|
2025-10-13 04:03:14
|
|
|
C
|
ca_bc_new_westminster
|
2025-10-13 04:10:14
|
2025-10-13 04:10:14
|
|
|
C
|
ca_bc_richmond
|
2025-10-13 04:02:14
|
2025-10-13 04:02:14
|
|
|
C
|
ca_bc_saanich
|
2025-10-13 04:03:40
|
2025-10-13 04:03:40
|
|
|
C
|
ca_bc_surrey
|
2025-10-13 04:07:09
|
2025-10-13 04:07:09
|
|
|
C
|
ca_bc_vancouver
|
2025-10-13 04:08:33
|
2025-10-13 04:08:33
|
|
|
C
|
ca_bc_victoria
|
2025-10-13 04:40:06
|
2025-10-13 04:40:06
|
|
D>
04:04:02 ERROR ca_candidates.people:
04:04:05 ERROR ca_candidates.people:
04:04:05 ERROR ca_candidates.people:
04:04:05 ERROR ca_candidates.people:
04:04:05 ERROR ca_candidates.people:
04:04:05 ERROR ca_candidates.people:
04:04:06 WARNING ca_candidates.people: 404 while retrieving https://www.greenparty.ca/en/candidates/page/2 (https://www.greenparty.ca/en/candidates/page/2)
04:04:07 WARNING ca_candidates.people: 404 while retrieving https://www.greenparty.ca/en/candidates/page/3 (https://www.greenparty.ca/en/candidates/page/3)
04:04:08 WARNING ca_candidates.people: 404 while retrieving https://www.greenparty.ca/en/candidates/page/4 (https://www.greenparty.ca/en/candidates/page/4)
04:04:09 WARNING ca_candidates.people: 404 while retrieving https://www.greenparty.ca/en/candidates/page/5 (https://www.greenparty.ca/en/candidates/page/5)
04:04:10 WARNING ca_candidates.people: 404 while retrieving https://www.greenparty.ca/en/candidates/page/6 (https://www.greenparty.ca/en/candidates/page/6)
04:04:11 WARNING ca_candidates.people: 404 while retrieving https://www.greenparty.ca/en/candidates/page/7 (https://www.greenparty.ca/en/candidates/page/7)
04:04:12 WARNING ca_candidates.people: 404 while retrieving https://www.greenparty.ca/en/candidates/page/8 (https://www.greenparty.ca/en/candidates/page/8)
04:04:13 WARNING ca_candidates.people: 404 while retrieving https://www.greenparty.ca/en/candidates/page/9 (https://www.greenparty.ca/en/candidates/page/9)
04:04:14 WARNING ca_candidates.people: 404 while retrieving https://www.greenparty.ca/en/candidates/page/10 (https://www.greenparty.ca/en/candidates/page/10)
04:04:15 WARNING ca_candidates.people: 404 while retrieving https://www.greenparty.ca/en/candidates/page/11 (https://www.greenparty.ca/en/candidates/page/11)
04:04:16 WARNING ca_candidates.people: 404 while retrieving https://www.greenparty.ca/en/candidates/page/12 (https://www.greenparty.ca/en/candidates/page/12)
04:04:17 WARNING ca_candidates.people: 404 while retrieving https://www.greenparty.ca/en/candidates/page/13 (https://www.greenparty.ca/en/candidates/page/13)
04:04:18 WARNING ca_candidates.people: 404 while retrieving https://www.greenparty.ca/en/candidates/page/14 (https://www.greenparty.ca/en/candidates/page/14)
04:04:19 WARNING ca_candidates.people: 404 while retrieving https://www.greenparty.ca/en/candidates/page/15 (https://www.greenparty.ca/en/candidates/page/15)
04:04:20 WARNING ca_candidates.people: 404 while retrieving https://www.greenparty.ca/en/candidates/page/16 (https://www.greenparty.ca/en/candidates/page/16)
04:04:21 WARNING ca_candidates.people: 404 while retrieving https://www.greenparty.ca/en/candidates/page/17 (https://www.greenparty.ca/en/candidates/page/17)
|
ca_candidates
|
2025-04-29 04:39:17
|
2025-10-13 04:04:23
|
scrapelib.HTTPError: 404 while retrieving https://www.conservative.ca/candidates
Traceback (most recent call last):
File "/app/reports/utils.py", line 73, in scrape_people
report.report = subcommand.handle(args, other)
File "/app/.heroku/python/lib/python3.10/site-packages/pupa/cli/commands/update.py", line 260, in handle
return self.do_handle(args, other, juris)
File "/app/.heroku/python/lib/python3.10/site-packages/pupa/cli/commands/update.py", line 305, in do_handle
report['scrape'] = self.do_scrape(juris, args, scrapers)
File "/app/.heroku/python/lib/python3.10/site-packages/pupa/cli/commands/update.py", line 173, in do_scrape
report[scraper_name] = scraper.do_scrape(**scrape_args)
File "/app/.heroku/python/lib/python3.10/site-packages/pupa/scrape/base.py", line 99, in do_scrape
for obj in self.scrape(**kwargs) or []:
File "/app/scrapers/ca_candidates/people.py", line 162, in scrape
for p in getattr(self, f"scrape_{party}")():
File "/app/scrapers/ca_candidates/people.py", line 425, in scrape_conservative
page = self.lxmlize(start_url)
File "/app/scrapers/utils.py", line 217, in lxmlize
response = self.get(url, cookies=cookies, verify=verify)
File "/app/scrapers/utils.py", line 198, in get
return super().get(*args, verify=kwargs.pop("verify", SSL_VERIFY), **kwargs)
File "/app/.heroku/python/lib/python3.10/site-packages/requests/sessions.py", line 602, in get
return self.request("GET", url, **kwargs)
File "/app/.heroku/python/lib/python3.10/site-packages/scrapelib/__init__.py", line 619, in request
raise HTTPError(resp)
scrapelib.HTTPError: 404 while retrieving https://www.conservative.ca/candidates
|
|
C
|
ca_mb
|
2025-10-13 04:37:07
|
2025-10-13 04:37:07
|
|
|
C
|
ca_mb_winnipeg
|
2025-10-13 04:03:18
|
2025-10-13 04:03:18
|
|
|
C
|
ca_nb
|
2025-10-13 04:06:57
|
2025-10-13 04:06:57
|
|
|
C
|
ca_nb_fredericton
|
2025-10-13 04:05:41
|
2025-10-13 04:05:41
|
|
|
C
|
ca_nb_moncton
|
2025-10-13 04:10:17
|
2025-10-13 04:10:17
|
|
|
C
|
ca_nb_saint_john
|
2025-10-13 04:02:40
|
2025-10-13 04:02:40
|
|
D>
04:37:20 WARNING pupa: validation of CanadianPerson 4e820948-a7ee-11f0-8c67-d662ad5d87e2 failed: 1 validation errors:
Value ' ' for field '<obj>.name' does not match regular expression 'regex.Regex('\\A(?!(?:Chair|Commissioner|Conseiller|Councillor|Deputy|Dr|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|St\\.|Van|Vander?|van|vanden)?\\p{Lu}\\p{Ll}+|\\p{Lu}\\p{Ll}+Anne?|Marie\\p{Lu}\\p{Ll}+|[ᐁᐃᐄᐅᐆᐊᐋᐯᐱᐲᐳᐴᐸᐹᑉᑊᑌᑎᑏᑐᑑᑕᑖᑦᑫᑭᑮᑯᑰᑲᑳᒃᒉᒋᒌᒍᒎᒐᒑᒡᒣᒥᒦᒧᒨᒪᒫᒻᓀᓂᓃᓄᓅᓇᓈᓐᓓᓕᓖᓗᓘᓚᓛᓪᓭᓯᓰᓱᓲᓴᓵᔅᔦᔨᔩᔪᔫᔭᔮᔾᕂᕆᕇᕈᕉᕋᕌᕐᕓᕕᕖᕗᕘᕙᕚᕝᕴᕵᕶᕷᕸᕹᕺᕻᕼᕿᖀᖁᖂᖃᖄᖅᖏᖐᖑᖒᖓᖔᖕᖖᖠᖡᖢᖣᖤᖥᖦᖨᖩᖪᖫᖬᖭᖮᖯᙯᙰᙱᙲᙳᙴᙵᙶ\U00011ab0\U00011ab1\U00011ab2\U00011ab3\U00011ab4\U00011ab5\U00011ab6\U00011ab7\U00011ab8\U00011ab9\U00011aba\U00011abb]+|Á\'a:líya|A\'aliya|Ch\'ng|Prud\'homme|Qwulti\'stunaat|Ya\'ara|D!ONNE|ChiefCalf|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|St\\.|Van|Vander?|van|vanden)?\\p{Lu}\\p{Ll}+|\\p{Lu}\\p{Ll}+Anne?|Marie\\p{Lu}\\p{Ll}+|[ᐁᐃᐄᐅᐆᐊᐋᐯᐱᐲᐳᐴᐸᐹᑉᑊᑌᑎᑏᑐᑑᑕᑖᑦᑫᑭᑮᑯᑰᑲᑳᒃᒉᒋᒌᒍᒎᒐᒑᒡᒣᒥᒦᒧᒨᒪᒫᒻᓀᓂᓃᓄᓅᓇᓈᓐᓓᓕᓖᓗᓘᓚᓛᓪᓭᓯᓰᓱᓲᓴᓵᔅᔦᔨᔩᔪᔫᔭᔮᔾᕂᕆᕇᕈᕉᕋᕌᕐᕓᕕᕖᕗᕘᕙᕚᕝᕴᕵᕶᕷᕸᕹᕺᕻᕼᕿᖀᖁᖂᖃᖄᖅᖏᖐᖑᖒᖓᖔᖕᖖᖠᖡᖢᖣᖤᖥᖦᖨᖩᖪᖫᖬᖭᖮᖯᙯᙰᙱᙲᙳᙴᙵᙶ\U00011ab0\U00011ab1\U00011ab2\U00011ab3\U00011ab4\U00011ab5\U00011ab6\U00011ab7\U00011ab8\U00011ab9\U00011aba\U00011abb]+|Á\'a:líya|A\'aliya|Ch\'ng|Prud\'homme|Qwulti\'stunaat|Ya\'ara|D!ONNE|ChiefCalf|IsaBelle)\\Z', flags=regex.V0)'
|
ca_nl
|
2025-09-15 04:33:31
|
2025-10-13 04:37:21
|
Value ' ' for field '<obj>.name' does not match regular expression 'regex.Regex('\\A(?!(?:Chair|Commissioner|Conseiller…
Traceback (most recent call last):
File "/app/.heroku/python/lib/python3.10/site-packages/pupa/scrape/base.py", line 175, in validate
validator.validate(self.as_dict(), schema)
File "/app/.heroku/python/lib/python3.10/site-packages/validictory/validator.py", line 616, in validate
raise MultipleValidationError(self._errors)
validictory.validator.MultipleValidationError: 1 validation errors:
Value ' ' for field '<obj>.name' does not match regular expression 'regex.Regex('\\A(?!(?:Chair|Commissioner|Conseiller|Councillor|Deputy|Dr|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|St\\.|Van|Vander?|van|vanden)?\\p{Lu}\\p{Ll}+|\\p{Lu}\\p{Ll}+Anne?|Marie\\p{Lu}\\p{Ll}+|[ᐁᐃᐄᐅᐆᐊᐋᐯᐱᐲᐳᐴᐸᐹᑉᑊᑌᑎᑏᑐᑑᑕᑖᑦᑫᑭᑮᑯᑰᑲᑳᒃᒉᒋᒌᒍᒎᒐᒑᒡᒣᒥᒦᒧᒨᒪᒫᒻᓀᓂᓃᓄᓅᓇᓈᓐᓓᓕᓖᓗᓘᓚᓛᓪᓭᓯᓰᓱᓲᓴᓵᔅᔦᔨᔩᔪᔫᔭᔮᔾᕂᕆᕇᕈᕉᕋᕌᕐᕓᕕᕖᕗᕘᕙᕚᕝᕴᕵᕶᕷᕸᕹᕺᕻᕼᕿᖀᖁᖂᖃᖄᖅᖏᖐᖑᖒᖓᖔᖕᖖᖠᖡᖢᖣᖤᖥᖦᖨᖩᖪᖫᖬᖭᖮᖯᙯᙰᙱᙲᙳᙴᙵᙶ\U00011ab0\U00011ab1\U00011ab2\U00011ab3\U00011ab4\U00011ab5\U00011ab6\U00011ab7\U00011ab8\U00011ab9\U00011aba\U00011abb]+|Á\'a:líya|A\'aliya|Ch\'ng|Prud\'homme|Qwulti\'stunaat|Ya\'ara|D!ONNE|ChiefCalf|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|St\\.|Van|Vander?|van|vanden)?\\p{Lu}\\p{Ll}+|\\p{Lu}\\p{Ll}+Anne?|Marie\\p{Lu}\\p{Ll}+|[ᐁᐃᐄᐅᐆᐊᐋᐯᐱᐲᐳᐴᐸᐹᑉᑊᑌᑎᑏᑐᑑᑕᑖᑦᑫᑭᑮᑯᑰᑲᑳᒃᒉᒋᒌᒍᒎᒐᒑᒡᒣᒥᒦᒧᒨᒪᒫᒻᓀᓂᓃᓄᓅᓇᓈᓐᓓᓕᓖᓗᓘᓚᓛᓪᓭᓯᓰᓱᓲᓴᓵᔅᔦᔨᔩᔪᔫᔭᔮᔾᕂᕆᕇᕈᕉᕋᕌᕐᕓᕕᕖᕗᕘᕙᕚᕝᕴᕵᕶᕷᕸᕹᕺᕻᕼᕿᖀᖁᖂᖃᖄᖅᖏᖐᖑᖒᖓᖔᖕᖖᖠᖡᖢᖣᖤᖥᖦᖨᖩᖪᖫᖬᖭᖮᖯᙯᙰᙱᙲᙳᙴᙵᙶ\U00011ab0\U00011ab1\U00011ab2\U00011ab3\U00011ab4\U00011ab5\U00011ab6\U00011ab7\U00011ab8\U00011ab9\U00011aba\U00011abb]+|Á\'a:líya|A\'aliya|Ch\'ng|Prud\'homme|Qwulti\'stunaat|Ya\'ara|D!ONNE|ChiefCalf|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 73, in scrape_people
report.report = subcommand.handle(args, other)
File "/app/.heroku/python/lib/python3.10/site-packages/pupa/cli/commands/update.py", line 260, in handle
return self.do_handle(args, other, juris)
File "/app/.heroku/python/lib/python3.10/site-packages/pupa/cli/commands/update.py", line 305, in do_handle
report['scrape'] = self.do_scrape(juris, args, scrapers)
File "/app/.heroku/python/lib/python3.10/site-packages/pupa/cli/commands/update.py", line 173, in do_scrape
report[scraper_name] = scraper.do_scrape(**scrape_args)
File "/app/.heroku/python/lib/python3.10/site-packages/pupa/scrape/base.py", line 104, in do_scrape
self.save_object(obj)
File "/app/.heroku/python/lib/python3.10/site-packages/pupa/scrape/base.py", line 89, in save_object
raise ve
File "/app/.heroku/python/lib/python3.10/site-packages/pupa/scrape/base.py", line 85, in save_object
obj.validate()
File "/app/.heroku/python/lib/python3.10/site-packages/pupa/scrape/base.py", line 177, in validate
raise ScrapeValueError('validation of {} {} failed: {}'.format(
pupa.exceptions.ScrapeValueError: validation of CanadianPerson 4e820948-a7ee-11f0-8c67-d662ad5d87e2 failed: 1 validation errors:
Value ' ' for field '<obj>.name' does not match regular expression 'regex.Regex('\\A(?!(?:Chair|Commissioner|Conseiller|Councillor|Deputy|Dr|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|St\\.|Van|Vander?|van|vanden)?\\p{Lu}\\p{Ll}+|\\p{Lu}\\p{Ll}+Anne?|Marie\\p{Lu}\\p{Ll}+|[ᐁᐃᐄᐅᐆᐊᐋᐯᐱᐲᐳᐴᐸᐹᑉᑊᑌᑎᑏᑐᑑᑕᑖᑦᑫᑭᑮᑯᑰᑲᑳᒃᒉᒋᒌᒍᒎᒐᒑᒡᒣᒥᒦᒧᒨᒪᒫᒻᓀᓂᓃᓄᓅᓇᓈᓐᓓᓕᓖᓗᓘᓚᓛᓪᓭᓯᓰᓱᓲᓴᓵᔅᔦᔨᔩᔪᔫᔭᔮᔾᕂᕆᕇᕈᕉᕋᕌᕐᕓᕕᕖᕗᕘᕙᕚᕝᕴᕵᕶᕷᕸᕹᕺᕻᕼᕿᖀᖁᖂᖃᖄᖅᖏᖐᖑᖒᖓᖔᖕᖖᖠᖡᖢᖣᖤᖥᖦᖨᖩᖪᖫᖬᖭᖮᖯᙯᙰᙱᙲᙳᙴᙵᙶ\U00011ab0\U00011ab1\U00011ab2\U00011ab3\U00011ab4\U00011ab5\U00011ab6\U00011ab7\U00011ab8\U00011ab9\U00011aba\U00011abb]+|Á\'a:líya|A\'aliya|Ch\'ng|Prud\'homme|Qwulti\'stunaat|Ya\'ara|D!ONNE|ChiefCalf|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|St\\.|Van|Vander?|van|vanden)?\\p{Lu}\\p{Ll}+|\\p{Lu}\\p{Ll}+Anne?|Marie\\p{Lu}\\p{Ll}+|[ᐁᐃᐄᐅᐆᐊᐋᐯᐱᐲᐳᐴᐸᐹᑉᑊᑌᑎᑏᑐᑑᑕᑖᑦᑫᑭᑮᑯᑰᑲᑳᒃᒉᒋᒌᒍᒎᒐᒑᒡᒣᒥᒦᒧᒨᒪᒫᒻᓀᓂᓃᓄᓅᓇᓈᓐᓓᓕᓖᓗᓘᓚᓛᓪᓭᓯᓰᓱᓲᓴᓵᔅᔦᔨᔩᔪᔫᔭᔮᔾᕂᕆᕇᕈᕉᕋᕌᕐᕓᕕᕖᕗᕘᕙᕚᕝᕴᕵᕶᕷᕸᕹᕺᕻᕼᕿᖀᖁᖂᖃᖄᖅᖏᖐᖑᖒᖓᖔᖕᖖᖠᖡᖢᖣᖤᖥᖦᖨᖩᖪᖫᖬᖭᖮᖯᙯᙰᙱᙲᙳᙴᙵᙶ\U00011ab0\U00011ab1\U00011ab2\U00011ab3\U00011ab4\U00011ab5\U00011ab6\U00011ab7\U00011ab8\U00011ab9\U00011aba\U00011abb]+|Á\'a:líya|A\'aliya|Ch\'ng|Prud\'homme|Qwulti\'stunaat|Ya\'ara|D!ONNE|ChiefCalf|IsaBelle)\\Z', flags=regex.V0)'
|
|
C
|
ca_nl_st_john_s
|
2025-10-13 04:03:33
|
2025-10-13 04:03:33
|
|
|
C
|
ca_ns
|
2025-10-13 04:31:47
|
2025-10-13 04:31:47
|
|
|
C
|
ca_ns_cape_breton
|
2025-10-13 04:40:22
|
2025-10-13 04:40:22
|
|
|
C
|
ca_ns_halifax
|
2025-10-13 04:03:01
|
2025-10-13 04:03:01
|
|
|
C
|
ca_nt
|
2025-10-13 04:10:42
|
2025-10-13 04:10:43
|
|
|
A
|
ca_nu
|
2025-10-13 04:01:25
|
2025-10-13 04:01:25
|
|
|
C
|
ca_on
|
2025-10-13 04:39:39
|
2025-10-13 04:39:39
|
|
|
C
|
ca_on_ajax
|
2025-10-13 04:39:44
|
2025-10-13 04:39:44
|
|
|
C
|
ca_on_belleville
|
2025-10-13 04:09:26
|
2025-10-13 04:09:26
|
|
|
C
|
ca_on_brampton
|
2025-10-13 04:04:49
|
2025-10-13 04:04:49
|
|
|
C
|
ca_on_brantford
|
2025-10-13 20:58:35
|
2025-10-13 20:58:35
|
|
|
C
|
ca_on_burlington
|
2025-10-13 04:03:26
|
2025-10-13 04:03:26
|
|
|
C
|
ca_on_caledon
|
2025-10-13 04:10:06
|
2025-10-13 04:10:06
|
|
|
C
|
ca_on_cambridge
|
2025-10-13 04:22:57
|
2025-10-13 04:22:57
|
|
|
C
|
ca_on_chatham_kent
|
2025-10-13 04:30:43
|
2025-10-13 04:30:44
|
|
|
C
|
ca_on_clarington
|
2025-10-13 04:09:47
|
2025-10-13 04:09:47
|
|
|
C
|
ca_on_fort_erie
|
2025-10-13 04:22:53
|
2025-10-13 04:22:53
|
|
|
C
|
ca_on_georgina
|
2025-10-13 04:33:05
|
2025-10-13 04:33:05
|
|
|
C
|
ca_on_greater_sudbury
|
2025-10-13 04:07:22
|
2025-10-13 04:07:22
|
|
|
C
|
ca_on_grimsby
|
2025-10-13 04:04:42
|
2025-10-13 04:04:42
|
|
|
C
|
ca_on_guelph
|
2025-10-13 04:22:54
|
2025-10-13 04:22:54
|
|
|
C
|
ca_on_haldimand_county
|
2025-10-13 19:19:45
|
2025-10-13 19:19:45
|
|
|
D>
|
ca_on_hamilton
|
2025-07-02 04:38:31
|
2025-10-13 05:10:33
|
Committee & Board membership
Traceback (most recent call last):
File "/app/reports/utils.py", line 73, in scrape_people
report.report = subcommand.handle(args, other)
File "/app/.heroku/python/lib/python3.10/site-packages/pupa/cli/commands/update.py", line 260, in handle
return self.do_handle(args, other, juris)
File "/app/.heroku/python/lib/python3.10/site-packages/pupa/cli/commands/update.py", line 305, in do_handle
report['scrape'] = self.do_scrape(juris, args, scrapers)
File "/app/.heroku/python/lib/python3.10/site-packages/pupa/cli/commands/update.py", line 173, in do_scrape
report[scraper_name] = scraper.do_scrape(**scrape_args)
File "/app/.heroku/python/lib/python3.10/site-packages/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 17, in scrape
yield self.councillor_data(url)
File "/app/scrapers/ca_on_hamilton/people.py", line 27, in councillor_data
phone = self.get_phone(info_node, area_codes=[289, 365, 905])
File "/app/scrapers/utils.py", line 186, in get_phone
raise Exception(f"No phone pattern in {node.text_content()}")
Exception: No phone pattern in
Councillor
Rob Cooper
Email: [email protected]Hamilton City Hall2nd floor - 71 Main Street WestHamilton, Ontario L8P 4Y5
Committee & Board membership
|
|
C
|
ca_on_huron
|
2025-10-13 04:04:33
|
2025-10-13 04:04:33
|
|
|
D>
|
ca_on_kawartha_lakes
|
2025-09-25 04:24:22
|
2025-10-13 04:04:37
|
scrapelib.HTTPError: 404 while retrieving https://www.kawarthalakes.ca/en/municipal-services/contact-a-council-member.aspx
Traceback (most recent call last):
File "/app/reports/utils.py", line 73, in scrape_people
report.report = subcommand.handle(args, other)
File "/app/.heroku/python/lib/python3.10/site-packages/pupa/cli/commands/update.py", line 260, in handle
return self.do_handle(args, other, juris)
File "/app/.heroku/python/lib/python3.10/site-packages/pupa/cli/commands/update.py", line 305, in do_handle
report['scrape'] = self.do_scrape(juris, args, scrapers)
File "/app/.heroku/python/lib/python3.10/site-packages/pupa/cli/commands/update.py", line 173, in do_scrape
report[scraper_name] = scraper.do_scrape(**scrape_args)
File "/app/.heroku/python/lib/python3.10/site-packages/pupa/scrape/base.py", line 99, in do_scrape
for obj in self.scrape(**kwargs) or []:
File "/app/scrapers/ca_on_kawartha_lakes/people.py", line 11, in scrape
page = self.lxmlize(COUNCIL_PAGE)
File "/app/scrapers/utils.py", line 217, in lxmlize
response = self.get(url, cookies=cookies, verify=verify)
File "/app/scrapers/utils.py", line 198, in get
return super().get(*args, verify=kwargs.pop("verify", SSL_VERIFY), **kwargs)
File "/app/.heroku/python/lib/python3.10/site-packages/requests/sessions.py", line 602, in get
return self.request("GET", url, **kwargs)
File "/app/.heroku/python/lib/python3.10/site-packages/scrapelib/__init__.py", line 619, in request
raise HTTPError(resp)
scrapelib.HTTPError: 404 while retrieving https://www.kawarthalakes.ca/en/municipal-services/contact-a-council-member.aspx
|
|
C
|
ca_on_king
|
2025-10-13 04:33:02
|
2025-10-13 04:33:02
|
|
|
C
|
ca_on_kingston
|
2025-10-13 04:22:59
|
2025-10-13 04:22:59
|
|
|
C
|
ca_on_kitchener
|
2025-10-13 04:03:46
|
2025-10-13 04:03:46
|
|
|
C
|
ca_on_lambton
|
2025-10-13 16:32:08
|
2025-10-13 16:32:08
|
|
|
C
|
ca_on_lasalle
|
2025-10-13 04:01:29
|
2025-10-13 04:01:29
|
|
|
C
|
ca_on_lincoln
|
2025-10-13 04:07:27
|
2025-10-13 04:07:27
|
|
|
C
|
ca_on_london
|
2025-10-13 04:02:32
|
2025-10-13 04:02:33
|
|
|
D>
|
ca_on_markham
|
2025-07-04 04:13:21
|
2025-10-13 04:09:24
|
IndexError: list index out of range
Traceback (most recent call last):
File "/app/reports/utils.py", line 73, in scrape_people
report.report = subcommand.handle(args, other)
File "/app/.heroku/python/lib/python3.10/site-packages/pupa/cli/commands/update.py", line 260, in handle
return self.do_handle(args, other, juris)
File "/app/.heroku/python/lib/python3.10/site-packages/pupa/cli/commands/update.py", line 305, in do_handle
report['scrape'] = self.do_scrape(juris, args, scrapers)
File "/app/.heroku/python/lib/python3.10/site-packages/pupa/cli/commands/update.py", line 173, in do_scrape
report[scraper_name] = scraper.do_scrape(**scrape_args)
File "/app/.heroku/python/lib/python3.10/site-packages/pupa/scrape/base.py", line 101, in do_scrape
for iterobj in obj:
File "/app/scrapers/ca_on_markham/people.py", line 97, in scrape_mayor
p.image = page.xpath('.//div[@class="align-right media--image"]/div/img/@src')[0]
IndexError: list index out of range
|
|
D>
|
ca_on_milton
|
2025-10-07 04:23:59
|
2025-10-13 04:35:06
|
Details on how to contact the councillor will be posted once finalized.
Traceback (most recent call last):
File "/app/reports/utils.py", line 73, in scrape_people
report.report = subcommand.handle(args, other)
File "/app/.heroku/python/lib/python3.10/site-packages/pupa/cli/commands/update.py", line 260, in handle
return self.do_handle(args, other, juris)
File "/app/.heroku/python/lib/python3.10/site-packages/pupa/cli/commands/update.py", line 305, in do_handle
report['scrape'] = self.do_scrape(juris, args, scrapers)
File "/app/.heroku/python/lib/python3.10/site-packages/pupa/cli/commands/update.py", line 173, in do_scrape
report[scraper_name] = scraper.do_scrape(**scrape_args)
File "/app/.heroku/python/lib/python3.10/site-packages/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 21, in scrape
p = self.scrape_person(councillor, district, url)
File "/app/scrapers/ca_on_milton/people.py", line 43, in scrape_person
phone = self.get_phone(node)
File "/app/scrapers/utils.py", line 186, in get_phone
raise Exception(f"No phone pattern in {node.text_content()}")
Exception: No phone pattern in
Town CouncillorGeorge Minakakis
Details on how to contact the councillor will be posted once finalized.
|
|
C
|
ca_on_mississauga
|
2025-10-13 04:33:20
|
2025-10-13 04:33:20
|
|
|
C
|
ca_on_newmarket
|
2025-10-13 04:03:38
|
2025-10-13 04:03:38
|
|
|
C
|
ca_on_niagara
|
2025-10-13 04:04:35
|
2025-10-13 04:04:35
|
|
|
C
|
ca_on_niagara_on_the_lake
|
2025-10-13 04:32:59
|
2025-10-13 04:32:59
|
|
|
D>
|
ca_on_north_dumfries
|
2025-06-19 04:19:39
|
2025-10-13 04:41:49
|
scrapelib.HTTPError: 404 while retrieving https://www.northdumfries.ca/en/township-services/mayor-and-council.aspx
Traceback (most recent call last):
File "/app/reports/utils.py", line 73, in scrape_people
report.report = subcommand.handle(args, other)
File "/app/.heroku/python/lib/python3.10/site-packages/pupa/cli/commands/update.py", line 260, in handle
return self.do_handle(args, other, juris)
File "/app/.heroku/python/lib/python3.10/site-packages/pupa/cli/commands/update.py", line 305, in do_handle
report['scrape'] = self.do_scrape(juris, args, scrapers)
File "/app/.heroku/python/lib/python3.10/site-packages/pupa/cli/commands/update.py", line 173, in do_scrape
report[scraper_name] = scraper.do_scrape(**scrape_args)
File "/app/.heroku/python/lib/python3.10/site-packages/pupa/scrape/base.py", line 99, in do_scrape
for obj in self.scrape(**kwargs) or []:
File "/app/scrapers/ca_on_north_dumfries/people.py", line 11, in scrape
page = self.lxmlize(COUNCIL_PAGE)
File "/app/scrapers/utils.py", line 217, in lxmlize
response = self.get(url, cookies=cookies, verify=verify)
File "/app/scrapers/utils.py", line 198, in get
return super().get(*args, verify=kwargs.pop("verify", SSL_VERIFY), **kwargs)
File "/app/.heroku/python/lib/python3.10/site-packages/requests/sessions.py", line 602, in get
return self.request("GET", url, **kwargs)
File "/app/.heroku/python/lib/python3.10/site-packages/scrapelib/__init__.py", line 619, in request
raise HTTPError(resp)
scrapelib.HTTPError: 404 while retrieving https://www.northdumfries.ca/en/township-services/mayor-and-council.aspx
|
|
C
|
ca_on_oakville
|
2025-10-13 04:10:16
|
2025-10-13 04:10:16
|
|
|
D>
|
ca_on_oshawa
|
2025-09-18 04:52:15
|
2025-10-13 04:09:44
|
scrapelib.HTTPError: 404 while retrieving https://www.oshawa.ca/en/city-hall/council-members.aspx
Traceback (most recent call last):
File "/app/reports/utils.py", line 73, in scrape_people
report.report = subcommand.handle(args, other)
File "/app/.heroku/python/lib/python3.10/site-packages/pupa/cli/commands/update.py", line 260, in handle
return self.do_handle(args, other, juris)
File "/app/.heroku/python/lib/python3.10/site-packages/pupa/cli/commands/update.py", line 305, in do_handle
report['scrape'] = self.do_scrape(juris, args, scrapers)
File "/app/.heroku/python/lib/python3.10/site-packages/pupa/cli/commands/update.py", line 173, in do_scrape
report[scraper_name] = scraper.do_scrape(**scrape_args)
File "/app/.heroku/python/lib/python3.10/site-packages/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 12, in scrape
page = self.lxmlize(COUNCIL_PAGE)
File "/app/scrapers/utils.py", line 217, in lxmlize
response = self.get(url, cookies=cookies, verify=verify)
File "/app/scrapers/utils.py", line 198, in get
return super().get(*args, verify=kwargs.pop("verify", SSL_VERIFY), **kwargs)
File "/app/.heroku/python/lib/python3.10/site-packages/requests/sessions.py", line 602, in get
return self.request("GET", url, **kwargs)
File "/app/.heroku/python/lib/python3.10/site-packages/scrapelib/__init__.py", line 619, in request
raise HTTPError(resp)
scrapelib.HTTPError: 404 while retrieving https://www.oshawa.ca/en/city-hall/council-members.aspx
|
D>
04:40:37 WARNING scrapelib: sleeping for 10 seconds before retry
04:40:47 WARNING scrapelib: sleeping for 20 seconds before retry
04:41:07 WARNING scrapelib: sleeping for 40 seconds before retry
|
ca_on_ottawa
|
2025-06-26 04:31:47
|
2025-10-13 04:41:47
|
scrapelib.HTTPError: 400 while retrieving https://www.arcgis.com/sharing/rest/content/items/a5e9dc2425274bb796d3ded47b0d7b00…
Traceback (most recent call last):
File "/app/reports/utils.py", line 73, in scrape_people
report.report = subcommand.handle(args, other)
File "/app/.heroku/python/lib/python3.10/site-packages/pupa/cli/commands/update.py", line 260, in handle
return self.do_handle(args, other, juris)
File "/app/.heroku/python/lib/python3.10/site-packages/pupa/cli/commands/update.py", line 305, in do_handle
report['scrape'] = self.do_scrape(juris, args, scrapers)
File "/app/.heroku/python/lib/python3.10/site-packages/pupa/cli/commands/update.py", line 173, in do_scrape
report[scraper_name] = scraper.do_scrape(**scrape_args)
File "/app/.heroku/python/lib/python3.10/site-packages/pupa/scrape/base.py", line 99, in do_scrape
for obj in self.scrape(**kwargs) or []:
File "/app/scrapers/utils.py", line 386, in scrape
binary = BytesIO(self.get(self.csv_url).content)
File "/app/scrapers/utils.py", line 198, in get
return super().get(*args, verify=kwargs.pop("verify", SSL_VERIFY), **kwargs)
File "/app/.heroku/python/lib/python3.10/site-packages/requests/sessions.py", line 602, in get
return self.request("GET", url, **kwargs)
File "/app/.heroku/python/lib/python3.10/site-packages/scrapelib/__init__.py", line 619, in request
raise HTTPError(resp)
scrapelib.HTTPError: 400 while retrieving https://www.arcgis.com/sharing/rest/content/items/a5e9dc2425274bb796d3ded47b0d7b00/data
|
|
C
|
ca_on_peel
|
2025-10-13 04:34:56
|
2025-10-13 04:34:56
|
|
|
C
|
ca_on_pickering
|
2025-10-13 04:00:58
|
2025-10-13 04:00:58
|
|
|
C
|
ca_on_richmond_hill
|
2025-10-13 04:02:26
|
2025-10-13 04:02:27
|
|
|
D>
|
ca_on_sault_ste_marie
|
2025-09-24 04:33:36
|
2025-10-13 04:30:46
|
AssertionError: No councillors found
Traceback (most recent call last):
File "/app/reports/utils.py", line 73, in scrape_people
report.report = subcommand.handle(args, other)
File "/app/.heroku/python/lib/python3.10/site-packages/pupa/cli/commands/update.py", line 260, in handle
return self.do_handle(args, other, juris)
File "/app/.heroku/python/lib/python3.10/site-packages/pupa/cli/commands/update.py", line 305, in do_handle
report['scrape'] = self.do_scrape(juris, args, scrapers)
File "/app/.heroku/python/lib/python3.10/site-packages/pupa/cli/commands/update.py", line 173, in do_scrape
report[scraper_name] = scraper.do_scrape(**scrape_args)
File "/app/.heroku/python/lib/python3.10/site-packages/pupa/scrape/base.py", line 99, in do_scrape
for obj in self.scrape(**kwargs) or []:
File "/app/scrapers/ca_on_sault_ste_marie/people.py", line 16, in scrape
assert len(councillors), "No councillors found"
AssertionError: No councillors found
|
D>
04:31:48 WARNING scrapelib: sleeping for 10 seconds before retry
04:31:58 WARNING scrapelib: sleeping for 20 seconds before retry
04:32:18 WARNING scrapelib: sleeping for 40 seconds before retry
|
ca_on_st_catharines
|
2025-10-09 04:06:20
|
2025-10-13 04:32:58
|
scrapelib.HTTPError: 502 while retrieving https://niagaraopendata.ca/dataset/ccb9c7f1-d3b0-4049-9c08-e4f7b048722c/resource/1…
Traceback (most recent call last):
File "/app/reports/utils.py", line 73, in scrape_people
report.report = subcommand.handle(args, other)
File "/app/.heroku/python/lib/python3.10/site-packages/pupa/cli/commands/update.py", line 260, in handle
return self.do_handle(args, other, juris)
File "/app/.heroku/python/lib/python3.10/site-packages/pupa/cli/commands/update.py", line 305, in do_handle
report['scrape'] = self.do_scrape(juris, args, scrapers)
File "/app/.heroku/python/lib/python3.10/site-packages/pupa/cli/commands/update.py", line 173, in do_scrape
report[scraper_name] = scraper.do_scrape(**scrape_args)
File "/app/.heroku/python/lib/python3.10/site-packages/pupa/scrape/base.py", line 99, in do_scrape
for obj in self.scrape(**kwargs) or []:
File "/app/scrapers/utils.py", line 408, in scrape
reader = self.csv_reader(
File "/app/scrapers/utils.py", line 251, in csv_reader
response = self.get(url, **kwargs)
File "/app/scrapers/utils.py", line 198, in get
return super().get(*args, verify=kwargs.pop("verify", SSL_VERIFY), **kwargs)
File "/app/.heroku/python/lib/python3.10/site-packages/requests/sessions.py", line 602, in get
return self.request("GET", url, **kwargs)
File "/app/.heroku/python/lib/python3.10/site-packages/scrapelib/__init__.py", line 619, in request
raise HTTPError(resp)
scrapelib.HTTPError: 502 while retrieving https://niagaraopendata.ca/dataset/ccb9c7f1-d3b0-4049-9c08-e4f7b048722c/resource/128a39f0-8234-4708-b69b-9c73f7a55475/download/stcathcounsilors.csv
|
|
C
|
ca_on_thunder_bay
|
2025-10-13 20:07:50
|
2025-10-13 20:07:50
|
|
|
C
|
ca_on_toronto
|
2025-10-13 04:03:36
|
2025-10-13 04:03:36
|
|
|
C
|
ca_on_uxbridge
|
2025-10-13 04:39:41
|
2025-10-13 04:39:41
|
|
|
C
|
ca_on_vaughan
|
2025-10-13 04:30:21
|
2025-10-13 04:30:21
|
|
|
C
|
ca_on_waterloo
|
2025-10-13 18:29:31
|
2025-10-13 18:29:31
|
|
|
C
|
ca_on_waterloo_region
|
2025-10-13 04:05:07
|
2025-10-13 04:05:07
|
|
|
C
|
ca_on_welland
|
2025-10-13 04:03:44
|
2025-10-13 04:03:44
|
|
|
D>
|
ca_on_wellesley
|
2025-09-11 04:47:48
|
2025-10-13 04:29:23
|
scrapelib.HTTPError: 404 while retrieving https://www.wellesley.ca/council/councillors/?q=council/councillors
Traceback (most recent call last):
File "/app/reports/utils.py", line 73, in scrape_people
report.report = subcommand.handle(args, other)
File "/app/.heroku/python/lib/python3.10/site-packages/pupa/cli/commands/update.py", line 260, in handle
return self.do_handle(args, other, juris)
File "/app/.heroku/python/lib/python3.10/site-packages/pupa/cli/commands/update.py", line 305, in do_handle
report['scrape'] = self.do_scrape(juris, args, scrapers)
File "/app/.heroku/python/lib/python3.10/site-packages/pupa/cli/commands/update.py", line 173, in do_scrape
report[scraper_name] = scraper.do_scrape(**scrape_args)
File "/app/.heroku/python/lib/python3.10/site-packages/pupa/scrape/base.py", line 99, in do_scrape
for obj in self.scrape(**kwargs) or []:
File "/app/scrapers/ca_on_wellesley/people.py", line 15, in scrape
page = self.lxmlize(COUNCIL_PAGE)
File "/app/scrapers/utils.py", line 217, in lxmlize
response = self.get(url, cookies=cookies, verify=verify)
File "/app/scrapers/utils.py", line 198, in get
return super().get(*args, verify=kwargs.pop("verify", SSL_VERIFY), **kwargs)
File "/app/.heroku/python/lib/python3.10/site-packages/requests/sessions.py", line 602, in get
return self.request("GET", url, **kwargs)
File "/app/.heroku/python/lib/python3.10/site-packages/scrapelib/__init__.py", line 619, in request
raise HTTPError(resp)
scrapelib.HTTPError: 404 while retrieving https://www.wellesley.ca/council/councillors/?q=council/councillors
|
|
D>
|
ca_on_whitby
|
2025-09-12 04:03:37
|
2025-10-13 04:39:45
|
ValueError: not enough values to unpack (expected 2, got 1)
Traceback (most recent call last):
File "/app/reports/utils.py", line 73, in scrape_people
report.report = subcommand.handle(args, other)
File "/app/.heroku/python/lib/python3.10/site-packages/pupa/cli/commands/update.py", line 260, in handle
return self.do_handle(args, other, juris)
File "/app/.heroku/python/lib/python3.10/site-packages/pupa/cli/commands/update.py", line 305, in do_handle
report['scrape'] = self.do_scrape(juris, args, scrapers)
File "/app/.heroku/python/lib/python3.10/site-packages/pupa/cli/commands/update.py", line 173, in do_scrape
report[scraper_name] = scraper.do_scrape(**scrape_args)
File "/app/.heroku/python/lib/python3.10/site-packages/pupa/scrape/base.py", line 99, in do_scrape
for obj in self.scrape(**kwargs) or []:
File "/app/scrapers/ca_on_whitby/people.py", line 23, in scrape
name, role = name.split(", ")
ValueError: not enough values to unpack (expected 2, got 1)
|
|
C
|
ca_on_whitchurch_stouffville
|
2025-10-13 04:04:29
|
2025-10-13 04:04:29
|
|
|
D>
|
ca_on_wilmot
|
2025-09-30 04:25:16
|
2025-10-13 04:22:51
|
scrapelib.HTTPError: 404 while retrieving https://www.wilmot.ca/en/township-office/council.aspx
Traceback (most recent call last):
File "/app/reports/utils.py", line 73, in scrape_people
report.report = subcommand.handle(args, other)
File "/app/.heroku/python/lib/python3.10/site-packages/pupa/cli/commands/update.py", line 260, in handle
return self.do_handle(args, other, juris)
File "/app/.heroku/python/lib/python3.10/site-packages/pupa/cli/commands/update.py", line 305, in do_handle
report['scrape'] = self.do_scrape(juris, args, scrapers)
File "/app/.heroku/python/lib/python3.10/site-packages/pupa/cli/commands/update.py", line 173, in do_scrape
report[scraper_name] = scraper.do_scrape(**scrape_args)
File "/app/.heroku/python/lib/python3.10/site-packages/pupa/scrape/base.py", line 99, in do_scrape
for obj in self.scrape(**kwargs) or []:
File "/app/scrapers/ca_on_wilmot/people.py", line 9, in scrape
page = self.lxmlize(COUNCIL_PAGE)
File "/app/scrapers/utils.py", line 217, in lxmlize
response = self.get(url, cookies=cookies, verify=verify)
File "/app/scrapers/utils.py", line 198, in get
return super().get(*args, verify=kwargs.pop("verify", SSL_VERIFY), **kwargs)
File "/app/.heroku/python/lib/python3.10/site-packages/requests/sessions.py", line 602, in get
return self.request("GET", url, **kwargs)
File "/app/.heroku/python/lib/python3.10/site-packages/scrapelib/__init__.py", line 619, in request
raise HTTPError(resp)
scrapelib.HTTPError: 404 while retrieving https://www.wilmot.ca/en/township-office/council.aspx
|
|
C
|
ca_on_windsor
|
2025-10-13 04:37:19
|
2025-10-13 04:37:19
|
|
|
C
|
ca_on_woolwich
|
2025-10-13 04:04:30
|
2025-10-13 04:04:30
|
|
|
C
|
ca_pe
|
2025-10-13 04:35:38
|
2025-10-13 04:35:38
|
|
|
C
|
ca_pe_charlottetown
|
2025-10-13 04:05:43
|
2025-10-13 04:05:43
|
|
|
C
|
ca_pe_stratford
|
2025-10-13 04:22:56
|
2025-10-13 04:22:56
|
|
|
C
|
ca_pe_summerside
|
2025-10-13 21:51:49
|
2025-10-13 21:51:49
|
|
|
C
|
ca_qc
|
2025-10-13 04:29:20
|
2025-10-13 04:29:20
|
|
|
C
|
ca_qc_beaconsfield
|
2025-10-13 04:33:07
|
2025-10-13 04:33:07
|
|
D>
04:55:56 WARNING pupa: validation of CanadianPerson e7a8a512-a7f0-11f0-a04a-4a5572e64d5a failed: 1 validation errors:
Value "data:image/svg+xml,%3Csvg%20xmlns='http://www.w3.org/2000/svg'%20viewBox='0%200%20341%20400'%3E%3C/svg%3E" for field '<obj>.image' does not match regular expression '\A(?:(?:ftp|https?)://|\Z)'
|
ca_qc_brossard
|
2025-09-25 04:11:31
|
2025-10-13 04:55:56
|
Value "data:image/svg+xml,%3Csvg%20xmlns='http://www.w3.org/2000/svg'%20viewBox='0%200%20341%20400'%3E%3C/svg%3E" for field …
Traceback (most recent call last):
File "/app/.heroku/python/lib/python3.10/site-packages/pupa/scrape/base.py", line 175, in validate
validator.validate(self.as_dict(), schema)
File "/app/.heroku/python/lib/python3.10/site-packages/validictory/validator.py", line 616, in validate
raise MultipleValidationError(self._errors)
validictory.validator.MultipleValidationError: 1 validation errors:
Value "data:image/svg+xml,%3Csvg%20xmlns='http://www.w3.org/2000/svg'%20viewBox='0%200%20341%20400'%3E%3C/svg%3E" 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 73, in scrape_people
report.report = subcommand.handle(args, other)
File "/app/.heroku/python/lib/python3.10/site-packages/pupa/cli/commands/update.py", line 260, in handle
return self.do_handle(args, other, juris)
File "/app/.heroku/python/lib/python3.10/site-packages/pupa/cli/commands/update.py", line 305, in do_handle
report['scrape'] = self.do_scrape(juris, args, scrapers)
File "/app/.heroku/python/lib/python3.10/site-packages/pupa/cli/commands/update.py", line 173, in do_scrape
report[scraper_name] = scraper.do_scrape(**scrape_args)
File "/app/.heroku/python/lib/python3.10/site-packages/pupa/scrape/base.py", line 104, in do_scrape
self.save_object(obj)
File "/app/.heroku/python/lib/python3.10/site-packages/pupa/scrape/base.py", line 89, in save_object
raise ve
File "/app/.heroku/python/lib/python3.10/site-packages/pupa/scrape/base.py", line 85, in save_object
obj.validate()
File "/app/.heroku/python/lib/python3.10/site-packages/pupa/scrape/base.py", line 177, in validate
raise ScrapeValueError('validation of {} {} failed: {}'.format(
pupa.exceptions.ScrapeValueError: validation of CanadianPerson e7a8a512-a7f0-11f0-a04a-4a5572e64d5a failed: 1 validation errors:
Value "data:image/svg+xml,%3Csvg%20xmlns='http://www.w3.org/2000/svg'%20viewBox='0%200%20341%20400'%3E%3C/svg%3E" for field '<obj>.image' does not match regular expression '\A(?:(?:ftp|https?)://|\Z)'
|
|
C
|
ca_qc_cote_saint_luc
|
2025-10-13 04:39:43
|
2025-10-13 04:39:43
|
|
|
C
|
ca_qc_dollard_des_ormeaux
|
2025-10-13 04:03:37
|
2025-10-13 04:03:37
|
|
|
C
|
ca_qc_dorval
|
2025-10-13 17:20:21
|
2025-10-13 17:20:21
|
|
|
C
|
ca_qc_gatineau
|
2025-10-13 04:06:07
|
2025-10-13 04:06:07
|
|
|
C
|
ca_qc_kirkland
|
2025-10-13 04:30:45
|
2025-10-13 04:30:45
|
|
|
C
|
ca_qc_laval
|
2025-10-13 04:10:18
|
2025-10-13 04:10:18
|
|
|
C
|
ca_qc_levis
|
2025-10-13 23:23:06
|
2025-10-13 23:23:06
|
|
|
C
|
ca_qc_longueuil
|
2025-10-13 04:36:06
|
2025-10-13 04:36:06
|
|
|
C
|
ca_qc_mercier
|
2025-10-13 04:09:22
|
2025-10-13 04:09:22
|
|
|
C
|
ca_qc_montreal
|
2025-10-13 09:00:11
|
2025-10-13 09:00:11
|
|
|
C
|
ca_qc_montreal_est
|
2025-10-13 04:10:21
|
2025-10-13 04:10:21
|
|
|
C
|
ca_qc_pointe_claire
|
2025-10-13 17:21:02
|
2025-10-13 17:21:02
|
|
|
C
|
ca_qc_quebec
|
2025-10-13 04:04:39
|
2025-10-13 04:04:39
|
|
|
D>
|
ca_qc_saguenay
|
2025-08-27 04:01:52
|
2025-10-13 04:41:56
|
scrapelib.HTTPError: 404 while retrieving https://ville.saguenay.ca/la-ville-et-vie-democratique/cabinet
Traceback (most recent call last):
File "/app/reports/utils.py", line 73, in scrape_people
report.report = subcommand.handle(args, other)
File "/app/.heroku/python/lib/python3.10/site-packages/pupa/cli/commands/update.py", line 260, in handle
return self.do_handle(args, other, juris)
File "/app/.heroku/python/lib/python3.10/site-packages/pupa/cli/commands/update.py", line 305, in do_handle
report['scrape'] = self.do_scrape(juris, args, scrapers)
File "/app/.heroku/python/lib/python3.10/site-packages/pupa/cli/commands/update.py", line 173, in do_scrape
report[scraper_name] = scraper.do_scrape(**scrape_args)
File "/app/.heroku/python/lib/python3.10/site-packages/pupa/scrape/base.py", line 99, in do_scrape
for obj in self.scrape(**kwargs) or []:
File "/app/scrapers/ca_qc_saguenay/people.py", line 14, in scrape
contact_page = self.lxmlize(CONTACT_PAGE)
File "/app/scrapers/utils.py", line 217, in lxmlize
response = self.get(url, cookies=cookies, verify=verify)
File "/app/scrapers/utils.py", line 198, in get
return super().get(*args, verify=kwargs.pop("verify", SSL_VERIFY), **kwargs)
File "/app/.heroku/python/lib/python3.10/site-packages/requests/sessions.py", line 602, in get
return self.request("GET", url, **kwargs)
File "/app/.heroku/python/lib/python3.10/site-packages/scrapelib/__init__.py", line 619, in request
raise HTTPError(resp)
scrapelib.HTTPError: 404 while retrieving https://ville.saguenay.ca/la-ville-et-vie-democratique/cabinet
|
|
C
|
ca_qc_sainte_anne_de_bellevue
|
2025-10-13 23:23:38
|
2025-10-13 23:23:38
|
|
|
C
|
ca_qc_saint_jean_sur_richelieu
|
2025-10-13 04:09:43
|
2025-10-13 04:09:43
|
|
|
C
|
ca_qc_saint_jerome
|
2025-10-13 04:09:28
|
2025-10-13 04:09:28
|
|
|
D>
|
ca_qc_senneville
|
2025-10-02 04:03:34
|
2025-10-13 04:03:47
|
pupa.exceptions.UnresolvedIdError: cannot resolve pseudo id to Post: ~{"label": "District 4", "organization__classification"…
Traceback (most recent call last):
File "/app/reports/utils.py", line 73, in scrape_people
report.report = subcommand.handle(args, other)
File "/app/.heroku/python/lib/python3.10/site-packages/pupa/cli/commands/update.py", line 260, in handle
return self.do_handle(args, other, juris)
File "/app/.heroku/python/lib/python3.10/site-packages/pupa/cli/commands/update.py", line 307, in do_handle
report['import'] = self.do_import(juris, args)
File "/app/.heroku/python/lib/python3.10/site-packages/pupa/cli/commands/update.py", line 211, in do_import
report.update(membership_importer.import_directory(datadir))
File "/app/.heroku/python/lib/python3.10/site-packages/pupa/importers/base.py", line 190, in import_directory
return self.import_data(json_stream())
File "/app/.heroku/python/lib/python3.10/site-packages/pupa/importers/base.py", line 227, in import_data
obj_id, what = self.import_item(data)
File "/app/.heroku/python/lib/python3.10/site-packages/pupa/importers/base.py", line 247, in import_item
data = self.prepare_for_db(data)
File "/app/.heroku/python/lib/python3.10/site-packages/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/python/lib/python3.10/site-packages/pupa/importers/base.py", line 165, in resolve_json_id
raise UnresolvedIdError(errmsg)
pupa.exceptions.UnresolvedIdError: cannot resolve pseudo id to Post: ~{"label": "District 4", "organization__classification": "legislature", "role": "Conseill\u00e8re"}
|
|
C
|
ca_qc_sherbrooke
|
2025-10-13 19:20:08
|
2025-10-13 19:20:08
|
|
D>
04:41:58 WARNING scrapelib: sleeping for 10 seconds before retry
04:42:08 WARNING scrapelib: sleeping for 20 seconds before retry
04:42:28 WARNING scrapelib: sleeping for 40 seconds before retry
|
ca_qc_terrebonne
|
|
2025-10-13 04:43:08
|
scrapelib.HTTPError: 403 while retrieving https://terrebonne.ca/membres-du-conseil-municipal/
Traceback (most recent call last):
File "/app/reports/utils.py", line 73, in scrape_people
report.report = subcommand.handle(args, other)
File "/app/.heroku/python/lib/python3.10/site-packages/pupa/cli/commands/update.py", line 260, in handle
return self.do_handle(args, other, juris)
File "/app/.heroku/python/lib/python3.10/site-packages/pupa/cli/commands/update.py", line 305, in do_handle
report['scrape'] = self.do_scrape(juris, args, scrapers)
File "/app/.heroku/python/lib/python3.10/site-packages/pupa/cli/commands/update.py", line 173, in do_scrape
report[scraper_name] = scraper.do_scrape(**scrape_args)
File "/app/.heroku/python/lib/python3.10/site-packages/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 9, in scrape
page = self.lxmlize(COUNCIL_PAGE, user_agent=CUSTOM_USER_AGENT)
File "/app/scrapers/utils.py", line 217, in lxmlize
response = self.get(url, cookies=cookies, verify=verify)
File "/app/scrapers/utils.py", line 198, in get
return super().get(*args, verify=kwargs.pop("verify", SSL_VERIFY), **kwargs)
File "/app/.heroku/python/lib/python3.10/site-packages/requests/sessions.py", line 602, in get
return self.request("GET", url, **kwargs)
File "/app/.heroku/python/lib/python3.10/site-packages/scrapelib/__init__.py", line 619, in request
raise HTTPError(resp)
scrapelib.HTTPError: 403 while retrieving https://terrebonne.ca/membres-du-conseil-municipal/
|
|
C
|
ca_qc_trois_rivieres
|
2025-10-13 04:00:36
|
2025-10-13 04:00:36
|
|
|
C
|
ca_qc_westmount
|
2025-10-13 04:00:19
|
2025-10-13 04:00:19
|
|
|
C
|
ca_sk
|
2025-10-13 04:08:31
|
2025-10-13 04:08:31
|
|
|
C
|
ca_sk_regina
|
2025-10-13 04:40:36
|
2025-10-13 04:40:36
|
|
|
C
|
ca_sk_saskatoon
|
2025-10-13 04:09:20
|
2025-10-13 04:09:20
|
|
|
D>
|
ca_yt
|
|
2025-10-13 11:40:49
|
requests.exceptions.HTTPError: 403 Client Error: Forbidden for url: https://yukonassembly.ca/mlas
Traceback (most recent call last):
File "/app/reports/utils.py", line 73, in scrape_people
report.report = subcommand.handle(args, other)
File "/app/.heroku/python/lib/python3.10/site-packages/pupa/cli/commands/update.py", line 260, in handle
return self.do_handle(args, other, juris)
File "/app/.heroku/python/lib/python3.10/site-packages/pupa/cli/commands/update.py", line 305, in do_handle
report['scrape'] = self.do_scrape(juris, args, scrapers)
File "/app/.heroku/python/lib/python3.10/site-packages/pupa/cli/commands/update.py", line 173, in do_scrape
report[scraper_name] = scraper.do_scrape(**scrape_args)
File "/app/.heroku/python/lib/python3.10/site-packages/pupa/scrape/base.py", line 99, in do_scrape
for obj in self.scrape(**kwargs) or []:
File "/app/scrapers/ca_yt/people.py", line 11, in scrape
page = self.cloudscrape(COUNCIL_PAGE)
File "/app/scrapers/utils.py", line 205, in cloudscrape
response.raise_for_status()
File "/app/.heroku/python/lib/python3.10/site-packages/requests/models.py", line 1026, in raise_for_status
raise HTTPError(http_error_msg, response=self)
requests.exceptions.HTTPError: 403 Client Error: Forbidden for url: https://yukonassembly.ca/mlas
|