diff --git a/api/failing.json b/api/failing.json index babf04e63a..a08b9881c7 100644 --- a/api/failing.json +++ b/api/failing.json @@ -1 +1 @@ -[{"council_id":"BDG","missing":false,"latest_run":{"status_code":1,"log_text":"[09:55:26] Fetching Scraper for: BDG handlers.py:23\n Begin attempting to scrape: BDG handlers.py:27\n Deleting existing data... base.py:257\n[09:55:27] 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[09:55:28] ...data deleted. base.py:264\n Scraping from base.py:49\n https://modgov.lbbd.gov.uk/internet/mgWebService.asmx/GetC \n ouncillorsByWard \n[09:55:43] [Errno 110] Connection timed out handlers.py:36\n Finished attempting to scrape: BDG 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":"2024-09-06 09:55:26.316014","end":"2024-09-06 09:55:43.888704","duration":17}},{"council_id":"BOL","missing":false,"latest_run":{"status_code":1,"log_text":"[09:56:03] Fetching Scraper for: BOL handlers.py:23\n Begin attempting to scrape: BOL handlers.py:27\n Deleting existing data... base.py:257\n[09:56:04] 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[09:56:05] ...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":"2024-09-06 09:56:03.243016","end":"2024-09-06 09:56:05.357437","duration":2}},{"council_id":"BRT","missing":false,"latest_run":{"status_code":1,"log_text":"[10:17:03] Fetching Scraper for: BRT handlers.py:23\n Begin attempting to scrape: BRT handlers.py:27\n[10:17:04] 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[10:17:05] ...found 44 files in Councillors/json base.py:225\n Getting all files in Councillors/raw... base.py:209\n ...found 44 files in Councillors/raw base.py:225\n ...found 89 files in Councillors base.py:225\n Deleting batch no. 1 consisting of 89 files base.py:236\n[10:17:06] ...data deleted. base.py:264\n Scraping from base.py:49\n http://democracy.broxtowe.gov.uk/mgWebService.asmx/GetCoun \n cillorsByWard \n[10:17:21] [Errno 110] Connection timed out handlers.py:36\n[10:17:22] Finished attempting to scrape: BRT 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":"2024-09-06 10:17:03.878794","end":"2024-09-06 10:17:22.004748","duration":18}},{"council_id":"CAN","missing":false,"latest_run":{"status_code":1,"log_text":"[10:34:34] Fetching Scraper for: CAN handlers.py:23\n Begin attempting to scrape: CAN handlers.py:27\n Deleting existing data... base.py:257\n[10:34:35] 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[10:34:36] ...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[10:34:38] 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":"2024-09-06 10:34:34.156339","end":"2024-09-06 10:34:38.487219","duration":4}},{"council_id":"CAS","missing":false,"latest_run":{"status_code":1,"log_text":"[08:54:12] Fetching Scraper for: CAS handlers.py:23\n Begin attempting to scrape: CAS handlers.py:27\n[08:54:13] 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[08:54:14] ...data deleted. base.py:264\n Scraping from https://www.castlepoint.gov.uk/councillors base.py:49\n[08:54:15] Scraping from base.py:49\n https://www.castlepoint.gov.ukhttps://castlepoint.cmis.uk. \n com/castlepoint/Committees/CurrentCommittees.aspx?a=1 \n[08:54:16] [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":"2024-09-06 08:54:12.804800","end":"2024-09-06 08:54:16.211089","duration":3}},{"council_id":"CMD","missing":false,"latest_run":{"status_code":1,"log_text":"[08:55:03] Fetching Scraper for: CMD handlers.py:23\n Begin attempting to scrape: CMD handlers.py:27\n Deleting existing data... base.py:257\n Getting all files in Councillors... base.py:209\n[08:55:04] ...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://democracy.camden.gov.uk/mgWebService.asmx/GetCounc \n illorsByWard \n[08:55:05] 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":"2024-09-06 08:55:03.151336","end":"2024-09-06 08:55:05.276410","duration":2}},{"council_id":"EAY","missing":false,"latest_run":{"status_code":1,"log_text":"[08:40:16] Fetching Scraper for: EAY handlers.py:23\n Begin attempting to scrape: EAY handlers.py:27\n[08:40:17] 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[08:40:18] ...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[08:40:19] 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[08:40:20] '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":"2024-09-06 08:40:16.896323","end":"2024-09-06 08:40:20.763508","duration":3}},{"council_id":"GLG","missing":false,"latest_run":{"status_code":1,"log_text":"[08:37:41] Fetching Scraper for: GLG handlers.py:23\n Begin attempting to scrape: GLG handlers.py:27\n[08:37:42] Deleting existing data... base.py:257\n[08:37:44] 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[08:37:45] ...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":"2024-09-06 08:37:41.740082","end":"2024-09-06 08:37:45.438270","duration":3}},{"council_id":"GLS","missing":false,"latest_run":{"status_code":1,"log_text":"[08:53:51] Fetching Scraper for: GLS handlers.py:23\n Begin attempting to scrape: GLS handlers.py:27\n Deleting existing data... base.py:257\n[08:53:52] 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[08:53:53] ...data deleted. base.py:264\n Scraping from base.py:49\n http://glostext.gloucestershire.gov.uk//mgWebService.asmx/ \n GetCouncillorsByWard \n[08:54:08] [Errno 110] Connection timed out handlers.py:36\n[08:54:09] 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":"2024-09-06 08:53:51.516517","end":"2024-09-06 08:54:09.275010","duration":17}},{"council_id":"GRE","missing":false,"latest_run":{"status_code":1,"log_text":"[09:36:27] Fetching Scraper for: GRE handlers.py:23\n Begin attempting to scrape: GRE handlers.py:27\n Deleting existing data... base.py:257\n[09:36:28] 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://committees.royalgreenwich.gov.uk/Councillors/tabid \n /63/ScreenMode/Alphabetical/Default.aspx \n[09:36:29] 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":"2024-09-06 09:36:27.321564","end":"2024-09-06 09:36:29.553938","duration":2}},{"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":"TEW","missing":false,"latest_run":{"status_code":1,"log_text":"[08:18:37] Fetching Scraper for: TEW handlers.py:23\n Begin attempting to scrape: TEW handlers.py:27\n Deleting existing data... base.py:257\n[08:18:38] 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[08:18:39] ...data deleted. base.py:264\n Scraping from base.py:49\n http://minutes.tewkesbury.gov.uk/mgWebService.asmx/GetCoun \n cillorsByWard \n[08:18:54] [Errno 110] Connection timed out handlers.py:36\n Finished attempting to scrape: TEW 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":"2024-09-06 08:18:37.282986","end":"2024-09-06 08:18:54.992811","duration":17}},{"council_id":"THE","missing":false,"latest_run":{"status_code":1,"log_text":"[09:23:16] Fetching Scraper for: THE handlers.py:23\n Begin attempting to scrape: THE handlers.py:27\n Deleting existing data... base.py:257\n[09:23:17] 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[09:23:18] ...data deleted. base.py:264\n Scraping from base.py:49\n https://www.threerivers.gov.uk/listing/councillors \n[09:23:21] '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":"2024-09-06 09:23:16.360332","end":"2024-09-06 09:23:21.610806","duration":5}}] +[{"council_id":"BDG","missing":false,"latest_run":{"status_code":1,"log_text":"[09:31:28] Fetching Scraper for: BDG handlers.py:23\n Begin attempting to scrape: BDG handlers.py:27\n[09:31:29] 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[09:31:30] ...data deleted. base.py:264\n Scraping from base.py:49\n https://modgov.lbbd.gov.uk/internet/mgWebService.asmx/GetC \n ouncillorsByWard \n[09:31:45] [Errno 110] Connection timed out handlers.py:36\n[09:31:46] Finished attempting to scrape: BDG 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":"2024-09-07 09:31:28.967405","end":"2024-09-07 09:31:46.104169","duration":17}},{"council_id":"BOL","missing":false,"latest_run":{"status_code":1,"log_text":"[08:52:56] Fetching Scraper for: BOL handlers.py:23\n Begin attempting to scrape: BOL handlers.py:27\n Deleting existing data... base.py:257\n[08:52:57] 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[08:52:58] ...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":"2024-09-07 08:52:56.518750","end":"2024-09-07 08:52:58.331288","duration":1}},{"council_id":"CAN","missing":false,"latest_run":{"status_code":1,"log_text":"[09:31:52] 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 ...found 1 files in Councillors base.py:225\n Deleting batch no. 1 consisting of 1 files base.py:236\n[09:31:53] ...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[09:31:55] 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":"2024-09-07 09:31:52.004818","end":"2024-09-07 09:31:55.362930","duration":3}},{"council_id":"CAS","missing":false,"latest_run":{"status_code":1,"log_text":"[08:20:45] Fetching Scraper for: CAS handlers.py:23\n Begin attempting to scrape: CAS handlers.py:27\n Deleting existing data... base.py:257\n[08:20:46] 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[08:20:47] ...data deleted. base.py:264\n Scraping from https://www.castlepoint.gov.uk/councillors base.py:49\n[08:20:48] 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":"2024-09-07 08:20:45.618642","end":"2024-09-07 08:20:48.794189","duration":3}},{"council_id":"CMD","missing":false,"latest_run":{"status_code":1,"log_text":"[10:31:14] Fetching Scraper for: CMD handlers.py:23\n Begin attempting to scrape: CMD handlers.py:27\n Deleting existing data... base.py:257\n Getting all files in Councillors... base.py:209\n[10:31:15] ...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://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[10:31:16] 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":"2024-09-07 10:31:14.190080","end":"2024-09-07 10:31:16.178558","duration":1}},{"council_id":"EAY","missing":false,"latest_run":{"status_code":1,"log_text":"[09:45:55] Fetching Scraper for: EAY handlers.py:23\n Begin attempting to scrape: EAY handlers.py:27\n[09:45:56] 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[09:45:57] ...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[09:45:58] 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 'NoneType' object has no attribute 'find_parent' handlers.py:36\n[09:45:59] 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":"2024-09-07 09:45:55.837155","end":"2024-09-07 09:45:59.126944","duration":3}},{"council_id":"GLG","missing":false,"latest_run":{"status_code":1,"log_text":"[10:21:27] Fetching Scraper for: GLG handlers.py:23\n Begin attempting to scrape: GLG handlers.py:27\n[10:21:28] 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[10:21:29] ...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":"2024-09-07 10:21:27.794241","end":"2024-09-07 10:21:29.959750","duration":2}},{"council_id":"GLS","missing":false,"latest_run":{"status_code":1,"log_text":"[09:53:49] Fetching Scraper for: GLS handlers.py:23\n Begin attempting to scrape: GLS handlers.py:27\n[09:53:50] Deleting existing data... base.py:257\n[09:53:51] 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[09:54:07] [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":"2024-09-07 09:53:49.655201","end":"2024-09-07 09:54:07.554906","duration":17}},{"council_id":"GRE","missing":false,"latest_run":{"status_code":1,"log_text":"[10:14:28] Fetching Scraper for: GRE handlers.py:23\n Begin attempting to scrape: GRE handlers.py:27\n Deleting existing data... base.py:257\n Getting all files in Councillors... base.py:209\n[10:14:29] ...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://committees.royalgreenwich.gov.uk/Councillors/tabid \n /63/ScreenMode/Alphabetical/Default.aspx \n[10:14:35] 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":"2024-09-07 10:14:28.316383","end":"2024-09-07 10:14:35.741451","duration":7}},{"council_id":"HAV","missing":false,"latest_run":{"status_code":1,"log_text":"[10:00:54] Fetching Scraper for: HAV handlers.py:23\n Begin attempting to scrape: HAV handlers.py:27\n Deleting existing data... base.py:257\n[10:00:55] Getting all files in Councillors... base.py:209\n Getting all files in Councillors/json... base.py:209\n ...found 55 files in Councillors/json base.py:225\n Getting all files in Councillors/raw... base.py:209\n ...found 55 files in Councillors/raw base.py:225\n ...found 111 files in Councillors base.py:225\n Deleting batch no. 1 consisting of 100 files base.py:236\n[10:00:56] Deleting batch no. 2 consisting of 11 files base.py:236\n ...data deleted. base.py:264\n Scraping from base.py:49\n http://democracy.havering.gov.uk/mgWebService.asmx/GetCoun \n cillorsByWard \n Server error '502 Bad Gateway' for url handlers.py:36\n 'http://democracy.havering.gov.uk/mgWebService.asmx/Ge \n tCouncillorsByWard' \n For more information check: \n https://developer.mozilla.org/en-US/docs/Web/HTTP/Stat \n us/502 \n[10:00:57] Finished attempting to scrape: HAV 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: Server error '502 Bad Gateway' for url 'http://democracy.havering.gov.uk/mgWebService.asmx/GetCouncillorsByWard'\nFor more information check: https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/502\n","start":"2024-09-07 10:00:54.248706","end":"2024-09-07 10:00:57.135201","duration":2}},{"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":"TEW","missing":false,"latest_run":{"status_code":1,"log_text":"[09:35:17] Fetching Scraper for: TEW handlers.py:23\n Begin attempting to scrape: TEW handlers.py:27\n Deleting existing data... base.py:257\n Getting all files in Councillors... base.py:209\n[09:35:18] ...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://minutes.tewkesbury.gov.uk/mgWebService.asmx/GetCoun \n cillorsByWard \n[09:35:34] [Errno 110] Connection timed out handlers.py:36\n Finished attempting to scrape: TEW 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":"2024-09-07 09:35:17.096876","end":"2024-09-07 09:35:34.413870","duration":17}},{"council_id":"THE","missing":false,"latest_run":{"status_code":1,"log_text":"[08:58:38] Fetching Scraper for: THE handlers.py:23\n Begin attempting to scrape: THE handlers.py:27\n Deleting existing data... base.py:257\n Getting all files in Councillors... base.py:209\n[08:58:39] ...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[08:58:42] '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":"2024-09-07 08:58:38.321880","end":"2024-09-07 08:58:42.365797","duration":4}}] diff --git a/index.html b/index.html index f93db0d3d8..6c849b35e3 100644 --- a/index.html +++ b/index.html @@ -49,10 +49,6 @@
[09:51:28] Fetching Scraper for: ABC handlers.py:23 + Begin attempting to scrape: ABC handlers.py:27 + Deleting existing data... base.py:257 + Getting all files in Councillors... base.py:209 +[09:51:29] 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 +[09:51:30] ...data deleted. base.py:264 + Scraping from base.py:49 + https://www.armaghbanbridgecraigavon.gov.uk/councillors/ +[09:51:33] Committing batch 1 consisting of 32 files base.py:297 +[09:51:34] Finished attempting to scrape: ABC base.py:345 ++ + + + +
[09:43:27] Fetching Scraper for: ABC handlers.py:23 - Begin attempting to scrape: ABC handlers.py:27 -[09:43:28] Deleting existing data... base.py:257 - Getting all files in Councillors... base.py:209 - Getting all files in Councillors/json... base.py:209 -[09:43:29] ...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 -[09:43:30] ...data deleted. base.py:264 - Scraping from base.py:49 - https://www.armaghbanbridgecraigavon.gov.uk/councillors/ -[09:43:33] Committing batch 1 consisting of 32 files base.py:297 -[09:43:35] Finished attempting to scrape: ABC base.py:345 -- -