diff --git a/api/failing.json b/api/failing.json index bd8d51e3d7..8462b51893 100644 --- a/api/failing.json +++ b/api/failing.json @@ -1 +1 @@ -[{"council_id":"BDG","missing":false,"latest_run":{"status_code":1,"log_text":"[09:53:44] Fetching Scraper for: BDG handlers.py:23\n Begin attempting to scrape: BDG handlers.py:27\n Deleting existing data... base.py:257\n Getting all files in Councillors... base.py:209\n[09:53:45] ...found 1 files in Councillors base.py:225\n Deleting batch no. 1 consisting of 1 files base.py:236\n[09:53:46] ...data deleted. base.py:264\n Scraping from base.py:49\n https://modgov.lbbd.gov.uk/internet/mgWebService.asmx/GetC \n ouncillorsByWard \n[09:54:01] [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":"2024-09-12 09:53:44.130353","end":"2024-09-12 09:54:01.798069","duration":17}},{"council_id":"BOL","missing":false,"latest_run":{"status_code":1,"log_text":"[10:16:20] Fetching Scraper for: BOL handlers.py:23\n Begin attempting to scrape: BOL handlers.py:27\n[10:16:21] 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[10:16:22] ...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":"2024-09-12 10:16:20.835903","end":"2024-09-12 10:16:22.986949","duration":2}},{"council_id":"CAN","missing":false,"latest_run":{"status_code":1,"log_text":"[10:34:41] Fetching Scraper for: CAN handlers.py:23\n Begin attempting to scrape: CAN handlers.py:27\n Deleting existing data... base.py:257\n[10:34:42] 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[10:34:43] ...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[10:34:45] 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":"2024-09-12 10:34:41.159607","end":"2024-09-12 10:34:45.439335","duration":4}},{"council_id":"CAS","missing":false,"latest_run":{"status_code":1,"log_text":"[09:27:29] Fetching Scraper for: CAS handlers.py:23\n Begin attempting to scrape: CAS handlers.py:27\n[09:27:30] 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[09:27:31] ...data deleted. base.py:264\n Scraping from https://www.castlepoint.gov.uk/councillors base.py:49\n[09:27:33] 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":"2024-09-12 09:27:29.629166","end":"2024-09-12 09:27:33.366518","duration":3}},{"council_id":"CGN","missing":false,"latest_run":{"status_code":1,"log_text":"[09:21:12] Fetching Scraper for: CGN handlers.py:23\n Begin attempting to scrape: CGN handlers.py:27\n[09:21:13] 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[09:21:14] ...found 38 files in Councillors/json base.py:225\n Getting all files in Councillors/raw... base.py:209\n ...found 38 files in Councillors/raw base.py:225\n ...found 77 files in Councillors base.py:225\n Deleting batch no. 1 consisting of 77 files base.py:236\n[09:21:15] ...data deleted. base.py:264\n Scraping from base.py:49\n https://council.ceredigion.gov.uk/mgWebService.asmx/GetCou \n ncillorsByWard \n [Errno 97] Address family not supported by protocol handlers.py:36\n Finished attempting to scrape: CGN 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 97] Address family not supported by protocol\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: [Errno 97] Address family not supported by protocol\n","start":"2024-09-12 09:21:12.918820","end":"2024-09-12 09:21:15.433664","duration":2}},{"council_id":"CMD","missing":false,"latest_run":{"status_code":1,"log_text":"[09:52:40] Fetching Scraper for: CMD handlers.py:23\n Begin attempting to scrape: CMD handlers.py:27\n[09:52:41] 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[09:52:42] ...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[09:52:43] 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":"2024-09-12 09:52:40.913453","end":"2024-09-12 09:52:43.130650","duration":2}},{"council_id":"EAY","missing":false,"latest_run":{"status_code":1,"log_text":"[10:33:40] Fetching Scraper for: EAY handlers.py:23\n Begin attempting to scrape: EAY handlers.py:27\n[10:33:41] 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[10:33:42] ...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[10:33:43] 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[10:33:44] '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":"2024-09-12 10:33:40.825621","end":"2024-09-12 10:33:44.769345","duration":3}},{"council_id":"GLG","missing":false,"latest_run":{"status_code":1,"log_text":"[09:27:38] Fetching Scraper for: GLG handlers.py:23\n Begin attempting to scrape: GLG handlers.py:27\n Deleting existing data... base.py:257\n[09:27:39] 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 ...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[09:27:40] 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":"2024-09-12 09:27:38.339732","end":"2024-09-12 09:27:40.335410","duration":1}},{"council_id":"GLS","missing":false,"latest_run":{"status_code":1,"log_text":"[09:28:46] Fetching Scraper for: GLS handlers.py:23\n Begin attempting to scrape: GLS handlers.py:27\n[09:28:47] 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[09:28:48] ...data deleted. base.py:264\n Scraping from base.py:49\n http://glostext.gloucestershire.gov.uk//mgWebService.asmx/ \n GetCouncillorsByWard \n[09:29:04] [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":"2024-09-12 09:28:46.651929","end":"2024-09-12 09:29:04.465483","duration":17}},{"council_id":"GRE","missing":false,"latest_run":{"status_code":1,"log_text":"[09:42:44] Fetching Scraper for: GRE handlers.py:23\n Begin attempting to scrape: GRE handlers.py:27\n Deleting existing data... base.py:257\n[09:42:45] 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[09:42:46] ...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[09:42:52] 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[09:42:53] 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":"2024-09-12 09:42:44.507037","end":"2024-09-12 09:42:53.113954","duration":8}},{"council_id":"HAR","missing":false,"latest_run":{"status_code":1,"log_text":"[10:25:56] Fetching Scraper for: HAR handlers.py:23\n[10:25:57] Begin attempting to scrape: HAR handlers.py:27\n Deleting existing data... base.py:257\n Getting all files in Councillors... base.py:209\n[10:25:58] Getting all files in Councillors/json... base.py:209\n ...found 32 files in Councillors/json base.py:225\n Getting all files in Councillors/raw... base.py:209\n ...found 32 files in Councillors/raw base.py:225\n ...found 65 files in Councillors base.py:225\n Deleting batch no. 1 consisting of 65 files base.py:236\n[10:25:59] ...data deleted. base.py:264\n Scraping from base.py:49\n http://moderngov.harlow.gov.uk/mgWebService.asmx/GetCounci \n llorsByWard \n[10:26:29] The read operation timed out handlers.py:36\n Finished attempting to scrape: HAR 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":"2024-09-12 10:25:56.957507","end":"2024-09-12 10:26:29.902901","duration":32}},{"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":"SND","missing":false,"latest_run":{"status_code":1,"log_text":"[10:10:21] Fetching Scraper for: SND handlers.py:23\n Begin attempting to scrape: SND handlers.py:27\n Deleting existing data... base.py:257\n Getting all files in Councillors... base.py:209\n[10:10:22] Getting all files in Councillors/json... base.py:209\n ...found 75 files in Councillors/json base.py:225\n Getting all files in Councillors/raw... base.py:209\n ...found 75 files in Councillors/raw base.py:225\n ...found 151 files in Councillors base.py:225\n Deleting batch no. 1 consisting of 100 files base.py:236\n[10:10:23] Deleting batch no. 2 consisting of 51 files base.py:236\n[10:10:24] ...data deleted. base.py:264\n Scraping from base.py:49\n https://committees.sunderland.gov.uk/committees/cmis5/Memb \n ers.aspx \n[10:10:25] Scraping from base.py:49\n https://committees.sunderland.gov.uk/committees/cmis5/Memb \n ers/tabid/62/ctl/ViewCMIS_Person/mid/600/id/1974/ScreenMod \n e/Ward/Default.aspx \n[10:10:27] Scraping from base.py:49\n https://committees.sunderland.gov.uk/committees/cmis5/Memb \n ers/tabid/62/ctl/ViewCMIS_Person/mid/600/id/1816/ScreenMod \n e/Ward/Default.aspx \n[10:10:29] Scraping from base.py:49\n https://committees.sunderland.gov.uk/committees/cmis5/Memb \n ers/tabid/62/ctl/ViewCMIS_Person/mid/600/id/1994/ScreenMod \n e/Ward/Default.aspx \n[10:10:32] Scraping from base.py:49\n https://committees.sunderland.gov.uk/committees/cmis5/Memb \n ers/tabid/62/ctl/ViewCMIS_Person/mid/600/id/1961/ScreenMod \n e/Ward/Default.aspx \n[10:10:33] Scraping from base.py:49\n https://committees.sunderland.gov.uk/committees/cmis5/Memb \n ers/tabid/62/ctl/ViewCMIS_Person/mid/600/id/1586/ScreenMod \n e/Ward/Default.aspx \n[10:10:36] Scraping from base.py:49\n https://committees.sunderland.gov.uk/committees/cmis5/Memb \n ers/tabid/62/ctl/ViewCMIS_Person/mid/600/id/1228/ScreenMod \n e/Ward/Default.aspx \n[10:10:38] Scraping from base.py:49\n https://committees.sunderland.gov.uk/committees/cmis5/Memb \n ers/tabid/62/ctl/ViewCMIS_Person/mid/600/id/1902/ScreenMod \n e/Ward/Default.aspx \n[10:10:41] Scraping from base.py:49\n https://committees.sunderland.gov.uk/committees/cmis5/Memb \n ers/tabid/62/ctl/ViewCMIS_Person/mid/600/id/1742/ScreenMod \n e/Ward/Default.aspx \n[10:10:43] Scraping from base.py:49\n https://committees.sunderland.gov.uk/committees/cmis5/Memb \n ers/tabid/62/ctl/ViewCMIS_Person/mid/600/id/1861/ScreenMod \n e/Ward/Default.aspx \n[10:10:45] Scraping from base.py:49\n https://committees.sunderland.gov.uk/committees/cmis5/Memb \n ers/tabid/62/ctl/ViewCMIS_Person/mid/600/id/1958/ScreenMod \n e/Ward/Default.aspx \n[10:10:47] Scraping from base.py:49\n https://committees.sunderland.gov.uk/committees/cmis5/Memb \n ers/tabid/62/ctl/ViewCMIS_Person/mid/600/id/1854/ScreenMod \n e/Ward/Default.aspx \n[10:10:49] Scraping from base.py:49\n https://committees.sunderland.gov.uk/committees/cmis5/Memb \n ers/tabid/62/ctl/ViewCMIS_Person/mid/600/id/1914/ScreenMod \n e/Ward/Default.aspx \n[10:10:51] Scraping from base.py:49\n https://committees.sunderland.gov.uk/committees/cmis5/Memb \n ers/tabid/62/ctl/ViewCMIS_Person/mid/600/id/1944/ScreenMod \n e/Ward/Default.aspx \n[10:10:55] Scraping from base.py:49\n https://committees.sunderland.gov.uk/committees/cmis5/Memb \n ers/tabid/62/ctl/ViewCMIS_Person/mid/600/id/1906/ScreenMod \n e/Ward/Default.aspx \n[10:10:58] Scraping from base.py:49\n https://committees.sunderland.gov.uk/committees/cmis5/Memb \n ers/tabid/62/ctl/ViewCMIS_Person/mid/600/id/1981/ScreenMod \n e/Ward/Default.aspx \n[10:11:00] Scraping from base.py:49\n https://committees.sunderland.gov.uk/committees/cmis5/Memb \n ers/tabid/62/ctl/ViewCMIS_Person/mid/600/id/1990/ScreenMod \n e/Ward/Default.aspx \n[10:11:01] Scraping from base.py:49\n https://committees.sunderland.gov.uk/committees/cmis5/Memb \n ers/tabid/62/ctl/ViewCMIS_Person/mid/600/id/1247/ScreenMod \n e/Ward/Default.aspx \n[10:11:04] Scraping from base.py:49\n https://committees.sunderland.gov.uk/committees/cmis5/Memb \n ers/tabid/62/ctl/ViewCMIS_Person/mid/600/id/1588/ScreenMod \n e/Ward/Default.aspx \n[10:11:07] Scraping from base.py:49\n https://committees.sunderland.gov.uk/committees/cmis5/Memb \n ers/tabid/62/ctl/ViewCMIS_Person/mid/600/id/1359/ScreenMod \n e/Ward/Default.aspx \n[10:11:10] Scraping from base.py:49\n https://committees.sunderland.gov.uk/committees/cmis5/Memb \n ers/tabid/62/ctl/ViewCMIS_Person/mid/600/id/1823/ScreenMod \n e/Ward/Default.aspx \n[10:11:11] Scraping from base.py:49\n https://committees.sunderland.gov.uk/committees/cmis5/Memb \n ers/tabid/62/ctl/ViewCMIS_Person/mid/600/id/1936/ScreenMod \n e/Ward/Default.aspx \n[10:11:14] Scraping from base.py:49\n https://committees.sunderland.gov.uk/committees/cmis5/Memb \n ers/tabid/62/ctl/ViewCMIS_Person/mid/600/id/1959/ScreenMod \n e/Ward/Default.aspx \n[10:11:18] Scraping from base.py:49\n https://committees.sunderland.gov.uk/committees/cmis5/Memb \n ers/tabid/62/ctl/ViewCMIS_Person/mid/600/id/1415/ScreenMod \n e/Ward/Default.aspx \n[10:11:20] Scraping from base.py:49\n https://committees.sunderland.gov.uk/committees/cmis5/Memb \n ers/tabid/62/ctl/ViewCMIS_Person/mid/600/id/1916/ScreenMod \n e/Ward/Default.aspx \n[10:11:22] Scraping from base.py:49\n https://committees.sunderland.gov.uk/committees/cmis5/Memb \n ers/tabid/62/ctl/ViewCMIS_Person/mid/600/id/1744/ScreenMod \n e/Ward/Default.aspx \n[10:11:24] Scraping from base.py:49\n https://committees.sunderland.gov.uk/committees/cmis5/Memb \n ers/tabid/62/ctl/ViewCMIS_Person/mid/600/id/1860/ScreenMod \n e/Ward/Default.aspx \n[10:11:26] Scraping from base.py:49\n https://committees.sunderland.gov.uk/committees/cmis5/Memb \n ers/tabid/62/ctl/ViewCMIS_Person/mid/600/id/1818/ScreenMod \n e/Ward/Default.aspx \n[10:11:28] Scraping from base.py:49\n https://committees.sunderland.gov.uk/committees/cmis5/Memb \n ers/tabid/62/ctl/ViewCMIS_Person/mid/600/id/1992/ScreenMod \n e/Ward/Default.aspx \n[10:11:29] Scraping from base.py:49\n https://committees.sunderland.gov.uk/committees/cmis5/Memb \n ers/tabid/62/ctl/ViewCMIS_Person/mid/600/id/1814/ScreenMod \n e/Ward/Default.aspx \n[10:11:31] Scraping from base.py:49\n https://committees.sunderland.gov.uk/committees/cmis5/Memb \n ers/tabid/62/ctl/ViewCMIS_Person/mid/600/id/1819/ScreenMod \n e/Ward/Default.aspx \n[10:11:33] Scraping from base.py:49\n https://committees.sunderland.gov.uk/committees/cmis5/Memb \n ers/tabid/62/ctl/ViewCMIS_Person/mid/600/id/1910/ScreenMod \n e/Ward/Default.aspx \n[10:11:35] Scraping from base.py:49\n https://committees.sunderland.gov.uk/committees/cmis5/Memb \n ers/tabid/62/ctl/ViewCMIS_Person/mid/600/id/1399/ScreenMod \n e/Ward/Default.aspx \n[10:11:40] Scraping from base.py:49\n https://committees.sunderland.gov.uk/committees/cmis5/Memb \n ers/tabid/62/ctl/ViewCMIS_Person/mid/600/id/1940/ScreenMod \n e/Ward/Default.aspx \n[10:11:43] Scraping from base.py:49\n https://committees.sunderland.gov.uk/committees/cmis5/Memb \n ers/tabid/62/ctl/ViewCMIS_Person/mid/600/id/1993/ScreenMod \n e/Ward/Default.aspx \n[10:11:45] Scraping from base.py:49\n https://committees.sunderland.gov.uk/committees/cmis5/Memb \n ers/tabid/62/ctl/ViewCMIS_Person/mid/600/id/1956/ScreenMod \n e/Ward/Default.aspx \n[10:11:47] Scraping from base.py:49\n https://committees.sunderland.gov.uk/committees/cmis5/Memb \n ers/tabid/62/ctl/ViewCMIS_Person/mid/600/id/1980/ScreenMod \n e/Ward/Default.aspx \n[10:11:49] Scraping from base.py:49\n https://committees.sunderland.gov.uk/committees/cmis5/Memb \n ers/tabid/62/ctl/ViewCMIS_Person/mid/600/id/1852/ScreenMod \n e/Ward/Default.aspx \n[10:11:51] Scraping from base.py:49\n https://committees.sunderland.gov.uk/committees/cmis5/Memb \n ers/tabid/62/ctl/ViewCMIS_Person/mid/600/id/1900/ScreenMod \n e/Ward/Default.aspx \n[10:11:53] Scraping from base.py:49\n https://committees.sunderland.gov.uk/committees/cmis5/Memb \n ers/tabid/62/ctl/ViewCMIS_Person/mid/600/id/1766/ScreenMod \n e/Ward/Default.aspx \n[10:11:56] Scraping from base.py:49\n https://committees.sunderland.gov.uk/committees/cmis5/Memb \n ers/tabid/62/ctl/ViewCMIS_Person/mid/600/id/1917/ScreenMod \n e/Ward/Default.aspx \n[10:11:57] Scraping from base.py:49\n https://committees.sunderland.gov.uk/committees/cmis5/Memb \n ers/tabid/62/ctl/ViewCMIS_Person/mid/600/id/1642/ScreenMod \n e/Ward/Default.aspx \n[10:12:00] Scraping from base.py:49\n https://committees.sunderland.gov.uk/committees/cmis5/Memb \n ers/tabid/62/ctl/ViewCMIS_Person/mid/600/id/1390/ScreenMod \n e/Ward/Default.aspx \n[10:12:05] Scraping from base.py:49\n https://committees.sunderland.gov.uk/committees/cmis5/Memb \n ers/tabid/62/ctl/ViewCMIS_Person/mid/600/id/1996/ScreenMod \n e/Ward/Default.aspx \n[10:12:06] Scraping from base.py:49\n https://committees.sunderland.gov.uk/committees/cmis5/Memb \n ers/tabid/62/ctl/ViewCMIS_Person/mid/600/id/1979/ScreenMod \n e/Ward/Default.aspx \n[10:12:08] Scraping from base.py:49\n https://committees.sunderland.gov.uk/committees/cmis5/Memb \n ers/tabid/62/ctl/ViewCMIS_Person/mid/600/id/1365/ScreenMod \n e/Ward/Default.aspx \n[10:12:11] Scraping from base.py:49\n https://committees.sunderland.gov.uk/committees/cmis5/Memb \n ers/tabid/62/ctl/ViewCMIS_Person/mid/600/id/1851/ScreenMod \n e/Ward/Default.aspx \n[10:12:14] Committing batch 1 consisting of 92 files base.py:297\n[10:12:15] Scraping from base.py:49\n https://committees.sunderland.gov.uk/committees/cmis5/Memb \n ers/tabid/62/ctl/ViewCMIS_Person/mid/600/id/1746/ScreenMod \n e/Ward/Default.aspx \n[10:12:18] Scraping from base.py:49\n https://committees.sunderland.gov.uk/committees/cmis5/Memb \n ers/tabid/62/ctl/ViewCMIS_Person/mid/600/id/1817/ScreenMod \n e/Ward/Default.aspx \n[10:12:20] Scraping from base.py:49\n https://committees.sunderland.gov.uk/committees/cmis5/Memb \n ers/tabid/62/ctl/ViewCMIS_Person/mid/600/id/1995/ScreenMod \n e/Ward/Default.aspx \n[10:12:21] Scraping from base.py:49\n https://committees.sunderland.gov.uk/committees/cmis5/Memb \n ers/tabid/62/ctl/ViewCMIS_Person/mid/600/id/1977/ScreenMod \n e/Ward/Default.aspx \n[10:12:39] Scraping from base.py:49\n https://committees.sunderland.gov.uk/committees/cmis5/Memb \n ers/tabid/62/ctl/ViewCMIS_Person/mid/600/id/1367/ScreenMod \n e/Ward/Default.aspx \n[10:13:09] The read operation timed out handlers.py:36\n Committing batch 2 consisting of 8 files base.py:297\n[10:13:11] Finished attempting to scrape: SND 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 57, in run\n councillor = self.get_single_councillor(councillor_html)\n File \"/var/task/lgsf/councillors/scrapers.py\", line 310, in get_single_councillor\n req = self.get(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":"2024-09-12 10:10:21.111960","end":"2024-09-12 10:13:11.184182","duration":170}},{"council_id":"TEW","missing":false,"latest_run":{"status_code":1,"log_text":"[10:37:56] Fetching Scraper for: TEW handlers.py:23\n Begin attempting to scrape: TEW handlers.py:27\n[10:37:57] 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[10:37:58] ...data deleted. base.py:264\n Scraping from base.py:49\n http://minutes.tewkesbury.gov.uk/mgWebService.asmx/GetCoun \n cillorsByWard \n[10:38:14] [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":"2024-09-12 10:37:56.809274","end":"2024-09-12 10:38:14.556080","duration":17}},{"council_id":"THE","missing":false,"latest_run":{"status_code":1,"log_text":"[10:27:48] Fetching Scraper for: THE handlers.py:23\n Begin attempting to scrape: THE handlers.py:27\n Deleting existing data... base.py:257\n[10:27:49] 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[10:27:50] ...data deleted. base.py:264\n Scraping from base.py:49\n https://www.threerivers.gov.uk/listing/councillors \n[10:27:51] 'NoneType' object has no attribute 'findNext' handlers.py:36\n[10:27:52] 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":"2024-09-12 10:27:48.407318","end":"2024-09-12 10:27:52.115816","duration":3}}] +[{"council_id":"BDG","missing":false,"latest_run":{"status_code":1,"log_text":"[09:28:09] Fetching Scraper for: BDG handlers.py:23\n Begin attempting to scrape: BDG handlers.py:27\n[09:28:10] 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[09:28:11] ...data deleted. base.py:264\n Scraping from base.py:49\n https://modgov.lbbd.gov.uk/internet/mgWebService.asmx/GetC \n ouncillorsByWard \n[09:28:27] [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":"2024-09-13 09:28:09.889627","end":"2024-09-13 09:28:27.377509","duration":17}},{"council_id":"BOL","missing":false,"latest_run":{"status_code":1,"log_text":"[08:42:32] Fetching Scraper for: BOL handlers.py:23\n Begin attempting to scrape: BOL handlers.py:27\n[08:42:33] 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[08:42:34] ...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":"2024-09-13 08:42:32.880926","end":"2024-09-13 08:42:34.910002","duration":2}},{"council_id":"CAN","missing":false,"latest_run":{"status_code":1,"log_text":"[09:58:14] Fetching Scraper for: CAN handlers.py:23\n[09:58:15] 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[09:58:16] ...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.cannockchasedc.gov.uk/council/about-council/yo \n ur-councillors \n[09:58:19] 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":"2024-09-13 09:58:14.988595","end":"2024-09-13 09:58:19.329694","duration":4}},{"council_id":"CAS","missing":false,"latest_run":{"status_code":1,"log_text":"[08:53:05] Fetching Scraper for: CAS handlers.py:23\n Begin attempting to scrape: CAS handlers.py:27\n[08:53:06] 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[08:53:07] ...data deleted. base.py:264\n Scraping from https://www.castlepoint.gov.uk/councillors base.py:49\n[08:53:08] 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[08:53:09] 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":"2024-09-13 08:53:05.547898","end":"2024-09-13 08:53:09.099689","duration":3}},{"council_id":"CMD","missing":false,"latest_run":{"status_code":1,"log_text":"[10:47:38] Fetching Scraper for: CMD handlers.py:23\n Begin attempting to scrape: CMD handlers.py:27\n Deleting existing data... base.py:257\n[10:47:39] 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[10:47:40] ...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":"2024-09-13 10:47:38.389175","end":"2024-09-13 10:47:40.643337","duration":2}},{"council_id":"EAY","missing":false,"latest_run":{"status_code":1,"log_text":"[09:21:25] Fetching Scraper for: EAY handlers.py:23\n Begin attempting to scrape: EAY handlers.py:27\n[09:21:26] 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[09:21:27] ...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[09:21:28] 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[09:21:29] '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":"2024-09-13 09:21:25.580296","end":"2024-09-13 09:21:29.513464","duration":3}},{"council_id":"GLG","missing":false,"latest_run":{"status_code":1,"log_text":"[09:10:44] Fetching Scraper for: GLG handlers.py:23\n Begin attempting to scrape: GLG handlers.py:27\n Deleting existing data... base.py:257\n Getting all files in Councillors... base.py:209\n[09:10:45] ...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 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[09:10:46] 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":"2024-09-13 09:10:44.101703","end":"2024-09-13 09:10:46.212541","duration":2}},{"council_id":"GLS","missing":false,"latest_run":{"status_code":1,"log_text":"[10:18:49] Fetching Scraper for: GLS handlers.py:23\n Begin attempting to scrape: GLS handlers.py:27\n[10:18:50] Deleting existing data... base.py:257\n Getting all files in Councillors... base.py:209\n[10:18:51] ...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[10:19:07] [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":"2024-09-13 10:18:49.839401","end":"2024-09-13 10:19:07.564136","duration":17}},{"council_id":"GRE","missing":false,"latest_run":{"status_code":1,"log_text":"[10:43:48] Fetching Scraper for: GRE handlers.py:23\n Begin attempting to scrape: GRE handlers.py:27\n Deleting existing data... base.py:257\n[10:43:49] 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[10:43:50] ...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 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":"2024-09-13 10:43:48.492184","end":"2024-09-13 10:43:50.801946","duration":2}},{"council_id":"MON","missing":false,"latest_run":{"status_code":1,"log_text":"[09:29:05] Fetching Scraper for: MON handlers.py:23\n Begin attempting to scrape: MON handlers.py:27\n Deleting existing data... base.py:257\n[09:29:06] Getting all files in Councillors... base.py:209\n Getting all files in Councillors/json... base.py:209\n ...found 46 files in Councillors/json base.py:225\n Getting all files in Councillors/raw... base.py:209\n ...found 46 files in Councillors/raw base.py:225\n ...found 93 files in Councillors base.py:225\n Deleting batch no. 1 consisting of 93 files base.py:236\n[09:29:07] ...data deleted. base.py:264\n Scraping from base.py:49\n https://democracy.monmouthshire.gov.uk/mgWebService.asmx/G \n etCouncillorsByWard \n[09:29:39] The read operation timed out handlers.py:36\n[09:29:40] Finished attempting to scrape: MON 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":"2024-09-13 09:29:05.407910","end":"2024-09-13 09:29:40.321446","duration":34}},{"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":"[09:05:03] Fetching Scraper for: TEW handlers.py:23\n Begin attempting to scrape: TEW handlers.py:27\n[09:05:04] Deleting existing data... base.py:257\n Getting all files in Councillors... base.py:209\n[09:05:05] ...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[09:05:21] [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":"2024-09-13 09:05:03.860024","end":"2024-09-13 09:05:21.680775","duration":17}},{"council_id":"THE","missing":false,"latest_run":{"status_code":1,"log_text":"[10:20:08] Fetching Scraper for: THE handlers.py:23\n Begin attempting to scrape: THE handlers.py:27\n Deleting existing data... base.py:257\n[10:20:09] 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[10:20:10] ...data deleted. base.py:264\n Scraping from base.py:49\n https://www.threerivers.gov.uk/listing/councillors \n[10:20:14] '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":"2024-09-13 10:20:08.327848","end":"2024-09-13 10:20:14.945709","duration":6}}] diff --git a/index.html b/index.html index 06f8c5920d..cd893b4e97 100644 --- a/index.html +++ b/index.html @@ -49,10 +49,6 @@
[10:17:55] Fetching Scraper for: ABC handlers.py:23 + Begin attempting to scrape: ABC handlers.py:27 +[10:17:56] Deleting existing data... base.py:257 + Getting all files in Councillors... base.py:209 + Getting all files in Councillors/json... base.py:209 +[10:17:57] ...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 + ...data deleted. base.py:264 + Scraping from base.py:49 + https://www.armaghbanbridgecraigavon.gov.uk/councillors/ +[10:18:01] Committing batch 1 consisting of 32 files base.py:297 +[10:18:02] Finished attempting to scrape: ABC base.py:345 ++ + + + +
[09:30:19] Fetching Scraper for: ABC handlers.py:23 - Begin attempting to scrape: ABC handlers.py:27 -[09:30:20] Deleting existing data... base.py:257 - Getting all files in Councillors... base.py:209 - Getting all files in Councillors/json... base.py:209 -[09:30:21] ...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 -[09:30:22] ...data deleted. base.py:264 - Scraping from base.py:49 - https://www.armaghbanbridgecraigavon.gov.uk/councillors/ -[09:30:25] Committing batch 1 consisting of 32 files base.py:297 -[09:30:26] Finished attempting to scrape: ABC base.py:345 -- -