diff --git a/api/failing.json b/api/failing.json index 3de17819e4..0e523cf9e5 100644 --- a/api/failing.json +++ b/api/failing.json @@ -1 +1 @@ -[{"council_id":"AGB","missing":false,"latest_run":{"status_code":1,"log_text":"[09:50:11] Fetching Scraper for: AGB handlers.py:23\n Begin attempting to scrape: AGB handlers.py:27\n Deleting existing data... base.py:257\n[09:50:12] Getting all files in Councillors... base.py:209\n Getting all files in Councillors/json... base.py:209\n ...found 11 files in Councillors/json base.py:225\n Getting all files in Councillors/raw... base.py:209\n[09:50:13] ...found 11 files in Councillors/raw base.py:225\n ...found 23 files in Councillors base.py:225\n Deleting batch no. 1 consisting of 23 files base.py:236\n ...data deleted. base.py:264\n Scraping from base.py:49\n https://www.argyll-bute.gov.uk/councillor_list \n[09:50:16] Scraping from base.py:49\n https://www.argyll-bute.gov.uk/my-council/councillors-dire \n ctory/south-kintyre/councillor/john-armour \n[09:50:17] Scraping from base.py:49\n https://www.argyll-bute.gov.uk/my-council/councillors-dire \n ctory/cowal/councillor/gordon-blair \n[09:50:18] Scraping from base.py:49\n https://www.argyll-bute.gov.uk/my-council/councillors-dire \n ctory/mid-argyll/councillor/jan-brown \n[09:50:19] Scraping from base.py:49\n https://www.argyll-bute.gov.uk/my-council/councillors-dire \n ctory/helensburgh-and-lomond-south/councillor/math-campbel \n l-sturgess \n[09:50:20] Scraping from base.py:49\n https://www.argyll-bute.gov.uk/my-council/councillors-dire \n ctory/mid-argyll/councillor/garret-corner \n[09:50:22] Scraping from base.py:49\n https://www.argyll-bute.gov.uk/my-council/councillors-dire \n ctory/lomond-north/councillor/maurice-corry \n[09:50:23] Scraping from base.py:49\n https://www.argyll-bute.gov.uk/my-council/councillors-dire \n ctory/dunoon/councillor/audrey-e-forrest \n[09:50:24] Scraping from base.py:49\n https://www.argyll-bute.gov.uk/my-council/councillors-dire \n ctory/oban-north-and-lorn/councillor/kieron-green \n[09:50:25] Scraping from base.py:49\n https://www.argyll-bute.gov.uk/my-council/councillors-dire \n ctory/dunoon/councillor/daniel-hampsey \n[09:50:27] Scraping from base.py:49\n https://www.argyll-bute.gov.uk/my-council/councillors-dire \n ctory/oban-south-and-isles/councillor/amanda-hampsey \n[09:50:28] Scraping from base.py:49\n https://www.argyll-bute.gov.uk/my-council/councillors-dire \n ctory/helensburgh-central/councillor/graham-archibald-hard \n ie \n[09:50:29] Scraping from base.py:49\n https://www.argyll-bute.gov.uk/my-council/councillors-dire \n ctory/kintyre-and-islands/councillor/anne-horn \n[09:50:31] 'NoneType' object has no attribute 'img' handlers.py:36\n Committing batch 1 consisting of 22 files base.py:297\n[09:50:32] Finished attempting to scrape: AGB base.py:345\n","errors":"Traceback (most recent call last):\n File \"/var/task/lgsf/aws_lambda/handlers.py\", line 32, in scraper_worker_handler\n scraper.run(run_log)\n File \"/var/task/lgsf/councillors/scrapers.py\", line 57, in run\n councillor = self.get_single_councillor(councillor_html)\n File \"scrapers/AGB-argyll-and-bute/councillors.py\", line 46, in get_single_councillor\n councillor.photo_url = soup.select_one(\".field--name-field-photo\").img[\nAttributeError: 'NoneType' object has no attribute 'img'\n","start":"2024-08-20 09:50:11.259040","end":"2024-08-20 09:50:32.543438","duration":21}},{"council_id":"BOL","missing":false,"latest_run":{"status_code":1,"log_text":"[08:48:33] Fetching Scraper for: BOL handlers.py:23\n Begin attempting to scrape: BOL handlers.py:27\n[08:48:34] Deleting existing data... base.py:257\n Getting all files in Councillors... base.py:209\n ...found 1 files in Councillors base.py:225\n Deleting batch no. 1 consisting of 1 files base.py:236\n[08:48:35] ...data deleted. base.py:264\n Scraping from base.py:49\n https://www.democracy.bolton.gov.uk/cmis5/People.aspx \n [Errno -2] Name or service not known handlers.py:36\n Finished attempting to scrape: BOL base.py:345\n","errors":"Traceback (most recent call last):\n File \"/opt/python/httpx/_transports/default.py\", line 69, in map_httpcore_exceptions\n yield\n File \"/opt/python/httpx/_transports/default.py\", line 233, in handle_request\n resp = self._pool.handle_request(req)\n File \"/opt/python/httpcore/_sync/connection_pool.py\", line 216, in handle_request\n raise exc from None\n File \"/opt/python/httpcore/_sync/connection_pool.py\", line 196, in handle_request\n response = connection.handle_request(\n File \"/opt/python/httpcore/_sync/connection.py\", line 99, in handle_request\n raise exc\n File \"/opt/python/httpcore/_sync/connection.py\", line 76, in handle_request\n stream = self._connect(request)\n File \"/opt/python/httpcore/_sync/connection.py\", line 122, in _connect\n stream = self._network_backend.connect_tcp(**kwargs)\n File \"/opt/python/httpcore/_backends/sync.py\", line 205, in connect_tcp\n with map_exceptions(exc_map):\n File \"/var/lang/lib/python3.10/contextlib.py\", line 153, in __exit__\n self.gen.throw(typ, value, traceback)\n File \"/opt/python/httpcore/_exceptions.py\", line 14, in map_exceptions\n raise to_exc(exc) from exc\nhttpcore.ConnectError: [Errno -2] Name or service not known\n\nThe above exception was the direct cause of the following exception:\n\nTraceback (most recent call last):\n File \"/var/task/lgsf/aws_lambda/handlers.py\", line 32, in scraper_worker_handler\n scraper.run(run_log)\n File \"/var/task/lgsf/councillors/scrapers.py\", line 55, in run\n for councillor_html in self.get_councillors():\n File \"/var/task/lgsf/councillors/scrapers.py\", line 272, in get_councillors\n req = self.get(\n File \"/var/task/lgsf/scrapers/base.py\", line 55, in get\n response = self.http_client.get(url, headers=headers, timeout=30)\n File \"/opt/python/httpx/_client.py\", line 1054, in get\n return self.request(\n File \"/opt/python/httpx/_client.py\", line 827, in request\n return self.send(request, auth=auth, follow_redirects=follow_redirects)\n File \"/opt/python/httpx/_client.py\", line 914, in send\n response = self._send_handling_auth(\n File \"/opt/python/httpx/_client.py\", line 942, in _send_handling_auth\n response = self._send_handling_redirects(\n File \"/opt/python/httpx/_client.py\", line 979, in _send_handling_redirects\n response = self._send_single_request(request)\n File \"/opt/python/httpx/_client.py\", line 1015, in _send_single_request\n response = transport.handle_request(request)\n File \"/opt/python/httpx/_transports/default.py\", line 232, in handle_request\n with map_httpcore_exceptions():\n File \"/var/lang/lib/python3.10/contextlib.py\", line 153, in __exit__\n self.gen.throw(typ, value, traceback)\n File \"/opt/python/httpx/_transports/default.py\", line 86, in map_httpcore_exceptions\n raise mapped_exc(message) from exc\nhttpx.ConnectError: [Errno -2] Name or service not known\n","start":"2024-08-20 08:48:33.637232","end":"2024-08-20 08:48:35.726792","duration":2}},{"council_id":"CAN","missing":false,"latest_run":{"status_code":1,"log_text":"[10:49:21] Fetching Scraper for: CAN handlers.py:23\n Begin attempting to scrape: CAN handlers.py:27\n[10:49:22] Deleting existing data... base.py:257\n Getting all files in Councillors... base.py:209\n ...found 1 files in Councillors base.py:225\n Deleting batch no. 1 consisting of 1 files base.py:236\n[10:49:23] ...data deleted. base.py:264\n Scraping from base.py:49\n https://www.cannockchasedc.gov.uk/council/about-council/yo \n ur-councillors \n[10:49:25] list index out of range handlers.py:36\n Finished attempting to scrape: CAN base.py:345\n","errors":"Traceback (most recent call last):\n File \"/var/task/lgsf/aws_lambda/handlers.py\", line 32, in scraper_worker_handler\n scraper.run(run_log)\n File \"/var/task/lgsf/councillors/scrapers.py\", line 55, in run\n for councillor_html in self.get_councillors():\n File \"/var/task/lgsf/councillors/scrapers.py\", line 161, in get_councillors\n container = self.get_list_container()\n File \"/var/task/lgsf/councillors/scrapers.py\", line 158, in get_list_container\n return selected[0]\nIndexError: list index out of range\n","start":"2024-08-20 10:49:21.574799","end":"2024-08-20 10:49:25.706525","duration":4}},{"council_id":"CAS","missing":false,"latest_run":{"status_code":1,"log_text":"[09:50:38] Fetching Scraper for: CAS handlers.py:23\n Begin attempting to scrape: CAS handlers.py:27\n Deleting existing data... base.py:257\n[09:50:39] Getting all files in Councillors... base.py:209\n ...found 1 files in Councillors base.py:225\n Deleting batch no. 1 consisting of 1 files base.py:236\n[09:50:40] ...data deleted. base.py:264\n Scraping from https://www.castlepoint.gov.uk/councillors base.py:49\n[09:50:41] Scraping from base.py:49\n https://www.castlepoint.gov.ukhttps://castlepoint.cmis.uk. \n com/castlepoint/Committees/CurrentCommittees.aspx?a=1 \n [Errno -2] Name or service not known handlers.py:36\n[09:50:42] Finished attempting to scrape: CAS base.py:345\n","errors":"Traceback (most recent call last):\n File \"/opt/python/httpx/_transports/default.py\", line 69, in map_httpcore_exceptions\n yield\n File \"/opt/python/httpx/_transports/default.py\", line 233, in handle_request\n resp = self._pool.handle_request(req)\n File \"/opt/python/httpcore/_sync/connection_pool.py\", line 216, in handle_request\n raise exc from None\n File \"/opt/python/httpcore/_sync/connection_pool.py\", line 196, in handle_request\n response = connection.handle_request(\n File \"/opt/python/httpcore/_sync/connection.py\", line 99, in handle_request\n raise exc\n File \"/opt/python/httpcore/_sync/connection.py\", line 76, in handle_request\n stream = self._connect(request)\n File \"/opt/python/httpcore/_sync/connection.py\", line 122, in _connect\n stream = self._network_backend.connect_tcp(**kwargs)\n File \"/opt/python/httpcore/_backends/sync.py\", line 205, in connect_tcp\n with map_exceptions(exc_map):\n File \"/var/lang/lib/python3.10/contextlib.py\", line 153, in __exit__\n self.gen.throw(typ, value, traceback)\n File \"/opt/python/httpcore/_exceptions.py\", line 14, in map_exceptions\n raise to_exc(exc) from exc\nhttpcore.ConnectError: [Errno -2] Name or service not known\n\nThe above exception was the direct cause of the following exception:\n\nTraceback (most recent call last):\n File \"/var/task/lgsf/aws_lambda/handlers.py\", line 32, in scraper_worker_handler\n scraper.run(run_log)\n File \"/var/task/lgsf/councillors/scrapers.py\", line 57, in run\n councillor = self.get_single_councillor(councillor_html)\n File \"scrapers/CAS-castle-point/councillors.py\", line 15, in get_single_councillor\n soup = self.get_page(url)\n File \"/var/task/lgsf/councillors/scrapers.py\", line 141, in get_page\n page = self.get(url, extra_headers=self.extra_headers).text\n File \"/var/task/lgsf/scrapers/base.py\", line 55, in get\n response = self.http_client.get(url, headers=headers, timeout=30)\n File \"/opt/python/httpx/_client.py\", line 1054, in get\n return self.request(\n File \"/opt/python/httpx/_client.py\", line 827, in request\n return self.send(request, auth=auth, follow_redirects=follow_redirects)\n File \"/opt/python/httpx/_client.py\", line 914, in send\n response = self._send_handling_auth(\n File \"/opt/python/httpx/_client.py\", line 942, in _send_handling_auth\n response = self._send_handling_redirects(\n File \"/opt/python/httpx/_client.py\", line 979, in _send_handling_redirects\n response = self._send_single_request(request)\n File \"/opt/python/httpx/_client.py\", line 1015, in _send_single_request\n response = transport.handle_request(request)\n File \"/opt/python/httpx/_transports/default.py\", line 232, in handle_request\n with map_httpcore_exceptions():\n File \"/var/lang/lib/python3.10/contextlib.py\", line 153, in __exit__\n self.gen.throw(typ, value, traceback)\n File \"/opt/python/httpx/_transports/default.py\", line 86, in map_httpcore_exceptions\n raise mapped_exc(message) from exc\nhttpx.ConnectError: [Errno -2] Name or service not known\n","start":"2024-08-20 09:50:38.369075","end":"2024-08-20 09:50:42.012452","duration":3}},{"council_id":"CMD","missing":false,"latest_run":{"status_code":1,"log_text":"[08:55:35] Fetching Scraper for: CMD handlers.py:23\n Begin attempting to scrape: CMD handlers.py:27\n Deleting existing data... base.py:257\n[08:55:36] Getting all files in Councillors... base.py:209\n ...found 1 files in Councillors base.py:225\n Deleting batch no. 1 consisting of 1 files base.py:236\n[08:55:37] ...data deleted. base.py:264\n Scraping from base.py:49\n https://democracy.camden.gov.uk/mgWebService.asmx/GetCounc \n illorsByWard \n Client error '403 Forbidden' for url handlers.py:36\n 'https://democracy.camden.gov.uk/mgWebService.asmx/Get \n CouncillorsByWard' \n For more information check: \n https://developer.mozilla.org/en-US/docs/Web/HTTP/Stat \n us/403 \n Finished attempting to scrape: CMD base.py:345\n","errors":"Traceback (most recent call last):\n File \"/var/task/lgsf/aws_lambda/handlers.py\", line 32, in scraper_worker_handler\n scraper.run(run_log)\n File \"/var/task/lgsf/councillors/scrapers.py\", line 197, in run\n wards = self.get_councillors()\n File \"/var/task/lgsf/councillors/scrapers.py\", line 216, in get_councillors\n req = self.get(self.format_councillor_api_url())\n File \"/var/task/lgsf/scrapers/base.py\", line 56, in get\n response.raise_for_status()\n File \"/opt/python/httpx/_models.py\", line 761, in raise_for_status\n raise HTTPStatusError(message, request=request, response=self)\nhttpx.HTTPStatusError: Client error '403 Forbidden' for url 'https://democracy.camden.gov.uk/mgWebService.asmx/GetCouncillorsByWard'\nFor more information check: https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/403\n","start":"2024-08-20 08:55:35.514187","end":"2024-08-20 08:55:37.666586","duration":2}},{"council_id":"DST","missing":false,"latest_run":{"status_code":1,"log_text":"[10:41:37] Fetching Scraper for: DST handlers.py:23\n Begin attempting to scrape: DST handlers.py:27\n[10:41:38] Deleting existing data... base.py:257\n Getting all files in Councillors... base.py:209\n ...found 1 files in Councillors base.py:225\n Deleting batch no. 1 consisting of 1 files base.py:236\n[10:41:39] ...data deleted. base.py:264\n Scraping from base.py:49\n http://moderngov.dorsetcouncil.gov.uk/mgWebService.asmx/Ge \n tCouncillorsByWard \n[10:41:54] [Errno 110] Connection timed out handlers.py:36\n[10:41:55] Finished attempting to scrape: DST base.py:345\n","errors":"Traceback (most recent call last):\n File \"/opt/python/httpx/_transports/default.py\", line 69, in map_httpcore_exceptions\n yield\n File \"/opt/python/httpx/_transports/default.py\", line 233, in handle_request\n resp = self._pool.handle_request(req)\n File \"/opt/python/httpcore/_sync/connection_pool.py\", line 216, in handle_request\n raise exc from None\n File \"/opt/python/httpcore/_sync/connection_pool.py\", line 196, in handle_request\n response = connection.handle_request(\n File \"/opt/python/httpcore/_sync/connection.py\", line 99, in handle_request\n raise exc\n File \"/opt/python/httpcore/_sync/connection.py\", line 76, in handle_request\n stream = self._connect(request)\n File \"/opt/python/httpcore/_sync/connection.py\", line 122, in _connect\n stream = self._network_backend.connect_tcp(**kwargs)\n File \"/opt/python/httpcore/_backends/sync.py\", line 205, in connect_tcp\n with map_exceptions(exc_map):\n File \"/var/lang/lib/python3.10/contextlib.py\", line 153, in __exit__\n self.gen.throw(typ, value, traceback)\n File \"/opt/python/httpcore/_exceptions.py\", line 14, in map_exceptions\n raise to_exc(exc) from exc\nhttpcore.ConnectTimeout: [Errno 110] Connection timed out\n\nThe above exception was the direct cause of the following exception:\n\nTraceback (most recent call last):\n File \"/var/task/lgsf/aws_lambda/handlers.py\", line 32, in scraper_worker_handler\n scraper.run(run_log)\n File \"/var/task/lgsf/councillors/scrapers.py\", line 197, in run\n wards = self.get_councillors()\n File \"/var/task/lgsf/councillors/scrapers.py\", line 216, in get_councillors\n req = self.get(self.format_councillor_api_url())\n File \"/var/task/lgsf/scrapers/base.py\", line 55, in get\n response = self.http_client.get(url, headers=headers, timeout=30)\n File \"/opt/python/httpx/_client.py\", line 1054, in get\n return self.request(\n File \"/opt/python/httpx/_client.py\", line 827, in request\n return self.send(request, auth=auth, follow_redirects=follow_redirects)\n File \"/opt/python/httpx/_client.py\", line 914, in send\n response = self._send_handling_auth(\n File \"/opt/python/httpx/_client.py\", line 942, in _send_handling_auth\n response = self._send_handling_redirects(\n File \"/opt/python/httpx/_client.py\", line 979, in _send_handling_redirects\n response = self._send_single_request(request)\n File \"/opt/python/httpx/_client.py\", line 1015, in _send_single_request\n response = transport.handle_request(request)\n File \"/opt/python/httpx/_transports/default.py\", line 232, in handle_request\n with map_httpcore_exceptions():\n File \"/var/lang/lib/python3.10/contextlib.py\", line 153, in __exit__\n self.gen.throw(typ, value, traceback)\n File \"/opt/python/httpx/_transports/default.py\", line 86, in map_httpcore_exceptions\n raise mapped_exc(message) from exc\nhttpx.ConnectTimeout: [Errno 110] Connection timed out\n","start":"2024-08-20 10:41:37.516746","end":"2024-08-20 10:41:55.341038","duration":17}},{"council_id":"EAY","missing":false,"latest_run":{"status_code":1,"log_text":"[08:29:39] Fetching Scraper for: EAY handlers.py:23\n Begin attempting to scrape: EAY handlers.py:27\n Deleting existing data... base.py:257\n[08:29:40] Getting all files in Councillors... base.py:209\n ...found 1 files in Councillors base.py:225\n Deleting batch no. 1 consisting of 1 files base.py:236\n[08:29:41] ...data deleted. base.py:264\n Scraping from base.py:49\n https://www.east-ayrshire.gov.uk/CouncilAndGovernment/Abou \n t-the-Council/Councillors-and-Provost/YourCouncillor.aspx \n[08:29:43] Scraping from base.py:49\n https://www.east-ayrshire.gov.uk/CouncilAndGovernment/Abou \n t-the-Council/Councillors-and-Provost/YourCouncillor.aspx? \n 9 \n[08:29:44] 'NoneType' object has no attribute 'find_parent' handlers.py:36\n[08:29:45] Finished attempting to scrape: EAY base.py:345\n","errors":"Traceback (most recent call last):\n File \"/var/task/lgsf/aws_lambda/handlers.py\", line 32, in scraper_worker_handler\n scraper.run(run_log)\n File \"/var/task/lgsf/councillors/scrapers.py\", line 57, in run\n councillor = self.get_single_councillor(councillor_html)\n File \"scrapers/EAY-east-ayrshire/councillors.py\", line 22, in get_single_councillor\n .find_parent(\"div\")\nAttributeError: 'NoneType' object has no attribute 'find_parent'\n","start":"2024-08-20 08:29:39.400448","end":"2024-08-20 08:29:45.127294","duration":5}},{"council_id":"GLG","missing":false,"latest_run":{"status_code":1,"log_text":"[09:42:37] Fetching Scraper for: GLG handlers.py:23\n Begin attempting to scrape: GLG handlers.py:27\n Deleting existing data... base.py:257\n[09:42:38] Getting all files in Councillors... base.py:209\n ...found 1 files in Councillors base.py:225\n Deleting batch no. 1 consisting of 1 files base.py:236\n ...data deleted. base.py:264\n Scraping from base.py:49\n https://www.glasgow.gov.uk/councillorsandcommittees/allMem \n bers.asp?sort=0&page=0&rec=100 \n[09:42:39] Client error '404 Not Found' for url handlers.py:36\n 'https://www.glasgow.gov.uk/councillorsandcommittees/a \n llMembers.asp?sort=0&page=0&rec=100' \n For more information check: \n https://developer.mozilla.org/en-US/docs/Web/HTTP/Stat \n us/404 \n Finished attempting to scrape: GLG base.py:345\n","errors":"Traceback (most recent call last):\n File \"/var/task/lgsf/aws_lambda/handlers.py\", line 32, in scraper_worker_handler\n scraper.run(run_log)\n File \"/var/task/lgsf/councillors/scrapers.py\", line 55, in run\n for councillor_html in self.get_councillors():\n File \"/var/task/lgsf/councillors/scrapers.py\", line 161, in get_councillors\n container = self.get_list_container()\n File \"/var/task/lgsf/councillors/scrapers.py\", line 152, in get_list_container\n self.base_url_soup = self.get_page(self.base_url)\n File \"/var/task/lgsf/councillors/scrapers.py\", line 141, in get_page\n page = self.get(url, extra_headers=self.extra_headers).text\n File \"/var/task/lgsf/scrapers/base.py\", line 56, in get\n response.raise_for_status()\n File \"/opt/python/httpx/_models.py\", line 761, in raise_for_status\n raise HTTPStatusError(message, request=request, response=self)\nhttpx.HTTPStatusError: Client error '404 Not Found' for url 'https://www.glasgow.gov.uk/councillorsandcommittees/allMembers.asp?sort=0&page=0&rec=100'\nFor more information check: https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/404\n","start":"2024-08-20 09:42:37.206754","end":"2024-08-20 09:42:39.305338","duration":2}},{"council_id":"GLS","missing":false,"latest_run":{"status_code":1,"log_text":"[08:48:53] Fetching Scraper for: GLS handlers.py:23\n Begin attempting to scrape: GLS handlers.py:27\n Deleting existing data... base.py:257\n[08:48:54] Getting all files in Councillors... base.py:209\n ...found 1 files in Councillors base.py:225\n Deleting batch no. 1 consisting of 1 files base.py:236\n ...data deleted. base.py:264\n Scraping from base.py:49\n http://glostext.gloucestershire.gov.uk//mgWebService.asmx/ \n GetCouncillorsByWard \n[08:49:10] [Errno 110] Connection timed out handlers.py:36\n Finished attempting to scrape: GLS base.py:345\n","errors":"Traceback (most recent call last):\n File \"/opt/python/httpx/_transports/default.py\", line 69, in map_httpcore_exceptions\n yield\n File \"/opt/python/httpx/_transports/default.py\", line 233, in handle_request\n resp = self._pool.handle_request(req)\n File \"/opt/python/httpcore/_sync/connection_pool.py\", line 216, in handle_request\n raise exc from None\n File \"/opt/python/httpcore/_sync/connection_pool.py\", line 196, in handle_request\n response = connection.handle_request(\n File \"/opt/python/httpcore/_sync/connection.py\", line 99, in handle_request\n raise exc\n File \"/opt/python/httpcore/_sync/connection.py\", line 76, in handle_request\n stream = self._connect(request)\n File \"/opt/python/httpcore/_sync/connection.py\", line 122, in _connect\n stream = self._network_backend.connect_tcp(**kwargs)\n File \"/opt/python/httpcore/_backends/sync.py\", line 205, in connect_tcp\n with map_exceptions(exc_map):\n File \"/var/lang/lib/python3.10/contextlib.py\", line 153, in __exit__\n self.gen.throw(typ, value, traceback)\n File \"/opt/python/httpcore/_exceptions.py\", line 14, in map_exceptions\n raise to_exc(exc) from exc\nhttpcore.ConnectTimeout: [Errno 110] Connection timed out\n\nThe above exception was the direct cause of the following exception:\n\nTraceback (most recent call last):\n File \"/var/task/lgsf/aws_lambda/handlers.py\", line 32, in scraper_worker_handler\n scraper.run(run_log)\n File \"/var/task/lgsf/councillors/scrapers.py\", line 197, in run\n wards = self.get_councillors()\n File \"/var/task/lgsf/councillors/scrapers.py\", line 216, in get_councillors\n req = self.get(self.format_councillor_api_url())\n File \"/var/task/lgsf/scrapers/base.py\", line 55, in get\n response = self.http_client.get(url, headers=headers, timeout=30)\n File \"/opt/python/httpx/_client.py\", line 1054, in get\n return self.request(\n File \"/opt/python/httpx/_client.py\", line 827, in request\n return self.send(request, auth=auth, follow_redirects=follow_redirects)\n File \"/opt/python/httpx/_client.py\", line 914, in send\n response = self._send_handling_auth(\n File \"/opt/python/httpx/_client.py\", line 942, in _send_handling_auth\n response = self._send_handling_redirects(\n File \"/opt/python/httpx/_client.py\", line 979, in _send_handling_redirects\n response = self._send_single_request(request)\n File \"/opt/python/httpx/_client.py\", line 1015, in _send_single_request\n response = transport.handle_request(request)\n File \"/opt/python/httpx/_transports/default.py\", line 232, in handle_request\n with map_httpcore_exceptions():\n File \"/var/lang/lib/python3.10/contextlib.py\", line 153, in __exit__\n self.gen.throw(typ, value, traceback)\n File \"/opt/python/httpx/_transports/default.py\", line 86, in map_httpcore_exceptions\n raise mapped_exc(message) from exc\nhttpx.ConnectTimeout: [Errno 110] Connection timed out\n","start":"2024-08-20 08:48:53.090177","end":"2024-08-20 08:49:10.787938","duration":17}},{"council_id":"GRE","missing":false,"latest_run":{"status_code":1,"log_text":"[09:49:29] Fetching Scraper for: GRE handlers.py:23\n Begin attempting to scrape: GRE handlers.py:27\n Deleting existing data... base.py:257\n[09:49:30] Getting all files in Councillors... base.py:209\n ...found 1 files in Councillors base.py:225\n Deleting batch no. 1 consisting of 1 files base.py:236\n[09:49:31] ...data deleted. base.py:264\n Scraping from base.py:49\n https://committees.royalgreenwich.gov.uk/Councillors/tabid \n /63/ScreenMode/Alphabetical/Default.aspx \n[09:49:34] Client error '404 Not Found' for url handlers.py:36\n 'https://committees.royalgreenwich.gov.uk/mgError.aspx \n ' \n For more information check: \n https://developer.mozilla.org/en-US/docs/Web/HTTP/Stat \n us/404 \n Finished attempting to scrape: GRE base.py:345\n","errors":"Traceback (most recent call last):\n File \"/var/task/lgsf/aws_lambda/handlers.py\", line 32, in scraper_worker_handler\n scraper.run(run_log)\n File \"/var/task/lgsf/councillors/scrapers.py\", line 55, in run\n for councillor_html in self.get_councillors():\n File \"/var/task/lgsf/councillors/scrapers.py\", line 272, in get_councillors\n req = self.get(\n File \"/var/task/lgsf/scrapers/base.py\", line 56, in get\n response.raise_for_status()\n File \"/opt/python/httpx/_models.py\", line 761, in raise_for_status\n raise HTTPStatusError(message, request=request, response=self)\nhttpx.HTTPStatusError: Client error '404 Not Found' for url 'https://committees.royalgreenwich.gov.uk/mgError.aspx'\nFor more information check: https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/404\n","start":"2024-08-20 09:49:29.474700","end":"2024-08-20 09:49:34.245088","duration":4}},{"council_id":"SHE","missing":false,"latest_run":{"status_code":null,"log_text":"[11:28:20] Fetching Scraper for: SHE handlers.py:22\n Begin attempting to scrape: SHE handlers.py:25\n Deleting existing data... base.py:234\n Getting all files in SHE... base.py:186\n[11:28:21] Getting all files in SHE/json... base.py:186\n ...found 30 files in SHE/json base.py:202\n Getting all files in SHE/raw... base.py:186\n ...found 30 files in SHE/raw base.py:202\n ...found 61 files in SHE base.py:202\n Deleting batch no. 1 consisting of 61 files base.py:211\n[11:28:32] An error occurred (ThrottlingException) when calling handlers.py:34\n the CreateCommit operation (reached max retries: 4): \n Rate exceeded \n Finished attempting to scrape: SHE base.py:319\n","errors":"An error occurred (ThrottlingException) when calling the CreateCommit operation (reached max retries: 4): Rate exceeded","start":"2022-04-04 11:28:20.509898","end":"2022-04-04 11:28:32.871624","duration":12}},{"council_id":"STG","missing":false,"latest_run":{"status_code":1,"log_text":"[10:49:59] Fetching Scraper for: STG handlers.py:23\n[10:50:00] Begin attempting to scrape: STG handlers.py:27\n Deleting existing data... base.py:257\n Getting all files in Councillors... base.py:209\n[10:50:01] Getting all files in Councillors/json... base.py:209\n ...found 22 files in Councillors/json base.py:225\n Getting all files in Councillors/raw... base.py:209\n ...found 22 files in Councillors/raw base.py:225\n ...found 45 files in Councillors base.py:225\n Deleting batch no. 1 consisting of 45 files base.py:236\n[10:50:02] ...data deleted. base.py:264\n Scraping from base.py:49\n https://www.stirling.gov.uk/council-and-committees/politic \n ians-and-elections/councillors/ \n[10:50:03] Scraping from base.py:49\n https://www.stirling.gov.uk/council-and-committees/politic \n ians-and-elections/councillors/elaine-watterson/ \n[10:50:04] Scraping from base.py:49\n https://www.stirling.gov.uk/council-and-committees/politic \n ians-and-elections/councillors/gene-maxwell/ \n[10:50:06] Scraping from base.py:49\n https://www.stirling.gov.uk/council-and-committees/politic \n ians-and-elections/councillors/martin-earl/ \n[10:50:07] Scraping from base.py:49\n https://www.stirling.gov.uk/council-and-committees/politic \n ians-and-elections/councillors/gerry-mcgarvey/ \n[10:50:08] Scraping from base.py:49\n https://www.stirling.gov.uk/council-and-committees/politic \n ians-and-elections/councillors/paul-henke/ \n[10:50:09] Scraping from base.py:49\n https://www.stirling.gov.uk/council-and-committees/politic \n ians-and-elections/councillors/rosemary-fraser/ \n[10:50:11] Scraping from base.py:49\n https://www.stirling.gov.uk/council-and-committees/politic \n ians-and-elections/councillors/alasdair-tollemache/ \n[10:50:12] Scraping from base.py:49\n https://www.stirling.gov.uk/council-and-committees/politic \n ians-and-elections/councillors/david-wilson/ \n[10:50:13] 'NoneType' object is not subscriptable handlers.py:36\n Committing batch 1 consisting of 14 files base.py:297\n[10:50:14] Finished attempting to scrape: STG base.py:345\n","errors":"Traceback (most recent call last):\n File \"/var/task/lgsf/aws_lambda/handlers.py\", line 32, in scraper_worker_handler\n scraper.run(run_log)\n File \"/var/task/lgsf/councillors/scrapers.py\", line 57, in run\n councillor = self.get_single_councillor(councillor_html)\n File \"scrapers/STG-stirling/councillors.py\", line 42, in get_single_councillor\n councillor.email = soup.select_one(\"a[href^=mailto]\")[\nTypeError: 'NoneType' object is not subscriptable\n","start":"2024-08-20 10:49:59.968753","end":"2024-08-20 10:50:14.910966","duration":14}},{"council_id":"THE","missing":false,"latest_run":{"status_code":1,"log_text":"[08:54:43] Fetching Scraper for: THE handlers.py:23\n Begin attempting to scrape: THE handlers.py:27\n Deleting existing data... base.py:257\n[08:54:44] Getting all files in Councillors... base.py:209\n ...found 1 files in Councillors base.py:225\n Deleting batch no. 1 consisting of 1 files base.py:236\n ...data deleted. base.py:264\n Scraping from base.py:49\n https://www.threerivers.gov.uk/listing/councillors \n[08:54:46] 'NoneType' object has no attribute 'findNext' handlers.py:36\n Finished attempting to scrape: THE base.py:345\n","errors":"Traceback (most recent call last):\n File \"/var/task/lgsf/aws_lambda/handlers.py\", line 32, in scraper_worker_handler\n scraper.run(run_log)\n File \"/var/task/lgsf/councillors/scrapers.py\", line 55, in run\n for councillor_html in self.get_councillors():\n File \"/var/task/lgsf/councillors/scrapers.py\", line 161, in get_councillors\n container = self.get_list_container()\n File \"scrapers/THE-three-rivers/councillors.py\", line 15, in get_list_container\n return soup.find(\"h3\", text=\"District Councillor\").findNext(\"ul\")\nAttributeError: 'NoneType' object has no attribute 'findNext'\n","start":"2024-08-20 08:54:43.114540","end":"2024-08-20 08:54:46.867940","duration":3}},{"council_id":"TWH","missing":false,"latest_run":{"status_code":1,"log_text":"[09:49:10] Fetching Scraper for: TWH handlers.py:23\n Begin attempting to scrape: TWH handlers.py:27\n[09:49:11] Deleting existing data... base.py:257\n Getting all files in Councillors... base.py:209\n Getting all files in Councillors/json... base.py:209\n ...found 45 files in Councillors/json base.py:225\n Getting all files in Councillors/raw... base.py:209\n[09:49:12] ...found 45 files in Councillors/raw base.py:225\n ...found 91 files in Councillors base.py:225\n Deleting batch no. 1 consisting of 91 files base.py:236\n ...data deleted. base.py:264\n Scraping from base.py:49\n http://democracy.towerhamlets.gov.uk/mgWebService.asmx/Get \n CouncillorsByWard \n [SSL: CERTIFICATE_VERIFY_FAILED] certificate verify handlers.py:36\n failed: unable to get local issuer certificate \n (_ssl.c:1007) \n[09:49:13] Finished attempting to scrape: TWH base.py:345\n","errors":"Traceback (most recent call last):\n File \"/opt/python/httpx/_transports/default.py\", line 69, in map_httpcore_exceptions\n yield\n File \"/opt/python/httpx/_transports/default.py\", line 233, in handle_request\n resp = self._pool.handle_request(req)\n File \"/opt/python/httpcore/_sync/connection_pool.py\", line 216, in handle_request\n raise exc from None\n File \"/opt/python/httpcore/_sync/connection_pool.py\", line 196, in handle_request\n response = connection.handle_request(\n File \"/opt/python/httpcore/_sync/connection.py\", line 99, in handle_request\n raise exc\n File \"/opt/python/httpcore/_sync/connection.py\", line 76, in handle_request\n stream = self._connect(request)\n File \"/opt/python/httpcore/_sync/connection.py\", line 154, in _connect\n stream = stream.start_tls(**kwargs)\n File \"/opt/python/httpcore/_backends/sync.py\", line 152, in start_tls\n with map_exceptions(exc_map):\n File \"/var/lang/lib/python3.10/contextlib.py\", line 153, in __exit__\n self.gen.throw(typ, value, traceback)\n File \"/opt/python/httpcore/_exceptions.py\", line 14, in map_exceptions\n raise to_exc(exc) from exc\nhttpcore.ConnectError: [SSL: CERTIFICATE_VERIFY_FAILED] certificate verify failed: unable to get local issuer certificate (_ssl.c:1007)\n\nThe above exception was the direct cause of the following exception:\n\nTraceback (most recent call last):\n File \"/var/task/lgsf/aws_lambda/handlers.py\", line 32, in scraper_worker_handler\n scraper.run(run_log)\n File \"/var/task/lgsf/councillors/scrapers.py\", line 197, in run\n wards = self.get_councillors()\n File \"/var/task/lgsf/councillors/scrapers.py\", line 216, in get_councillors\n req = self.get(self.format_councillor_api_url())\n File \"/var/task/lgsf/scrapers/base.py\", line 55, in get\n response = self.http_client.get(url, headers=headers, timeout=30)\n File \"/opt/python/httpx/_client.py\", line 1054, in get\n return self.request(\n File \"/opt/python/httpx/_client.py\", line 827, in request\n return self.send(request, auth=auth, follow_redirects=follow_redirects)\n File \"/opt/python/httpx/_client.py\", line 914, in send\n response = self._send_handling_auth(\n File \"/opt/python/httpx/_client.py\", line 942, in _send_handling_auth\n response = self._send_handling_redirects(\n File \"/opt/python/httpx/_client.py\", line 979, in _send_handling_redirects\n response = self._send_single_request(request)\n File \"/opt/python/httpx/_client.py\", line 1015, in _send_single_request\n response = transport.handle_request(request)\n File \"/opt/python/httpx/_transports/default.py\", line 232, in handle_request\n with map_httpcore_exceptions():\n File \"/var/lang/lib/python3.10/contextlib.py\", line 153, in __exit__\n self.gen.throw(typ, value, traceback)\n File \"/opt/python/httpx/_transports/default.py\", line 86, in map_httpcore_exceptions\n raise mapped_exc(message) from exc\nhttpx.ConnectError: [SSL: CERTIFICATE_VERIFY_FAILED] certificate verify failed: unable to get local issuer certificate (_ssl.c:1007)\n","start":"2024-08-20 09:49:10.549084","end":"2024-08-20 09:49:13.302217","duration":2}}] +[{"council_id":"AGB","missing":false,"latest_run":{"status_code":1,"log_text":"[09:01:42] Fetching Scraper for: AGB handlers.py:23\n Begin attempting to scrape: AGB handlers.py:27\n[09:01:43] Deleting existing data... base.py:257\n Getting all files in Councillors... base.py:209\n Getting all files in Councillors/json... base.py:209\n ...found 11 files in Councillors/json base.py:225\n Getting all files in Councillors/raw... base.py:209\n ...found 11 files in Councillors/raw base.py:225\n ...found 23 files in Councillors base.py:225\n Deleting batch no. 1 consisting of 23 files base.py:236\n[09:01:44] ...data deleted. base.py:264\n Scraping from base.py:49\n https://www.argyll-bute.gov.uk/councillor_list \n[09:01:51] Scraping from base.py:49\n https://www.argyll-bute.gov.uk/my-council/councillors-dire \n ctory/south-kintyre/councillor/john-armour \n[09:01:52] Scraping from base.py:49\n https://www.argyll-bute.gov.uk/my-council/councillors-dire \n ctory/cowal/councillor/gordon-blair \n[09:01:53] Scraping from base.py:49\n https://www.argyll-bute.gov.uk/my-council/councillors-dire \n ctory/mid-argyll/councillor/jan-brown \n[09:01:54] Scraping from base.py:49\n https://www.argyll-bute.gov.uk/my-council/councillors-dire \n ctory/helensburgh-and-lomond-south/councillor/math-campbel \n l-sturgess \n[09:01:55] Scraping from base.py:49\n https://www.argyll-bute.gov.uk/my-council/councillors-dire \n ctory/mid-argyll/councillor/garret-corner \n[09:01:56] Scraping from base.py:49\n https://www.argyll-bute.gov.uk/my-council/councillors-dire \n ctory/lomond-north/councillor/maurice-corry \n[09:01:58] Scraping from base.py:49\n https://www.argyll-bute.gov.uk/my-council/councillors-dire \n ctory/dunoon/councillor/audrey-e-forrest \n[09:01:59] Scraping from base.py:49\n https://www.argyll-bute.gov.uk/my-council/councillors-dire \n ctory/oban-north-and-lorn/councillor/kieron-green \n[09:02:00] Scraping from base.py:49\n https://www.argyll-bute.gov.uk/my-council/councillors-dire \n ctory/dunoon/councillor/daniel-hampsey \n[09:02:01] Scraping from base.py:49\n https://www.argyll-bute.gov.uk/my-council/councillors-dire \n ctory/oban-south-and-isles/councillor/amanda-hampsey \n[09:02:03] Scraping from base.py:49\n https://www.argyll-bute.gov.uk/my-council/councillors-dire \n ctory/helensburgh-central/councillor/graham-archibald-hard \n ie \n[09:02:04] Scraping from base.py:49\n https://www.argyll-bute.gov.uk/my-council/councillors-dire \n ctory/kintyre-and-islands/councillor/anne-horn \n[09:02:05] 'NoneType' object has no attribute 'img' handlers.py:36\n Committing batch 1 consisting of 22 files base.py:297\n[09:02:06] Finished attempting to scrape: AGB base.py:345\n","errors":"Traceback (most recent call last):\n File \"/var/task/lgsf/aws_lambda/handlers.py\", line 32, in scraper_worker_handler\n scraper.run(run_log)\n File \"/var/task/lgsf/councillors/scrapers.py\", line 57, in run\n councillor = self.get_single_councillor(councillor_html)\n File \"scrapers/AGB-argyll-and-bute/councillors.py\", line 46, in get_single_councillor\n councillor.photo_url = soup.select_one(\".field--name-field-photo\").img[\nAttributeError: 'NoneType' object has no attribute 'img'\n","start":"2024-08-21 09:01:42.619693","end":"2024-08-21 09:02:06.914830","duration":24}},{"council_id":"BOL","missing":false,"latest_run":{"status_code":1,"log_text":"[08:19:15] Fetching Scraper for: BOL handlers.py:23\n Begin attempting to scrape: BOL handlers.py:27\n Deleting existing data... base.py:257\n Getting all files in Councillors... base.py:209\n[08:19:16] ...found 1 files in Councillors base.py:225\n Deleting batch no. 1 consisting of 1 files base.py:236\n ...data deleted. base.py:264\n Scraping from base.py:49\n https://www.democracy.bolton.gov.uk/cmis5/People.aspx \n [Errno -2] Name or service not known handlers.py:36\n[08:19:17] Finished attempting to scrape: BOL base.py:345\n","errors":"Traceback (most recent call last):\n File \"/opt/python/httpx/_transports/default.py\", line 69, in map_httpcore_exceptions\n yield\n File \"/opt/python/httpx/_transports/default.py\", line 233, in handle_request\n resp = self._pool.handle_request(req)\n File \"/opt/python/httpcore/_sync/connection_pool.py\", line 216, in handle_request\n raise exc from None\n File \"/opt/python/httpcore/_sync/connection_pool.py\", line 196, in handle_request\n response = connection.handle_request(\n File \"/opt/python/httpcore/_sync/connection.py\", line 99, in handle_request\n raise exc\n File \"/opt/python/httpcore/_sync/connection.py\", line 76, in handle_request\n stream = self._connect(request)\n File \"/opt/python/httpcore/_sync/connection.py\", line 122, in _connect\n stream = self._network_backend.connect_tcp(**kwargs)\n File \"/opt/python/httpcore/_backends/sync.py\", line 205, in connect_tcp\n with map_exceptions(exc_map):\n File \"/var/lang/lib/python3.10/contextlib.py\", line 153, in __exit__\n self.gen.throw(typ, value, traceback)\n File \"/opt/python/httpcore/_exceptions.py\", line 14, in map_exceptions\n raise to_exc(exc) from exc\nhttpcore.ConnectError: [Errno -2] Name or service not known\n\nThe above exception was the direct cause of the following exception:\n\nTraceback (most recent call last):\n File \"/var/task/lgsf/aws_lambda/handlers.py\", line 32, in scraper_worker_handler\n scraper.run(run_log)\n File \"/var/task/lgsf/councillors/scrapers.py\", line 55, in run\n for councillor_html in self.get_councillors():\n File \"/var/task/lgsf/councillors/scrapers.py\", line 272, in get_councillors\n req = self.get(\n File \"/var/task/lgsf/scrapers/base.py\", line 55, in get\n response = self.http_client.get(url, headers=headers, timeout=30)\n File \"/opt/python/httpx/_client.py\", line 1054, in get\n return self.request(\n File \"/opt/python/httpx/_client.py\", line 827, in request\n return self.send(request, auth=auth, follow_redirects=follow_redirects)\n File \"/opt/python/httpx/_client.py\", line 914, in send\n response = self._send_handling_auth(\n File \"/opt/python/httpx/_client.py\", line 942, in _send_handling_auth\n response = self._send_handling_redirects(\n File \"/opt/python/httpx/_client.py\", line 979, in _send_handling_redirects\n response = self._send_single_request(request)\n File \"/opt/python/httpx/_client.py\", line 1015, in _send_single_request\n response = transport.handle_request(request)\n File \"/opt/python/httpx/_transports/default.py\", line 232, in handle_request\n with map_httpcore_exceptions():\n File \"/var/lang/lib/python3.10/contextlib.py\", line 153, in __exit__\n self.gen.throw(typ, value, traceback)\n File \"/opt/python/httpx/_transports/default.py\", line 86, in map_httpcore_exceptions\n raise mapped_exc(message) from exc\nhttpx.ConnectError: [Errno -2] Name or service not known\n","start":"2024-08-21 08:19:15.073473","end":"2024-08-21 08:19:17.107479","duration":2}},{"council_id":"CAN","missing":false,"latest_run":{"status_code":1,"log_text":"[09:18:51] Fetching Scraper for: CAN handlers.py:23\n Begin attempting to scrape: CAN handlers.py:27\n Deleting existing data... base.py:257\n Getting all files in Councillors... base.py:209\n[09:18:52] ...found 1 files in Councillors base.py:225\n Deleting batch no. 1 consisting of 1 files base.py:236\n ...data deleted. base.py:264\n Scraping from base.py:49\n https://www.cannockchasedc.gov.uk/council/about-council/yo \n ur-councillors \n[09:18:54] list index out of range handlers.py:36\n[09:18:55] Finished attempting to scrape: CAN base.py:345\n","errors":"Traceback (most recent call last):\n File \"/var/task/lgsf/aws_lambda/handlers.py\", line 32, in scraper_worker_handler\n scraper.run(run_log)\n File \"/var/task/lgsf/councillors/scrapers.py\", line 55, in run\n for councillor_html in self.get_councillors():\n File \"/var/task/lgsf/councillors/scrapers.py\", line 161, in get_councillors\n container = self.get_list_container()\n File \"/var/task/lgsf/councillors/scrapers.py\", line 158, in get_list_container\n return selected[0]\nIndexError: list index out of range\n","start":"2024-08-21 09:18:51.070275","end":"2024-08-21 09:18:55.140902","duration":4}},{"council_id":"CAS","missing":false,"latest_run":{"status_code":1,"log_text":"[10:38:10] Fetching Scraper for: CAS handlers.py:23\n Begin attempting to scrape: CAS handlers.py:27\n Deleting existing data... base.py:257\n Getting all files in Councillors... base.py:209\n[10:38:11] ...found 1 files in Councillors base.py:225\n Deleting batch no. 1 consisting of 1 files base.py:236\n ...data deleted. base.py:264\n Scraping from https://www.castlepoint.gov.uk/councillors base.py:49\n[10:38:13] Scraping from base.py:49\n https://www.castlepoint.gov.ukhttps://castlepoint.cmis.uk. \n com/castlepoint/Committees/CurrentCommittees.aspx?a=1 \n [Errno -2] Name or service not known handlers.py:36\n Finished attempting to scrape: CAS base.py:345\n","errors":"Traceback (most recent call last):\n File \"/opt/python/httpx/_transports/default.py\", line 69, in map_httpcore_exceptions\n yield\n File \"/opt/python/httpx/_transports/default.py\", line 233, in handle_request\n resp = self._pool.handle_request(req)\n File \"/opt/python/httpcore/_sync/connection_pool.py\", line 216, in handle_request\n raise exc from None\n File \"/opt/python/httpcore/_sync/connection_pool.py\", line 196, in handle_request\n response = connection.handle_request(\n File \"/opt/python/httpcore/_sync/connection.py\", line 99, in handle_request\n raise exc\n File \"/opt/python/httpcore/_sync/connection.py\", line 76, in handle_request\n stream = self._connect(request)\n File \"/opt/python/httpcore/_sync/connection.py\", line 122, in _connect\n stream = self._network_backend.connect_tcp(**kwargs)\n File \"/opt/python/httpcore/_backends/sync.py\", line 205, in connect_tcp\n with map_exceptions(exc_map):\n File \"/var/lang/lib/python3.10/contextlib.py\", line 153, in __exit__\n self.gen.throw(typ, value, traceback)\n File \"/opt/python/httpcore/_exceptions.py\", line 14, in map_exceptions\n raise to_exc(exc) from exc\nhttpcore.ConnectError: [Errno -2] Name or service not known\n\nThe above exception was the direct cause of the following exception:\n\nTraceback (most recent call last):\n File \"/var/task/lgsf/aws_lambda/handlers.py\", line 32, in scraper_worker_handler\n scraper.run(run_log)\n File \"/var/task/lgsf/councillors/scrapers.py\", line 57, in run\n councillor = self.get_single_councillor(councillor_html)\n File \"scrapers/CAS-castle-point/councillors.py\", line 15, in get_single_councillor\n soup = self.get_page(url)\n File \"/var/task/lgsf/councillors/scrapers.py\", line 141, in get_page\n page = self.get(url, extra_headers=self.extra_headers).text\n File \"/var/task/lgsf/scrapers/base.py\", line 55, in get\n response = self.http_client.get(url, headers=headers, timeout=30)\n File \"/opt/python/httpx/_client.py\", line 1054, in get\n return self.request(\n File \"/opt/python/httpx/_client.py\", line 827, in request\n return self.send(request, auth=auth, follow_redirects=follow_redirects)\n File \"/opt/python/httpx/_client.py\", line 914, in send\n response = self._send_handling_auth(\n File \"/opt/python/httpx/_client.py\", line 942, in _send_handling_auth\n response = self._send_handling_redirects(\n File \"/opt/python/httpx/_client.py\", line 979, in _send_handling_redirects\n response = self._send_single_request(request)\n File \"/opt/python/httpx/_client.py\", line 1015, in _send_single_request\n response = transport.handle_request(request)\n File \"/opt/python/httpx/_transports/default.py\", line 232, in handle_request\n with map_httpcore_exceptions():\n File \"/var/lang/lib/python3.10/contextlib.py\", line 153, in __exit__\n self.gen.throw(typ, value, traceback)\n File \"/opt/python/httpx/_transports/default.py\", line 86, in map_httpcore_exceptions\n raise mapped_exc(message) from exc\nhttpx.ConnectError: [Errno -2] Name or service not known\n","start":"2024-08-21 10:38:10.079757","end":"2024-08-21 10:38:13.578660","duration":3}},{"council_id":"CMD","missing":false,"latest_run":{"status_code":1,"log_text":"[09:55:24] Fetching Scraper for: CMD handlers.py:23\n Begin attempting to scrape: CMD handlers.py:27\n Deleting existing data... base.py:257\n[09:55:25] Getting all files in Councillors... base.py:209\n ...found 1 files in Councillors base.py:225\n Deleting batch no. 1 consisting of 1 files base.py:236\n[09:55:26] ...data deleted. base.py:264\n Scraping from base.py:49\n https://democracy.camden.gov.uk/mgWebService.asmx/GetCounc \n illorsByWard \n Client error '403 Forbidden' for url handlers.py:36\n 'https://democracy.camden.gov.uk/mgWebService.asmx/Get \n CouncillorsByWard' \n For more information check: \n https://developer.mozilla.org/en-US/docs/Web/HTTP/Stat \n us/403 \n Finished attempting to scrape: CMD base.py:345\n","errors":"Traceback (most recent call last):\n File \"/var/task/lgsf/aws_lambda/handlers.py\", line 32, in scraper_worker_handler\n scraper.run(run_log)\n File \"/var/task/lgsf/councillors/scrapers.py\", line 197, in run\n wards = self.get_councillors()\n File \"/var/task/lgsf/councillors/scrapers.py\", line 216, in get_councillors\n req = self.get(self.format_councillor_api_url())\n File \"/var/task/lgsf/scrapers/base.py\", line 56, in get\n response.raise_for_status()\n File \"/opt/python/httpx/_models.py\", line 761, in raise_for_status\n raise HTTPStatusError(message, request=request, response=self)\nhttpx.HTTPStatusError: Client error '403 Forbidden' for url 'https://democracy.camden.gov.uk/mgWebService.asmx/GetCouncillorsByWard'\nFor more information check: https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/403\n","start":"2024-08-21 09:55:24.520711","end":"2024-08-21 09:55:26.661587","duration":2}},{"council_id":"DST","missing":false,"latest_run":{"status_code":1,"log_text":"[08:52:32] Fetching Scraper for: DST handlers.py:23\n Begin attempting to scrape: DST handlers.py:27\n[08:52:33] Deleting existing data... base.py:257\n Getting all files in Councillors... base.py:209\n ...found 1 files in Councillors base.py:225\n Deleting batch no. 1 consisting of 1 files base.py:236\n[08:52:34] ...data deleted. base.py:264\n Scraping from base.py:49\n http://moderngov.dorsetcouncil.gov.uk/mgWebService.asmx/Ge \n tCouncillorsByWard \n[08:52:50] [Errno 110] Connection timed out handlers.py:36\n Finished attempting to scrape: DST base.py:345\n","errors":"Traceback (most recent call last):\n File \"/opt/python/httpx/_transports/default.py\", line 69, in map_httpcore_exceptions\n yield\n File \"/opt/python/httpx/_transports/default.py\", line 233, in handle_request\n resp = self._pool.handle_request(req)\n File \"/opt/python/httpcore/_sync/connection_pool.py\", line 216, in handle_request\n raise exc from None\n File \"/opt/python/httpcore/_sync/connection_pool.py\", line 196, in handle_request\n response = connection.handle_request(\n File \"/opt/python/httpcore/_sync/connection.py\", line 99, in handle_request\n raise exc\n File \"/opt/python/httpcore/_sync/connection.py\", line 76, in handle_request\n stream = self._connect(request)\n File \"/opt/python/httpcore/_sync/connection.py\", line 122, in _connect\n stream = self._network_backend.connect_tcp(**kwargs)\n File \"/opt/python/httpcore/_backends/sync.py\", line 205, in connect_tcp\n with map_exceptions(exc_map):\n File \"/var/lang/lib/python3.10/contextlib.py\", line 153, in __exit__\n self.gen.throw(typ, value, traceback)\n File \"/opt/python/httpcore/_exceptions.py\", line 14, in map_exceptions\n raise to_exc(exc) from exc\nhttpcore.ConnectTimeout: [Errno 110] Connection timed out\n\nThe above exception was the direct cause of the following exception:\n\nTraceback (most recent call last):\n File \"/var/task/lgsf/aws_lambda/handlers.py\", line 32, in scraper_worker_handler\n scraper.run(run_log)\n File \"/var/task/lgsf/councillors/scrapers.py\", line 197, in run\n wards = self.get_councillors()\n File \"/var/task/lgsf/councillors/scrapers.py\", line 216, in get_councillors\n req = self.get(self.format_councillor_api_url())\n File \"/var/task/lgsf/scrapers/base.py\", line 55, in get\n response = self.http_client.get(url, headers=headers, timeout=30)\n File \"/opt/python/httpx/_client.py\", line 1054, in get\n return self.request(\n File \"/opt/python/httpx/_client.py\", line 827, in request\n return self.send(request, auth=auth, follow_redirects=follow_redirects)\n File \"/opt/python/httpx/_client.py\", line 914, in send\n response = self._send_handling_auth(\n File \"/opt/python/httpx/_client.py\", line 942, in _send_handling_auth\n response = self._send_handling_redirects(\n File \"/opt/python/httpx/_client.py\", line 979, in _send_handling_redirects\n response = self._send_single_request(request)\n File \"/opt/python/httpx/_client.py\", line 1015, in _send_single_request\n response = transport.handle_request(request)\n File \"/opt/python/httpx/_transports/default.py\", line 232, in handle_request\n with map_httpcore_exceptions():\n File \"/var/lang/lib/python3.10/contextlib.py\", line 153, in __exit__\n self.gen.throw(typ, value, traceback)\n File \"/opt/python/httpx/_transports/default.py\", line 86, in map_httpcore_exceptions\n raise mapped_exc(message) from exc\nhttpx.ConnectTimeout: [Errno 110] Connection timed out\n","start":"2024-08-21 08:52:32.801349","end":"2024-08-21 08:52:50.554784","duration":17}},{"council_id":"EAY","missing":false,"latest_run":{"status_code":1,"log_text":"[08:19:20] Fetching Scraper for: EAY handlers.py:23\n[08:19:21] Begin attempting to scrape: EAY handlers.py:27\n Deleting existing data... base.py:257\n Getting all files in Councillors... base.py:209\n[08:19:22] ...found 1 files in Councillors base.py:225\n Deleting batch no. 1 consisting of 1 files base.py:236\n ...data deleted. base.py:264\n Scraping from base.py:49\n https://www.east-ayrshire.gov.uk/CouncilAndGovernment/Abou \n t-the-Council/Councillors-and-Provost/YourCouncillor.aspx \n[08:19:23] Scraping from base.py:49\n https://www.east-ayrshire.gov.uk/CouncilAndGovernment/Abou \n t-the-Council/Councillors-and-Provost/YourCouncillor.aspx? \n 9 \n[08:19:24] 'NoneType' object has no attribute 'find_parent' handlers.py:36\n Finished attempting to scrape: EAY base.py:345\n","errors":"Traceback (most recent call last):\n File \"/var/task/lgsf/aws_lambda/handlers.py\", line 32, in scraper_worker_handler\n scraper.run(run_log)\n File \"/var/task/lgsf/councillors/scrapers.py\", line 57, in run\n councillor = self.get_single_councillor(councillor_html)\n File \"scrapers/EAY-east-ayrshire/councillors.py\", line 22, in get_single_councillor\n .find_parent(\"div\")\nAttributeError: 'NoneType' object has no attribute 'find_parent'\n","start":"2024-08-21 08:19:20.987649","end":"2024-08-21 08:19:25.007153","duration":4}},{"council_id":"FLN","missing":false,"latest_run":{"status_code":1,"log_text":"[09:51:52] Fetching Scraper for: FLN handlers.py:23\n[09:51:53] Begin attempting to scrape: FLN handlers.py:27\n Deleting existing data... base.py:257\n Getting all files in Councillors... base.py:209\n Getting all files in Councillors/json... base.py:209\n[09:51:54] ...found 67 files in Councillors/json base.py:225\n Getting all files in Councillors/raw... base.py:209\n ...found 67 files in Councillors/raw base.py:225\n ...found 135 files in Councillors base.py:225\n Deleting batch no. 1 consisting of 100 files base.py:236\n[09:51:55] Deleting batch no. 2 consisting of 35 files base.py:236\n ...data deleted. base.py:264\n Scraping from base.py:49\n https://cyfarfodyddpwyllgor.siryfflint.gov.uk/mgWebService \n .asmx/GetCouncillorsByWard \n[09:52:26] The read operation timed out handlers.py:36\n Finished attempting to scrape: FLN base.py:345\n","errors":"Traceback (most recent call last):\n File \"/opt/python/httpx/_transports/default.py\", line 69, in map_httpcore_exceptions\n yield\n File \"/opt/python/httpx/_transports/default.py\", line 233, in handle_request\n resp = self._pool.handle_request(req)\n File \"/opt/python/httpcore/_sync/connection_pool.py\", line 216, in handle_request\n raise exc from None\n File \"/opt/python/httpcore/_sync/connection_pool.py\", line 196, in handle_request\n response = connection.handle_request(\n File \"/opt/python/httpcore/_sync/connection.py\", line 101, in handle_request\n return self._connection.handle_request(request)\n File \"/opt/python/httpcore/_sync/http11.py\", line 143, in handle_request\n raise exc\n File \"/opt/python/httpcore/_sync/http11.py\", line 113, in handle_request\n ) = self._receive_response_headers(**kwargs)\n File \"/opt/python/httpcore/_sync/http11.py\", line 186, in _receive_response_headers\n event = self._receive_event(timeout=timeout)\n File \"/opt/python/httpcore/_sync/http11.py\", line 224, in _receive_event\n data = self._network_stream.read(\n File \"/opt/python/httpcore/_backends/sync.py\", line 124, in read\n with map_exceptions(exc_map):\n File \"/var/lang/lib/python3.10/contextlib.py\", line 153, in __exit__\n self.gen.throw(typ, value, traceback)\n File \"/opt/python/httpcore/_exceptions.py\", line 14, in map_exceptions\n raise to_exc(exc) from exc\nhttpcore.ReadTimeout: The read operation timed out\n\nThe above exception was the direct cause of the following exception:\n\nTraceback (most recent call last):\n File \"/var/task/lgsf/aws_lambda/handlers.py\", line 32, in scraper_worker_handler\n scraper.run(run_log)\n File \"/var/task/lgsf/councillors/scrapers.py\", line 197, in run\n wards = self.get_councillors()\n File \"/var/task/lgsf/councillors/scrapers.py\", line 216, in get_councillors\n req = self.get(self.format_councillor_api_url())\n File \"/var/task/lgsf/scrapers/base.py\", line 55, in get\n response = self.http_client.get(url, headers=headers, timeout=30)\n File \"/opt/python/httpx/_client.py\", line 1054, in get\n return self.request(\n File \"/opt/python/httpx/_client.py\", line 827, in request\n return self.send(request, auth=auth, follow_redirects=follow_redirects)\n File \"/opt/python/httpx/_client.py\", line 914, in send\n response = self._send_handling_auth(\n File \"/opt/python/httpx/_client.py\", line 942, in _send_handling_auth\n response = self._send_handling_redirects(\n File \"/opt/python/httpx/_client.py\", line 979, in _send_handling_redirects\n response = self._send_single_request(request)\n File \"/opt/python/httpx/_client.py\", line 1015, in _send_single_request\n response = transport.handle_request(request)\n File \"/opt/python/httpx/_transports/default.py\", line 232, in handle_request\n with map_httpcore_exceptions():\n File \"/var/lang/lib/python3.10/contextlib.py\", line 153, in __exit__\n self.gen.throw(typ, value, traceback)\n File \"/opt/python/httpx/_transports/default.py\", line 86, in map_httpcore_exceptions\n raise mapped_exc(message) from exc\nhttpx.ReadTimeout: The read operation timed out\n","start":"2024-08-21 09:51:52.993735","end":"2024-08-21 09:52:26.644242","duration":33}},{"council_id":"GLG","missing":false,"latest_run":{"status_code":1,"log_text":"[09:03:25] Fetching Scraper for: GLG handlers.py:23\n Begin attempting to scrape: GLG handlers.py:27\n Deleting existing data... base.py:257\n[09:03:26] Getting all files in Councillors... base.py:209\n ...found 1 files in Councillors base.py:225\n Deleting batch no. 1 consisting of 1 files base.py:236\n[09:03:27] ...data deleted. base.py:264\n Scraping from base.py:49\n https://www.glasgow.gov.uk/councillorsandcommittees/allMem \n bers.asp?sort=0&page=0&rec=100 \n Client error '404 Not Found' for url handlers.py:36\n 'https://www.glasgow.gov.uk/councillorsandcommittees/a \n llMembers.asp?sort=0&page=0&rec=100' \n For more information check: \n https://developer.mozilla.org/en-US/docs/Web/HTTP/Stat \n us/404 \n Finished attempting to scrape: GLG base.py:345\n","errors":"Traceback (most recent call last):\n File \"/var/task/lgsf/aws_lambda/handlers.py\", line 32, in scraper_worker_handler\n scraper.run(run_log)\n File \"/var/task/lgsf/councillors/scrapers.py\", line 55, in run\n for councillor_html in self.get_councillors():\n File \"/var/task/lgsf/councillors/scrapers.py\", line 161, in get_councillors\n container = self.get_list_container()\n File \"/var/task/lgsf/councillors/scrapers.py\", line 152, in get_list_container\n self.base_url_soup = self.get_page(self.base_url)\n File \"/var/task/lgsf/councillors/scrapers.py\", line 141, in get_page\n page = self.get(url, extra_headers=self.extra_headers).text\n File \"/var/task/lgsf/scrapers/base.py\", line 56, in get\n response.raise_for_status()\n File \"/opt/python/httpx/_models.py\", line 761, in raise_for_status\n raise HTTPStatusError(message, request=request, response=self)\nhttpx.HTTPStatusError: Client error '404 Not Found' for url 'https://www.glasgow.gov.uk/councillorsandcommittees/allMembers.asp?sort=0&page=0&rec=100'\nFor more information check: https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/404\n","start":"2024-08-21 09:03:25.384364","end":"2024-08-21 09:03:27.555491","duration":2}},{"council_id":"GLS","missing":false,"latest_run":{"status_code":1,"log_text":"[10:38:48] Fetching Scraper for: GLS handlers.py:23\n Begin attempting to scrape: GLS handlers.py:27\n[10:38:49] Deleting existing data... base.py:257\n Getting all files in Councillors... base.py:209\n ...found 1 files in Councillors base.py:225\n Deleting batch no. 1 consisting of 1 files base.py:236\n[10:38:50] ...data deleted. base.py:264\n Scraping from base.py:49\n http://glostext.gloucestershire.gov.uk//mgWebService.asmx/ \n GetCouncillorsByWard \n[10:39:05] [Errno 110] Connection timed out handlers.py:36\n[10:39:06] Finished attempting to scrape: GLS base.py:345\n","errors":"Traceback (most recent call last):\n File \"/opt/python/httpx/_transports/default.py\", line 69, in map_httpcore_exceptions\n yield\n File \"/opt/python/httpx/_transports/default.py\", line 233, in handle_request\n resp = self._pool.handle_request(req)\n File \"/opt/python/httpcore/_sync/connection_pool.py\", line 216, in handle_request\n raise exc from None\n File \"/opt/python/httpcore/_sync/connection_pool.py\", line 196, in handle_request\n response = connection.handle_request(\n File \"/opt/python/httpcore/_sync/connection.py\", line 99, in handle_request\n raise exc\n File \"/opt/python/httpcore/_sync/connection.py\", line 76, in handle_request\n stream = self._connect(request)\n File \"/opt/python/httpcore/_sync/connection.py\", line 122, in _connect\n stream = self._network_backend.connect_tcp(**kwargs)\n File \"/opt/python/httpcore/_backends/sync.py\", line 205, in connect_tcp\n with map_exceptions(exc_map):\n File \"/var/lang/lib/python3.10/contextlib.py\", line 153, in __exit__\n self.gen.throw(typ, value, traceback)\n File \"/opt/python/httpcore/_exceptions.py\", line 14, in map_exceptions\n raise to_exc(exc) from exc\nhttpcore.ConnectTimeout: [Errno 110] Connection timed out\n\nThe above exception was the direct cause of the following exception:\n\nTraceback (most recent call last):\n File \"/var/task/lgsf/aws_lambda/handlers.py\", line 32, in scraper_worker_handler\n scraper.run(run_log)\n File \"/var/task/lgsf/councillors/scrapers.py\", line 197, in run\n wards = self.get_councillors()\n File \"/var/task/lgsf/councillors/scrapers.py\", line 216, in get_councillors\n req = self.get(self.format_councillor_api_url())\n File \"/var/task/lgsf/scrapers/base.py\", line 55, in get\n response = self.http_client.get(url, headers=headers, timeout=30)\n File \"/opt/python/httpx/_client.py\", line 1054, in get\n return self.request(\n File \"/opt/python/httpx/_client.py\", line 827, in request\n return self.send(request, auth=auth, follow_redirects=follow_redirects)\n File \"/opt/python/httpx/_client.py\", line 914, in send\n response = self._send_handling_auth(\n File \"/opt/python/httpx/_client.py\", line 942, in _send_handling_auth\n response = self._send_handling_redirects(\n File \"/opt/python/httpx/_client.py\", line 979, in _send_handling_redirects\n response = self._send_single_request(request)\n File \"/opt/python/httpx/_client.py\", line 1015, in _send_single_request\n response = transport.handle_request(request)\n File \"/opt/python/httpx/_transports/default.py\", line 232, in handle_request\n with map_httpcore_exceptions():\n File \"/var/lang/lib/python3.10/contextlib.py\", line 153, in __exit__\n self.gen.throw(typ, value, traceback)\n File \"/opt/python/httpx/_transports/default.py\", line 86, in map_httpcore_exceptions\n raise mapped_exc(message) from exc\nhttpx.ConnectTimeout: [Errno 110] Connection timed out\n","start":"2024-08-21 10:38:48.600310","end":"2024-08-21 10:39:06.215336","duration":17}},{"council_id":"GRE","missing":false,"latest_run":{"status_code":1,"log_text":"[10:27:02] Fetching Scraper for: GRE handlers.py:23\n Begin attempting to scrape: GRE handlers.py:27\n Deleting existing data... base.py:257\n[10:27:03] Getting all files in Councillors... base.py:209\n ...found 1 files in Councillors base.py:225\n Deleting batch no. 1 consisting of 1 files base.py:236\n[10:27:04] ...data deleted. base.py:264\n Scraping from base.py:49\n https://committees.royalgreenwich.gov.uk/Councillors/tabid \n /63/ScreenMode/Alphabetical/Default.aspx \n[10:27:09] Client error '404 Not Found' for url handlers.py:36\n 'https://committees.royalgreenwich.gov.uk/mgError.aspx \n ' \n For more information check: \n https://developer.mozilla.org/en-US/docs/Web/HTTP/Stat \n us/404 \n Finished attempting to scrape: GRE base.py:345\n","errors":"Traceback (most recent call last):\n File \"/var/task/lgsf/aws_lambda/handlers.py\", line 32, in scraper_worker_handler\n scraper.run(run_log)\n File \"/var/task/lgsf/councillors/scrapers.py\", line 55, in run\n for councillor_html in self.get_councillors():\n File \"/var/task/lgsf/councillors/scrapers.py\", line 272, in get_councillors\n req = self.get(\n File \"/var/task/lgsf/scrapers/base.py\", line 56, in get\n response.raise_for_status()\n File \"/opt/python/httpx/_models.py\", line 761, in raise_for_status\n raise HTTPStatusError(message, request=request, response=self)\nhttpx.HTTPStatusError: Client error '404 Not Found' for url 'https://committees.royalgreenwich.gov.uk/mgError.aspx'\nFor more information check: https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/404\n","start":"2024-08-21 10:27:02.536262","end":"2024-08-21 10:27:09.356918","duration":6}},{"council_id":"SHE","missing":false,"latest_run":{"status_code":null,"log_text":"[11:28:20] Fetching Scraper for: SHE handlers.py:22\n Begin attempting to scrape: SHE handlers.py:25\n Deleting existing data... base.py:234\n Getting all files in SHE... base.py:186\n[11:28:21] Getting all files in SHE/json... base.py:186\n ...found 30 files in SHE/json base.py:202\n Getting all files in SHE/raw... base.py:186\n ...found 30 files in SHE/raw base.py:202\n ...found 61 files in SHE base.py:202\n Deleting batch no. 1 consisting of 61 files base.py:211\n[11:28:32] An error occurred (ThrottlingException) when calling handlers.py:34\n the CreateCommit operation (reached max retries: 4): \n Rate exceeded \n Finished attempting to scrape: SHE base.py:319\n","errors":"An error occurred (ThrottlingException) when calling the CreateCommit operation (reached max retries: 4): Rate exceeded","start":"2022-04-04 11:28:20.509898","end":"2022-04-04 11:28:32.871624","duration":12}},{"council_id":"STG","missing":false,"latest_run":{"status_code":1,"log_text":"[09:03:31] Fetching Scraper for: STG handlers.py:23\n Begin attempting to scrape: STG handlers.py:27\n Deleting existing data... base.py:257\n[09:03:32] Getting all files in Councillors... base.py:209\n Getting all files in Councillors/json... base.py:209\n ...found 7 files in Councillors/json base.py:225\n Getting all files in Councillors/raw... base.py:209\n ...found 7 files in Councillors/raw base.py:225\n ...found 15 files in Councillors base.py:225\n Deleting batch no. 1 consisting of 15 files base.py:236\n[09:03:33] ...data deleted. base.py:264\n Scraping from base.py:49\n https://www.stirling.gov.uk/council-and-committees/politic \n ians-and-elections/councillors/ \n[09:03:34] Scraping from base.py:49\n https://www.stirling.gov.uk/council-and-committees/politic \n ians-and-elections/councillors/elaine-watterson/ \n[09:03:35] Scraping from base.py:49\n https://www.stirling.gov.uk/council-and-committees/politic \n ians-and-elections/councillors/gene-maxwell/ \n[09:03:37] Scraping from base.py:49\n https://www.stirling.gov.uk/council-and-committees/politic \n ians-and-elections/councillors/martin-earl/ \n[09:03:38] Scraping from base.py:49\n https://www.stirling.gov.uk/council-and-committees/politic \n ians-and-elections/councillors/gerry-mcgarvey/ \n[09:03:39] Scraping from base.py:49\n https://www.stirling.gov.uk/council-and-committees/politic \n ians-and-elections/councillors/paul-henke/ \n[09:03:40] Scraping from base.py:49\n https://www.stirling.gov.uk/council-and-committees/politic \n ians-and-elections/councillors/rosemary-fraser/ \n[09:03:42] Scraping from base.py:49\n https://www.stirling.gov.uk/council-and-committees/politic \n ians-and-elections/councillors/alasdair-tollemache/ \n[09:03:43] Scraping from base.py:49\n https://www.stirling.gov.uk/council-and-committees/politic \n ians-and-elections/councillors/david-wilson/ \n[09:03:44] 'NoneType' object is not subscriptable handlers.py:36\n Committing batch 1 consisting of 14 files base.py:297\n[09:03:45] Finished attempting to scrape: STG base.py:345\n","errors":"Traceback (most recent call last):\n File \"/var/task/lgsf/aws_lambda/handlers.py\", line 32, in scraper_worker_handler\n scraper.run(run_log)\n File \"/var/task/lgsf/councillors/scrapers.py\", line 57, in run\n councillor = self.get_single_councillor(councillor_html)\n File \"scrapers/STG-stirling/councillors.py\", line 42, in get_single_councillor\n councillor.email = soup.select_one(\"a[href^=mailto]\")[\nTypeError: 'NoneType' object is not subscriptable\n","start":"2024-08-21 09:03:31.319473","end":"2024-08-21 09:03:45.637077","duration":14}},{"council_id":"THE","missing":false,"latest_run":{"status_code":1,"log_text":"[10:05:03] Fetching Scraper for: THE handlers.py:23\n Begin attempting to scrape: THE handlers.py:27\n[10:05:04] Deleting existing data... base.py:257\n Getting all files in Councillors... base.py:209\n ...found 1 files in Councillors base.py:225\n Deleting batch no. 1 consisting of 1 files base.py:236\n[10:05:05] ...data deleted. base.py:264\n Scraping from base.py:49\n https://www.threerivers.gov.uk/listing/councillors \n[10:05:07] 'NoneType' object has no attribute 'findNext' handlers.py:36\n Finished attempting to scrape: THE base.py:345\n","errors":"Traceback (most recent call last):\n File \"/var/task/lgsf/aws_lambda/handlers.py\", line 32, in scraper_worker_handler\n scraper.run(run_log)\n File \"/var/task/lgsf/councillors/scrapers.py\", line 55, in run\n for councillor_html in self.get_councillors():\n File \"/var/task/lgsf/councillors/scrapers.py\", line 161, in get_councillors\n container = self.get_list_container()\n File \"scrapers/THE-three-rivers/councillors.py\", line 15, in get_list_container\n return soup.find(\"h3\", text=\"District Councillor\").findNext(\"ul\")\nAttributeError: 'NoneType' object has no attribute 'findNext'\n","start":"2024-08-21 10:05:03.737496","end":"2024-08-21 10:05:07.453760","duration":3}},{"council_id":"TWH","missing":false,"latest_run":{"status_code":1,"log_text":"[09:50:47] Fetching Scraper for: TWH handlers.py:23\n Begin attempting to scrape: TWH handlers.py:27\n Deleting existing data... base.py:257\n[09:50:48] Getting all files in Councillors... base.py:209\n ...found 1 files in Councillors base.py:225\n Deleting batch no. 1 consisting of 1 files base.py:236\n[09:50:49] ...data deleted. base.py:264\n Scraping from base.py:49\n http://democracy.towerhamlets.gov.uk/mgWebService.asmx/Get \n CouncillorsByWard \n [SSL: CERTIFICATE_VERIFY_FAILED] certificate verify handlers.py:36\n failed: unable to get local issuer certificate \n (_ssl.c:1007) \n Finished attempting to scrape: TWH base.py:345\n","errors":"Traceback (most recent call last):\n File \"/opt/python/httpx/_transports/default.py\", line 69, in map_httpcore_exceptions\n yield\n File \"/opt/python/httpx/_transports/default.py\", line 233, in handle_request\n resp = self._pool.handle_request(req)\n File \"/opt/python/httpcore/_sync/connection_pool.py\", line 216, in handle_request\n raise exc from None\n File \"/opt/python/httpcore/_sync/connection_pool.py\", line 196, in handle_request\n response = connection.handle_request(\n File \"/opt/python/httpcore/_sync/connection.py\", line 99, in handle_request\n raise exc\n File \"/opt/python/httpcore/_sync/connection.py\", line 76, in handle_request\n stream = self._connect(request)\n File \"/opt/python/httpcore/_sync/connection.py\", line 154, in _connect\n stream = stream.start_tls(**kwargs)\n File \"/opt/python/httpcore/_backends/sync.py\", line 152, in start_tls\n with map_exceptions(exc_map):\n File \"/var/lang/lib/python3.10/contextlib.py\", line 153, in __exit__\n self.gen.throw(typ, value, traceback)\n File \"/opt/python/httpcore/_exceptions.py\", line 14, in map_exceptions\n raise to_exc(exc) from exc\nhttpcore.ConnectError: [SSL: CERTIFICATE_VERIFY_FAILED] certificate verify failed: unable to get local issuer certificate (_ssl.c:1007)\n\nThe above exception was the direct cause of the following exception:\n\nTraceback (most recent call last):\n File \"/var/task/lgsf/aws_lambda/handlers.py\", line 32, in scraper_worker_handler\n scraper.run(run_log)\n File \"/var/task/lgsf/councillors/scrapers.py\", line 197, in run\n wards = self.get_councillors()\n File \"/var/task/lgsf/councillors/scrapers.py\", line 216, in get_councillors\n req = self.get(self.format_councillor_api_url())\n File \"/var/task/lgsf/scrapers/base.py\", line 55, in get\n response = self.http_client.get(url, headers=headers, timeout=30)\n File \"/opt/python/httpx/_client.py\", line 1054, in get\n return self.request(\n File \"/opt/python/httpx/_client.py\", line 827, in request\n return self.send(request, auth=auth, follow_redirects=follow_redirects)\n File \"/opt/python/httpx/_client.py\", line 914, in send\n response = self._send_handling_auth(\n File \"/opt/python/httpx/_client.py\", line 942, in _send_handling_auth\n response = self._send_handling_redirects(\n File \"/opt/python/httpx/_client.py\", line 979, in _send_handling_redirects\n response = self._send_single_request(request)\n File \"/opt/python/httpx/_client.py\", line 1015, in _send_single_request\n response = transport.handle_request(request)\n File \"/opt/python/httpx/_transports/default.py\", line 232, in handle_request\n with map_httpcore_exceptions():\n File \"/var/lang/lib/python3.10/contextlib.py\", line 153, in __exit__\n self.gen.throw(typ, value, traceback)\n File \"/opt/python/httpx/_transports/default.py\", line 86, in map_httpcore_exceptions\n raise mapped_exc(message) from exc\nhttpx.ConnectError: [SSL: CERTIFICATE_VERIFY_FAILED] certificate verify failed: unable to get local issuer certificate (_ssl.c:1007)\n","start":"2024-08-21 09:50:47.443507","end":"2024-08-21 09:50:49.571227","duration":2}}] diff --git a/index.html b/index.html index e76bc4b45a..88a61578a9 100644 --- a/index.html +++ b/index.html @@ -49,10 +49,6 @@
[08:28:24] Fetching Scraper for: ABC handlers.py:23 + Begin attempting to scrape: ABC handlers.py:27 + Deleting existing data... base.py:257 +[08:28:25] Getting all files in Councillors... base.py:209 + Getting all files in Councillors/json... base.py:209 + ...found 16 files in Councillors/json base.py:225 + Getting all files in Councillors/raw... base.py:209 + ...found 16 files in Councillors/raw base.py:225 + ...found 33 files in Councillors base.py:225 + Deleting batch no. 1 consisting of 33 files base.py:236 +[08:28:26] ...data deleted. base.py:264 + Scraping from base.py:49 + https://www.armaghbanbridgecraigavon.gov.uk/councillors/ +[08:28:30] Committing batch 1 consisting of 32 files base.py:297 +[08:28:31] Finished attempting to scrape: ABC base.py:345 ++ + + + +
[10:23:20] Fetching Scraper for: ABC handlers.py:23 - Begin attempting to scrape: ABC handlers.py:27 - Deleting existing data... base.py:257 -[10:23:21] Getting all files in Councillors... base.py:209 - Getting all files in Councillors/json... base.py:209 - ...found 16 files in Councillors/json base.py:225 - Getting all files in Councillors/raw... base.py:209 - ...found 16 files in Councillors/raw base.py:225 - ...found 33 files in Councillors base.py:225 - Deleting batch no. 1 consisting of 33 files base.py:236 -[10:23:22] ...data deleted. base.py:264 - Scraping from base.py:49 - https://www.armaghbanbridgecraigavon.gov.uk/councillors/ -[10:23:26] Committing batch 1 consisting of 32 files base.py:297 -[10:23:27] Finished attempting to scrape: ABC base.py:345 -- -