diff --git a/api/failing.json b/api/failing.json index 27bedf0490..5278f0b2d1 100644 --- a/api/failing.json +++ b/api/failing.json @@ -1 +1 @@ -[{"council_id":"BDG","missing":false,"latest_run":{"status_code":1,"log_text":"[09:55:58] Fetching Scraper for: BDG handlers.py:23\n Begin attempting to scrape: BDG handlers.py:27\n[09:55:59] 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[09:56:00] ...data deleted. base.py:264\n Scraping from base.py:49\n https://modgov.lbbd.gov.uk/internet/mgWebService.asmx/GetC \n ouncillorsByWard \n[09:56:15] [Errno 110] Connection timed out handlers.py:36\n[09:56:16] 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":"2024-10-05 09:55:58.756427","end":"2024-10-05 09:56:16.209989","duration":17}},{"council_id":"BOL","missing":false,"latest_run":{"status_code":1,"log_text":"[10:24:57] Fetching Scraper for: BOL handlers.py:23\n Begin attempting to scrape: BOL handlers.py:27\n Deleting existing data... base.py:257\n Getting all files in Councillors... base.py:209\n[10:24:58] ...found 1 files in Councillors base.py:225\n Deleting batch no. 1 consisting of 1 files base.py:236\n ...data deleted. base.py:264\n Scraping from base.py:49\n https://www.democracy.bolton.gov.uk/cmis5/People.aspx \n[10:24:59] [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":"2024-10-05 10:24:57.087798","end":"2024-10-05 10:24:59.242208","duration":2}},{"council_id":"CAN","missing":false,"latest_run":{"status_code":1,"log_text":"[09:35:02] Fetching Scraper for: CAN handlers.py:23\n Begin attempting to scrape: CAN handlers.py:27\n[09:35:03] 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[09:35:04] ...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[09:35:06] 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":"2024-10-05 09:35:02.680253","end":"2024-10-05 09:35:06.973622","duration":4}},{"council_id":"CAS","missing":false,"latest_run":{"status_code":1,"log_text":"[08:37:15] Fetching Scraper for: CAS handlers.py:23\n Begin attempting to scrape: CAS handlers.py:27\n Deleting existing data... base.py:257\n[08:37:16] 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[08:37:17] ...data deleted. base.py:264\n Scraping from https://www.castlepoint.gov.uk/councillors base.py:49\n[08:37:18] 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":"2024-10-05 08:37:15.327649","end":"2024-10-05 08:37:18.765185","duration":3}},{"council_id":"CMD","missing":false,"latest_run":{"status_code":1,"log_text":"[09:26:43] Fetching Scraper for: CMD handlers.py:23\n Begin attempting to scrape: CMD handlers.py:27\n Deleting existing data... base.py:257\n[09:26:44] 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[09:26:45] ...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":"2024-10-05 09:26:43.540214","end":"2024-10-05 09:26:45.654403","duration":2}},{"council_id":"EAY","missing":false,"latest_run":{"status_code":1,"log_text":"[09:55:25] Fetching Scraper for: EAY handlers.py:23\n Begin attempting to scrape: EAY handlers.py:27\n Deleting existing data... base.py:257\n[09:55:26] Getting all files in Councillors... base.py:209\n ...found 1 files in Councillors base.py:225\n Deleting batch no. 1 consisting of 1 files base.py:236\n[09:55:27] ...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[09:55:28] 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[09:55:29] '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":"2024-10-05 09:55:25.390172","end":"2024-10-05 09:55:29.446900","duration":4}},{"council_id":"GLG","missing":false,"latest_run":{"status_code":1,"log_text":"[10:34:53] Fetching Scraper for: GLG handlers.py:23\n Begin attempting to scrape: GLG handlers.py:27\n Deleting existing data... base.py:257\n[10:34:54] Getting all files in Councillors... base.py:209\n ...found 1 files in Councillors base.py:225\n Deleting batch no. 1 consisting of 1 files base.py:236\n[10:34:55] ...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":"2024-10-05 10:34:53.165124","end":"2024-10-05 10:34:55.435497","duration":2}},{"council_id":"GLS","missing":false,"latest_run":{"status_code":1,"log_text":"[10:29:12] Fetching Scraper for: GLS handlers.py:23\n Begin attempting to scrape: GLS handlers.py:27\n Deleting existing data... base.py:257\n[10:29:13] 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[10:29:14] ...data deleted. base.py:264\n Scraping from base.py:49\n http://glostext.gloucestershire.gov.uk//mgWebService.asmx/ \n GetCouncillorsByWard \n[10:29:29] [Errno 110] Connection timed out handlers.py:36\n[10:29:30] 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":"2024-10-05 10:29:12.425677","end":"2024-10-05 10:29:30.002821","duration":17}},{"council_id":"GRE","missing":false,"latest_run":{"status_code":1,"log_text":"[10:18:37] Fetching Scraper for: GRE handlers.py:23\n Begin attempting to scrape: GRE handlers.py:27\n[10:18:38] Deleting existing data... base.py:257\n Getting all files in Councillors... base.py:209\n ...found 1 files in Councillors base.py:225\n Deleting batch no. 1 consisting of 1 files base.py:236\n[10:18:39] ...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[10:18:44] 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":"2024-10-05 10:18:37.795637","end":"2024-10-05 10:18:44.452867","duration":6}},{"council_id":"SHE","missing":false,"latest_run":{"status_code":null,"log_text":"[11:28:20] Fetching Scraper for: SHE handlers.py:22\n Begin attempting to scrape: SHE handlers.py:25\n Deleting existing data... base.py:234\n Getting all files in SHE... base.py:186\n[11:28:21] Getting all files in SHE/json... base.py:186\n ...found 30 files in SHE/json base.py:202\n Getting all files in SHE/raw... base.py:186\n ...found 30 files in SHE/raw base.py:202\n ...found 61 files in SHE base.py:202\n Deleting batch no. 1 consisting of 61 files base.py:211\n[11:28:32] An error occurred (ThrottlingException) when calling handlers.py:34\n the CreateCommit operation (reached max retries: 4): \n Rate exceeded \n Finished attempting to scrape: SHE base.py:319\n","errors":"An error occurred (ThrottlingException) when calling the CreateCommit operation (reached max retries: 4): Rate exceeded","start":"2022-04-04 11:28:20.509898","end":"2022-04-04 11:28:32.871624","duration":12}},{"council_id":"STG","missing":false,"latest_run":{"status_code":1,"log_text":"[10:16:39] Fetching Scraper for: STG handlers.py:23\n Begin attempting to scrape: STG handlers.py:27\n Deleting existing data... base.py:257\n[10:16:40] Getting all files in Councillors... base.py:209\n Getting all files in Councillors/json... base.py:209\n ...found 19 files in Councillors/json base.py:225\n Getting all files in Councillors/raw... base.py:209\n[10:16:41] ...found 19 files in Councillors/raw base.py:225\n ...found 39 files in Councillors base.py:225\n Deleting batch no. 1 consisting of 39 files base.py:236\n ...data deleted. base.py:264\n Scraping from base.py:49\n https://www.stirling.gov.uk/council-and-committees/politic \n ians-and-elections/councillors/ \n[10:16:43] Scraping from base.py:49\n https://www.stirling.gov.uk/council-and-committees/politic \n ians-and-councillors/your-councillors/elaine-watterson/ \n[10:16:44] Scraping from base.py:49\n https://www.stirling.gov.uk/council-and-committees/politic \n ians-and-councillors/your-councillors/gene-maxwell/ \n[10:16:45] Scraping from base.py:49\n https://www.stirling.gov.uk/council-and-committees/politic \n ians-and-councillors/your-councillors/martin-earl/ \n[10:16:46] Scraping from base.py:49\n https://www.stirling.gov.uk/council-and-committees/politic \n ians-and-councillors/your-councillors/gerry-mcgarvey/ \n[10:16:47] Scraping from base.py:49\n https://www.stirling.gov.uk/council-and-committees/politic \n ians-and-councillors/your-councillors/paul-henke/ \n[10:16:49] Scraping from base.py:49\n https://www.stirling.gov.uk/council-and-committees/politic \n ians-and-councillors/your-councillors/rosemary-fraser/ \n[10:16:50] Scraping from base.py:49\n https://www.stirling.gov.uk/council-and-committees/politic \n ians-and-councillors/your-councillors/alasdair-tollemache/ \n[10:16:51] Scraping from base.py:49\n https://www.stirling.gov.uk/council-and-committees/politic \n ians-and-councillors/your-councillors/david-wilson/ \n[10:16:52] Scraping from base.py:49\n https://www.stirling.gov.uk/council-and-committees/politic \n ians-and-councillors/your-councillors/robin-kleinman/ \n[10:16:53] Scraping from base.py:49\n https://www.stirling.gov.uk/council-and-committees/politic \n ians-and-councillors/your-councillors/thomas-heald/ \n[10:16:54] Scraping from base.py:49\n https://www.stirling.gov.uk/council-and-committees/politic \n ians-and-councillors/your-councillors/danny-gibson/ \n[10:16:56] Scraping from base.py:49\n https://www.stirling.gov.uk/council-and-committees/politic \n ians-and-councillors/your-councillors/jim-thomson/ \n[10:16:57] Scraping from base.py:49\n https://www.stirling.gov.uk/council-and-committees/politic \n ians-and-councillors/your-councillors/rachel-nunn/ \n[10:16:58] Scraping from base.py:49\n https://www.stirling.gov.uk/council-and-committees/politic \n ians-and-councillors/your-councillors/susan-mcgill/ \n[10:16:59] Scraping from base.py:49\n https://www.stirling.gov.uk/council-and-committees/politic \n ians-and-councillors/your-councillors/jen-preston/ \n[10:17:00] Scraping from base.py:49\n https://www.stirling.gov.uk/council-and-committees/politic \n ians-and-councillors/your-councillors/neil-benny/ \n[10:17:01] Scraping from base.py:49\n https://www.stirling.gov.uk/council-and-committees/politic \n ians-and-councillors/your-councillors/scott-farmer/ \n[10:17:04] Scraping from base.py:49\n https://www.stirling.gov.uk/council-and-committees/politic \n ians-and-councillors/your-councillors/bryan-flannagan/ \n[10:17:05] Scraping from base.py:49\n https://www.stirling.gov.uk/council-and-committees/politic \n ians-and-councillors/your-councillors/gerry-mclaughlan/ \n[10:17:06] Scraping from base.py:49\n https://www.stirling.gov.uk/council-and-committees/politic \n ians-and-councillors/your-councillors/vacant/ \n[10:17:07] 'NoneType' object is not subscriptable handlers.py:36\n Committing batch 1 consisting of 38 files base.py:297\n[10:17:08] Finished attempting to scrape: STG base.py:345\n","errors":"Traceback (most recent call last):\n File \"/var/task/lgsf/aws_lambda/handlers.py\", line 32, in scraper_worker_handler\n scraper.run(run_log)\n File \"/var/task/lgsf/councillors/scrapers.py\", line 57, in run\n councillor = self.get_single_councillor(councillor_html)\n File \"scrapers/STG-stirling/councillors.py\", line 42, in get_single_councillor\n councillor.email = soup.select_one(\"a[href^=mailto]\")[\nTypeError: 'NoneType' object is not subscriptable\n","start":"2024-10-05 10:16:39.475772","end":"2024-10-05 10:17:08.670049","duration":29}},{"council_id":"TEI","missing":false,"latest_run":{"status_code":1,"log_text":"[10:47:06] Fetching Scraper for: TEI handlers.py:23\n Begin attempting to scrape: TEI handlers.py:27\n Deleting existing data... base.py:257\n[10:47:07] Getting all files in Councillors... base.py:209\n Getting all files in Councillors/json... base.py:209\n ...found 47 files in Councillors/json base.py:225\n Getting all files in Councillors/raw... base.py:209\n ...found 47 files in Councillors/raw base.py:225\n ...found 95 files in Councillors base.py:225\n Deleting batch no. 1 consisting of 95 files base.py:236\n[10:47:08] ...data deleted. base.py:264\n Scraping from base.py:49\n http://democracy.teignbridge.gov.uk/mgWebService.asmx/GetC \n ouncillorsByWard \n[10:47:09] [Errno 113] No route to host handlers.py:36\n Finished attempting to scrape: TEI 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 113] No route to host\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 113] No route to host\n","start":"2024-10-05 10:47:06.199364","end":"2024-10-05 10:47:09.944665","duration":3}},{"council_id":"TEW","missing":false,"latest_run":{"status_code":1,"log_text":"[09:52:52] Fetching Scraper for: TEW handlers.py:23\n Begin attempting to scrape: TEW handlers.py:27\n[09:52:53] 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[09:52:54] ...data deleted. base.py:264\n Scraping from base.py:49\n http://minutes.tewkesbury.gov.uk/mgWebService.asmx/GetCoun \n cillorsByWard \n[09:53:24] 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 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: 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: timed out\n","start":"2024-10-05 09:52:52.581601","end":"2024-10-05 09:53:24.915424","duration":32}},{"council_id":"THE","missing":false,"latest_run":{"status_code":1,"log_text":"[09:28:40] Fetching Scraper for: THE handlers.py:23\n Begin attempting to scrape: THE handlers.py:27\n Deleting existing data... base.py:257\n[09:28:41] 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[09:28:42] ...data deleted. base.py:264\n Scraping from base.py:49\n https://www.threerivers.gov.uk/listing/councillors \n[09:28:43] 'NoneType' object has no attribute 'findNext' handlers.py:36\n[09:28:44] 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":"2024-10-05 09:28:40.334838","end":"2024-10-05 09:28:44.237280","duration":3}},{"council_id":"VGL","missing":false,"latest_run":{"status_code":1,"log_text":"[08:54:31] Fetching Scraper for: VGL handlers.py:23\n Begin attempting to scrape: VGL handlers.py:27\n[08:54:32] 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[08:54:33] ...found 16 files in Councillors/json base.py:225\n Getting all files in Councillors/raw... base.py:209\n ...found 16 files in Councillors/raw base.py:225\n ...found 33 files in Councillors base.py:225\n Deleting batch no. 1 consisting of 33 files base.py:236\n[08:54:34] ...data deleted. base.py:264\n Scraping from base.py:49\n https://www.valeofglamorgan.gov.uk/en/our_council/Council- \n Structure/councillors/Councillors.aspx \n[08:54:36] Scraping from base.py:49\n https://www.valeofglamorgan.gov.uk/en/our_council/Council- \n Structure/councillors/Asbrey-Anne.aspx \n[08:54:37] Scraping from base.py:49\n https://www.valeofglamorgan.gov.uk/en/our_council/Council- \n Structure/councillors/Aviet-Julie.aspx \n[08:54:39] Scraping from base.py:49\n https://www.valeofglamorgan.gov.uk/en/our_council/Council- \n Structure/councillors/Ball-Gareth.aspx \n[08:54:41] Scraping from base.py:49\n https://www.valeofglamorgan.gov.uk/en/our_council/Council- \n Structure/councillors/Birch-Rhiannon.aspx \n[08:54:42] Scraping from base.py:49\n https://www.valeofglamorgan.gov.uk/en/our_council/Council- \n Structure/councillors/Brooks-Bronwen.aspx \n[08:54:44] Scraping from base.py:49\n https://www.valeofglamorgan.gov.uk/en/our_council/Council- \n Structure/councillors/Bruce-Gillian.aspx \n[08:54:45] Scraping from base.py:49\n https://www.valeofglamorgan.gov.uk/en/our_council/Council- \n Structure/councillors/Buckley-Ian.aspx \n[08:54:47] Scraping from base.py:49\n https://www.valeofglamorgan.gov.uk/en/our_council/Council- \n Structure/councillors/Burnett-Lis.aspx \n[08:54:49] Scraping from base.py:49\n https://www.valeofglamorgan.gov.uk/en/our_council/Council- \n Structure/councillors/Campbell-Samantha.aspx \n[08:54:50] Scraping from base.py:49\n https://www.valeofglamorgan.gov.uk/en/our_council/Council- \n Structure/councillors/Carroll-George.aspx \n[08:54:52] Scraping from base.py:49\n https://www.valeofglamorgan.gov.uk/en/our_council/Council- \n Structure/councillors/Cave-Christine.aspx \n[08:54:55] Scraping from base.py:49\n https://www.valeofglamorgan.gov.uk/en/our_council/Council- \n Structure/councillors/Champion-Charles.aspx \n[08:54:56] Scraping from base.py:49\n https://www.valeofglamorgan.gov.uk/en/our_council/Council- \n Structure/councillors/Charles-Janice.aspx \n[08:54:58] Scraping from base.py:49\n https://www.valeofglamorgan.gov.uk/en/our_council/Council- \n Structure/councillors/Collins-Amelia.aspx \n[08:54:59] Scraping from base.py:49\n https://www.valeofglamorgan.gov.uk/en/our_council/Council- \n Structure/councillors/Cowpe-Marianne.aspx \n[08:55:01] Scraping from base.py:49\n https://www.valeofglamorgan.gov.uk/en/our_council/Council- \n Structure/councillors/Drake-Pamela.aspx \n[08:55:02] Scraping from base.py:49\n https://www.valeofglamorgan.gov.uk/en/our_council/Council- \n Structure/councillors/Driscoll-Vincent.aspx \n[08:55:04] 'NoneType' object has no attribute 'get_text' handlers.py:36\n Committing batch 1 consisting of 32 files base.py:297\n[08:55:05] Finished attempting to scrape: VGL 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/VGL-the-vale-of-glamorgan/councillors.py\", line 36, in get_single_councillor\n email_text = soup.select_one(\"#S4_EmailPlaceholder\").get_text(\nAttributeError: 'NoneType' object has no attribute 'get_text'\n","start":"2024-10-05 08:54:31.714191","end":"2024-10-05 08:55:05.978018","duration":34}},{"council_id":"WLN","missing":false,"latest_run":{"status_code":1,"log_text":"[09:00:15] Fetching Scraper for: WLN handlers.py:23\n Begin attempting to scrape: WLN handlers.py:27\n[09:00:16] 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[09:00:17] ...found 25 files in Councillors/json base.py:225\n Getting all files in Councillors/raw... base.py:209\n ...found 25 files in Councillors/raw base.py:225\n ...found 51 files in Councillors base.py:225\n Deleting batch no. 1 consisting of 51 files base.py:236\n ...data deleted. base.py:264\n Scraping from https://westlothian.gov.uk/councillors base.py:49\n[09:00:18] Scraping from base.py:49\n https://westlothian.gov.uk/article/33888/Linlithgow \n[09:00:19] Scraping from base.py:49\n https://westlothian.gov.uk/article/33889/Broxburn-Uphall-a \n nd-Winchburgh \n[09:00:20] Scraping from base.py:49\n https://westlothian.gov.uk/article/33890/Livingston-North \n[09:00:21] Scraping from base.py:49\n https://westlothian.gov.uk/article/33891/Livingston-South \n[09:00:22] Scraping from base.py:49\n https://westlothian.gov.uk/article/33893/East-Livingston-a \n nd-East-Calder \n Scraping from base.py:49\n https://westlothian.gov.uk/article/33892/Fauldhouse-and-th \n e-Breich-Valley \n[09:00:23] Scraping from base.py:49\n https://westlothian.gov.uk/article/33894/Whitburn-and-Blac \n kburn \n[09:00:24] Scraping from base.py:49\n https://westlothian.gov.uk/article/33895/Bathgate \n[09:00:25] Scraping from base.py:49\n https://westlothian.gov.uk/article/33896/Armadale-and-Blac \n kridge \n[09:00:26] Scraping from base.py:49\n https://westlothian.gov.uk/article/33897/Councillor-Tom-Co \n nn \n[09:00:27] Scraping from base.py:49\n https://westlothian.gov.uk/article/33898/Councillor-Paulin \n e-Orr \n Scraping from base.py:49\n https://westlothian.gov.uk/article/33899/Councillor-Sally- \n Pattle \n[09:00:28] Scraping from base.py:49\n https://westlothian.gov.uk/article/34305/Councillor-Tony-B \n oyle \n[09:00:29] Scraping from base.py:49\n https://westlothian.gov.uk/article/34302/Councillor-Diane- \n Calder \n[09:00:32] Scraping from base.py:49\n https://westlothian.gov.uk/article/34303/Councillor-Janet- \n Campbell \n[09:00:33] Scraping from base.py:49\n https://westlothian.gov.uk/article/34304/Councillor-Angela \n -Doran-Timson \n[09:00:34] Scraping from base.py:49\n https://westlothian.gov.uk/article/34307/Councillor-Alison \n -Adamson \n[09:00:35] Scraping from base.py:49\n https://westlothian.gov.uk/article/34306/Councillor-Robert \n -De-Bold \n[09:00:36] Scraping from base.py:49\n https://westlothian.gov.uk/article/34308/Councillor-Anne-M \n cMillan \n[09:00:37] Scraping from base.py:49\n https://westlothian.gov.uk/article/34309/Councillor-Andrew \n -Miller \n[09:00:38] Scraping from base.py:49\n https://westlothian.gov.uk/article/34311/Councillor-Lawren \n ce-Fitzpatrick \n[09:00:39] Scraping from base.py:49\n https://westlothian.gov.uk/article/34310/Councillor-Peter- \n Heggie \n[09:00:40] Scraping from base.py:49\n https://westlothian.gov.uk/article/34312/Councillor-Maria- \n MacAulay \n[09:00:41] Scraping from base.py:49\n https://westlothian.gov.uk/article/34313/Councillor-Moira- \n McKee-Shemilt \n[09:00:42] Scraping from base.py:49\n https://westlothian.gov.uk/article/34317/Councillor-Damian \n -Doran-Timson \n[09:00:43] Scraping from base.py:49\n https://westlothian.gov.uk/article/34315/Councillor-Carl-J \n ohn \n[09:00:44] Scraping from base.py:49\n https://westlothian.gov.uk/article/34316/Councillor-Danny- \n Logue \n Scraping from base.py:49\n https://westlothian.gov.uk/article/34314/Councillor-Veroni \n ca-Smith \n[09:00:45] Scraping from base.py:49\n https://westlothian.gov.uk/article/34318/Councillor-Paulin \n e-Clark \n[09:00:47] Scraping from base.py:49\n https://westlothian.gov.uk/article/34319/Councillor-Craig- \n Meek \n Scraping from base.py:49\n https://westlothian.gov.uk/article/34320/Councillor-Cathy- \n Muldoon \n[09:00:48] Scraping from base.py:49\n https://westlothian.gov.uk/article/34321/Councillor-Jim-Di \n ckson \n[09:00:50] Scraping from base.py:49\n https://westlothian.gov.uk/article/34322/Councillor-Mary-D \n ickson \n Scraping from base.py:49\n https://westlothian.gov.uk/article/34323/Councillor-George \n -Paul \n[09:00:51] Scraping from base.py:49\n https://westlothian.gov.uk/article/34324/Councillor-Vacant \n[09:00:52] list index out of range handlers.py:36\n Committing batch 1 consisting of 50 files base.py:297\n[09:00:54] Finished attempting to scrape: WLN 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/WLN-west-lothian/councillors.py\", line 37, in get_single_councillor\n councillor.email = soup.select(\"a[href^=mailto]\")[0].get_text(\nIndexError: list index out of range\n","start":"2024-10-05 09:00:15.726245","end":"2024-10-05 09:00:54.117343","duration":38}}] +[{"council_id":"BDG","missing":false,"latest_run":{"status_code":1,"log_text":"[08:34:12] Fetching Scraper for: BDG handlers.py:23\n Begin attempting to scrape: BDG handlers.py:27\n Deleting existing data... base.py:257\n[08:34:13] 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[08:34:14] ...data deleted. base.py:264\n Scraping from base.py:49\n https://modgov.lbbd.gov.uk/internet/mgWebService.asmx/GetC \n ouncillorsByWard \n[08:34:29] [Errno 110] Connection timed out handlers.py:36\n[08:34:30] 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":"2024-10-06 08:34:12.584216","end":"2024-10-06 08:34:30.161725","duration":17}},{"council_id":"BOL","missing":false,"latest_run":{"status_code":1,"log_text":"[08:27:29] Fetching Scraper for: BOL handlers.py:23\n Begin attempting to scrape: BOL handlers.py:27\n Deleting existing data... base.py:257\n[08:27:30] Getting all files in Councillors... base.py:209\n ...found 1 files in Councillors base.py:225\n Deleting batch no. 1 consisting of 1 files base.py:236\n[08:27:31] ...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":"2024-10-06 08:27:29.457339","end":"2024-10-06 08:27:31.566230","duration":2}},{"council_id":"CAN","missing":false,"latest_run":{"status_code":1,"log_text":"[09:45:50] Fetching Scraper for: CAN handlers.py:23\n Begin attempting to scrape: CAN handlers.py:27\n Deleting existing data... base.py:257\n[09:45:51] 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[09:45:52] ...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[09:45:54] 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":"2024-10-06 09:45:50.249579","end":"2024-10-06 09:45:54.469565","duration":4}},{"council_id":"CAS","missing":false,"latest_run":{"status_code":1,"log_text":"[10:41:56] Fetching Scraper for: CAS handlers.py:23\n Begin attempting to scrape: CAS handlers.py:27\n Deleting existing data... base.py:257\n[10:41:57] 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[10:41:58] ...data deleted. base.py:264\n Scraping from https://www.castlepoint.gov.uk/councillors base.py:49\n[10:41:59] 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":"2024-10-06 10:41:56.187431","end":"2024-10-06 10:41:59.451247","duration":3}},{"council_id":"CMD","missing":false,"latest_run":{"status_code":1,"log_text":"[08:40:37] Fetching Scraper for: CMD handlers.py:23\n Begin attempting to scrape: CMD handlers.py:27\n Deleting existing data... base.py:257\n[08:40:38] 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[08:40:39] ...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":"2024-10-06 08:40:37.372139","end":"2024-10-06 08:40:39.463902","duration":2}},{"council_id":"EAY","missing":false,"latest_run":{"status_code":1,"log_text":"[09:23:56] Fetching Scraper for: EAY handlers.py:23\n Begin attempting to scrape: EAY handlers.py:27\n[09:23:57] 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[09:23:58] ...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[09:23:59] 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[09:24:00] '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":"2024-10-06 09:23:56.632442","end":"2024-10-06 09:24:00.630465","duration":3}},{"council_id":"FEN","missing":false,"latest_run":{"status_code":1,"log_text":"[10:36:56] Fetching Scraper for: FEN handlers.py:23\n Begin attempting to scrape: FEN handlers.py:27\n[10:36:57] Deleting existing data... base.py:257\n Getting all files in Councillors... base.py:209\n Getting all files in Councillors/json... base.py:209\n ...found 43 files in Councillors/json base.py:225\n Getting all files in Councillors/raw... base.py:209\n[10:36:58] ...found 43 files in Councillors/raw base.py:225\n ...found 87 files in Councillors base.py:225\n Deleting batch no. 1 consisting of 87 files base.py:236\n ...data deleted. base.py:264\n Scraping from base.py:49\n https://www.fenland.gov.uk/localgov//mgWebService.asmx/Get \n CouncillorsByWard \n[10:37:28] The read operation timed out handlers.py:36\n[10:37:29] Finished attempting to scrape: FEN 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":"2024-10-06 10:36:56.710047","end":"2024-10-06 10:37:29.230461","duration":32}},{"council_id":"FLN","missing":false,"latest_run":{"status_code":1,"log_text":"[09:53:27] Fetching Scraper for: FLN handlers.py:23\n Begin attempting to scrape: FLN handlers.py:27\n[09:53:28] Deleting existing data... base.py:257\n Getting all files in Councillors... base.py:209\n Getting all files in Councillors/json... base.py:209\n ...found 67 files in Councillors/json base.py:225\n Getting all files in Councillors/raw... base.py:209\n[09:53:29] ...found 67 files in Councillors/raw base.py:225\n ...found 135 files in Councillors base.py:225\n Deleting batch no. 1 consisting of 100 files base.py:236\n Deleting batch no. 2 consisting of 35 files base.py:236\n[09:53:30] ...data deleted. base.py:264\n Scraping from base.py:49\n https://cyfarfodyddpwyllgor.siryfflint.gov.uk/mgWebService \n .asmx/GetCouncillorsByWard \n Server error '503 Service Unavailable' for url handlers.py:36\n 'https://cyfarfodyddpwyllgor.siryfflint.gov.uk/mgWebSe \n rvice.asmx/GetCouncillorsByWard' \n For more information check: \n https://developer.mozilla.org/en-US/docs/Web/HTTP/Stat \n us/503 \n Finished attempting to scrape: FLN 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 '503 Service Unavailable' for url 'https://cyfarfodyddpwyllgor.siryfflint.gov.uk/mgWebService.asmx/GetCouncillorsByWard'\nFor more information check: https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/503\n","start":"2024-10-06 09:53:27.701417","end":"2024-10-06 09:53:30.974815","duration":3}},{"council_id":"GLG","missing":false,"latest_run":{"status_code":1,"log_text":"[08:26:05] Fetching Scraper for: GLG handlers.py:23\n Begin attempting to scrape: GLG handlers.py:27\n Deleting existing data... base.py:257\n[08:26:06] 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[08:26:07] ...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":"2024-10-06 08:26:05.441477","end":"2024-10-06 08:26:07.723887","duration":2}},{"council_id":"GLS","missing":false,"latest_run":{"status_code":1,"log_text":"[08:47:01] Fetching Scraper for: GLS handlers.py:23\n Begin attempting to scrape: GLS handlers.py:27\n Deleting existing data... base.py:257\n[08:47:02] 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[08:47:03] ...data deleted. base.py:264\n Scraping from base.py:49\n http://glostext.gloucestershire.gov.uk//mgWebService.asmx/ \n GetCouncillorsByWard \n[08:47:18] [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":"2024-10-06 08:47:01.447593","end":"2024-10-06 08:47:18.923847","duration":17}},{"council_id":"GRE","missing":false,"latest_run":{"status_code":1,"log_text":"[10:44:14] Fetching Scraper for: GRE handlers.py:23\n Begin attempting to scrape: GRE handlers.py:27\n[10:44:15] 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[10:44:16] ...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[10:44:18] 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":"2024-10-06 10:44:14.851185","end":"2024-10-06 10:44:18.830878","duration":3}},{"council_id":"SHE","missing":false,"latest_run":{"status_code":null,"log_text":"[11:28:20] Fetching Scraper for: SHE handlers.py:22\n Begin attempting to scrape: SHE handlers.py:25\n Deleting existing data... base.py:234\n Getting all files in SHE... base.py:186\n[11:28:21] Getting all files in SHE/json... base.py:186\n ...found 30 files in SHE/json base.py:202\n Getting all files in SHE/raw... base.py:186\n ...found 30 files in SHE/raw base.py:202\n ...found 61 files in SHE base.py:202\n Deleting batch no. 1 consisting of 61 files base.py:211\n[11:28:32] An error occurred (ThrottlingException) when calling handlers.py:34\n the CreateCommit operation (reached max retries: 4): \n Rate exceeded \n Finished attempting to scrape: SHE base.py:319\n","errors":"An error occurred (ThrottlingException) when calling the CreateCommit operation (reached max retries: 4): Rate exceeded","start":"2022-04-04 11:28:20.509898","end":"2022-04-04 11:28:32.871624","duration":12}},{"council_id":"STG","missing":false,"latest_run":{"status_code":1,"log_text":"[10:39:53] Fetching Scraper for: STG handlers.py:23\n Begin attempting to scrape: STG handlers.py:27\n Deleting existing data... base.py:257\n[10:39:54] Getting all files in Councillors... base.py:209\n Getting all files in Councillors/json... base.py:209\n ...found 19 files in Councillors/json base.py:225\n Getting all files in Councillors/raw... base.py:209\n ...found 19 files in Councillors/raw base.py:225\n ...found 39 files in Councillors base.py:225\n Deleting batch no. 1 consisting of 39 files base.py:236\n[10:39:55] ...data deleted. base.py:264\n Scraping from base.py:49\n https://www.stirling.gov.uk/council-and-committees/politic \n ians-and-elections/councillors/ \n[10:39:56] Scraping from base.py:49\n https://www.stirling.gov.uk/council-and-committees/politic \n ians-and-councillors/your-councillors/elaine-watterson/ \n[10:39:57] Scraping from base.py:49\n https://www.stirling.gov.uk/council-and-committees/politic \n ians-and-councillors/your-councillors/gene-maxwell/ \n[10:39:58] Scraping from base.py:49\n https://www.stirling.gov.uk/council-and-committees/politic \n ians-and-councillors/your-councillors/martin-earl/ \n[10:39:59] Scraping from base.py:49\n https://www.stirling.gov.uk/council-and-committees/politic \n ians-and-councillors/your-councillors/gerry-mcgarvey/ \n[10:40:01] Scraping from base.py:49\n https://www.stirling.gov.uk/council-and-committees/politic \n ians-and-councillors/your-councillors/paul-henke/ \n[10:40:02] Scraping from base.py:49\n https://www.stirling.gov.uk/council-and-committees/politic \n ians-and-councillors/your-councillors/rosemary-fraser/ \n[10:40:03] Scraping from base.py:49\n https://www.stirling.gov.uk/council-and-committees/politic \n ians-and-councillors/your-councillors/alasdair-tollemache/ \n[10:40:04] Scraping from base.py:49\n https://www.stirling.gov.uk/council-and-committees/politic \n ians-and-councillors/your-councillors/david-wilson/ \n[10:40:05] Scraping from base.py:49\n https://www.stirling.gov.uk/council-and-committees/politic \n ians-and-councillors/your-councillors/robin-kleinman/ \n[10:40:06] Scraping from base.py:49\n https://www.stirling.gov.uk/council-and-committees/politic \n ians-and-councillors/your-councillors/thomas-heald/ \n[10:40:08] Scraping from base.py:49\n https://www.stirling.gov.uk/council-and-committees/politic \n ians-and-councillors/your-councillors/danny-gibson/ \n[10:40:09] Scraping from base.py:49\n https://www.stirling.gov.uk/council-and-committees/politic \n ians-and-councillors/your-councillors/jim-thomson/ \n[10:40:10] Scraping from base.py:49\n https://www.stirling.gov.uk/council-and-committees/politic \n ians-and-councillors/your-councillors/rachel-nunn/ \n[10:40:11] Scraping from base.py:49\n https://www.stirling.gov.uk/council-and-committees/politic \n ians-and-councillors/your-councillors/susan-mcgill/ \n[10:40:12] Scraping from base.py:49\n https://www.stirling.gov.uk/council-and-committees/politic \n ians-and-councillors/your-councillors/jen-preston/ \n[10:40:13] Scraping from base.py:49\n https://www.stirling.gov.uk/council-and-committees/politic \n ians-and-councillors/your-councillors/neil-benny/ \n[10:40:14] Scraping from base.py:49\n https://www.stirling.gov.uk/council-and-committees/politic \n ians-and-councillors/your-councillors/scott-farmer/ \n[10:40:15] Scraping from base.py:49\n https://www.stirling.gov.uk/council-and-committees/politic \n ians-and-councillors/your-councillors/bryan-flannagan/ \n[10:40:18] Scraping from base.py:49\n https://www.stirling.gov.uk/council-and-committees/politic \n ians-and-councillors/your-councillors/gerry-mclaughlan/ \n[10:40:19] Scraping from base.py:49\n https://www.stirling.gov.uk/council-and-committees/politic \n ians-and-councillors/your-councillors/vacant/ \n[10:40:20] 'NoneType' object is not subscriptable handlers.py:36\n Committing batch 1 consisting of 38 files base.py:297\n[10:40:21] Finished attempting to scrape: STG base.py:345\n","errors":"Traceback (most recent call last):\n File \"/var/task/lgsf/aws_lambda/handlers.py\", line 32, in scraper_worker_handler\n scraper.run(run_log)\n File \"/var/task/lgsf/councillors/scrapers.py\", line 57, in run\n councillor = self.get_single_councillor(councillor_html)\n File \"scrapers/STG-stirling/councillors.py\", line 42, in get_single_councillor\n councillor.email = soup.select_one(\"a[href^=mailto]\")[\nTypeError: 'NoneType' object is not subscriptable\n","start":"2024-10-06 10:39:53.204280","end":"2024-10-06 10:40:21.490228","duration":28}},{"council_id":"TEW","missing":false,"latest_run":{"status_code":1,"log_text":"[08:33:17] Fetching Scraper for: TEW handlers.py:23\n Begin attempting to scrape: TEW handlers.py:27\n Deleting existing data... base.py:257\n[08:33:18] 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[08:33:19] ...data deleted. base.py:264\n Scraping from base.py:49\n http://minutes.tewkesbury.gov.uk/mgWebService.asmx/GetCoun \n cillorsByWard \n[08:33:49] 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 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: 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: timed out\n","start":"2024-10-06 08:33:17.177590","end":"2024-10-06 08:33:49.424187","duration":32}},{"council_id":"THE","missing":false,"latest_run":{"status_code":1,"log_text":"[09:32:09] Fetching Scraper for: THE handlers.py:23\n Begin attempting to scrape: THE handlers.py:27\n[09:32:10] Deleting existing data... base.py:257\n Getting all files in Councillors... base.py:209\n[09:32:11] ...found 1 files in Councillors base.py:225\n Deleting batch no. 1 consisting of 1 files base.py:236\n ...data deleted. base.py:264\n Scraping from base.py:49\n https://www.threerivers.gov.uk/listing/councillors \n[09:32:13] '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":"2024-10-06 09:32:09.943058","end":"2024-10-06 09:32:13.817997","duration":3}},{"council_id":"VGL","missing":false,"latest_run":{"status_code":1,"log_text":"[10:19:39] Fetching Scraper for: VGL handlers.py:23\n Begin attempting to scrape: VGL handlers.py:27\n Deleting existing data... base.py:257\n Getting all files in Councillors... base.py:209\n[10:19:40] Getting all files in Councillors/json... base.py:209\n ...found 16 files in Councillors/json base.py:225\n Getting all files in Councillors/raw... base.py:209\n ...found 16 files in Councillors/raw base.py:225\n ...found 33 files in Councillors base.py:225\n Deleting batch no. 1 consisting of 33 files base.py:236\n[10:19:41] ...data deleted. base.py:264\n Scraping from base.py:49\n https://www.valeofglamorgan.gov.uk/en/our_council/Council- \n Structure/councillors/Councillors.aspx \n[10:19:43] Scraping from base.py:49\n https://www.valeofglamorgan.gov.uk/en/our_council/Council- \n Structure/councillors/Asbrey-Anne.aspx \n[10:19:44] Scraping from base.py:49\n https://www.valeofglamorgan.gov.uk/en/our_council/Council- \n Structure/councillors/Aviet-Julie.aspx \n[10:19:46] Scraping from base.py:49\n https://www.valeofglamorgan.gov.uk/en/our_council/Council- \n Structure/councillors/Ball-Gareth.aspx \n[10:19:47] Scraping from base.py:49\n https://www.valeofglamorgan.gov.uk/en/our_council/Council- \n Structure/councillors/Birch-Rhiannon.aspx \n[10:19:49] Scraping from base.py:49\n https://www.valeofglamorgan.gov.uk/en/our_council/Council- \n Structure/councillors/Brooks-Bronwen.aspx \n[10:19:52] Scraping from base.py:49\n https://www.valeofglamorgan.gov.uk/en/our_council/Council- \n Structure/councillors/Bruce-Gillian.aspx \n[10:19:54] Scraping from base.py:49\n https://www.valeofglamorgan.gov.uk/en/our_council/Council- \n Structure/councillors/Buckley-Ian.aspx \n[10:19:55] Scraping from base.py:49\n https://www.valeofglamorgan.gov.uk/en/our_council/Council- \n Structure/councillors/Burnett-Lis.aspx \n[10:19:57] Scraping from base.py:49\n https://www.valeofglamorgan.gov.uk/en/our_council/Council- \n Structure/councillors/Campbell-Samantha.aspx \n[10:19:58] Scraping from base.py:49\n https://www.valeofglamorgan.gov.uk/en/our_council/Council- \n Structure/councillors/Carroll-George.aspx \n[10:20:00] Scraping from base.py:49\n https://www.valeofglamorgan.gov.uk/en/our_council/Council- \n Structure/councillors/Cave-Christine.aspx \n[10:20:01] Scraping from base.py:49\n https://www.valeofglamorgan.gov.uk/en/our_council/Council- \n Structure/councillors/Champion-Charles.aspx \n[10:20:03] Scraping from base.py:49\n https://www.valeofglamorgan.gov.uk/en/our_council/Council- \n Structure/councillors/Charles-Janice.aspx \n[10:20:04] Scraping from base.py:49\n https://www.valeofglamorgan.gov.uk/en/our_council/Council- \n Structure/councillors/Collins-Amelia.aspx \n[10:20:06] Scraping from base.py:49\n https://www.valeofglamorgan.gov.uk/en/our_council/Council- \n Structure/councillors/Cowpe-Marianne.aspx \n[10:20:07] Scraping from base.py:49\n https://www.valeofglamorgan.gov.uk/en/our_council/Council- \n Structure/councillors/Drake-Pamela.aspx \n[10:20:09] Scraping from base.py:49\n https://www.valeofglamorgan.gov.uk/en/our_council/Council- \n Structure/councillors/Driscoll-Vincent.aspx \n[10:20:11] 'NoneType' object has no attribute 'get_text' handlers.py:36\n Committing batch 1 consisting of 32 files base.py:297\n[10:20:12] Finished attempting to scrape: VGL 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/VGL-the-vale-of-glamorgan/councillors.py\", line 36, in get_single_councillor\n email_text = soup.select_one(\"#S4_EmailPlaceholder\").get_text(\nAttributeError: 'NoneType' object has no attribute 'get_text'\n","start":"2024-10-06 10:19:39.057208","end":"2024-10-06 10:20:12.637541","duration":33}},{"council_id":"WLN","missing":false,"latest_run":{"status_code":1,"log_text":"[09:22:39] Fetching Scraper for: WLN handlers.py:23\n Begin attempting to scrape: WLN handlers.py:27\n Deleting existing data... base.py:257\n[09:22:40] Getting all files in Councillors... base.py:209\n Getting all files in Councillors/json... base.py:209\n ...found 25 files in Councillors/json base.py:225\n Getting all files in Councillors/raw... base.py:209\n ...found 25 files in Councillors/raw base.py:225\n ...found 51 files in Councillors base.py:225\n Deleting batch no. 1 consisting of 51 files base.py:236\n[09:22:41] ...data deleted. base.py:264\n Scraping from https://westlothian.gov.uk/councillors base.py:49\n[09:22:44] Scraping from base.py:49\n https://westlothian.gov.uk/article/33888/Linlithgow \n Scraping from base.py:49\n https://westlothian.gov.uk/article/33889/Broxburn-Uphall-a \n nd-Winchburgh \n[09:22:45] Scraping from base.py:49\n https://westlothian.gov.uk/article/33890/Livingston-North \n[09:22:46] Scraping from base.py:49\n https://westlothian.gov.uk/article/33891/Livingston-South \n[09:22:47] Scraping from base.py:49\n https://westlothian.gov.uk/article/33893/East-Livingston-a \n nd-East-Calder \n Scraping from base.py:49\n https://westlothian.gov.uk/article/33892/Fauldhouse-and-th \n e-Breich-Valley \n[09:22:48] Scraping from base.py:49\n https://westlothian.gov.uk/article/33894/Whitburn-and-Blac \n kburn \n[09:22:49] Scraping from base.py:49\n https://westlothian.gov.uk/article/33895/Bathgate \n[09:22:50] Scraping from base.py:49\n https://westlothian.gov.uk/article/33896/Armadale-and-Blac \n kridge \n Scraping from base.py:49\n https://westlothian.gov.uk/article/33897/Councillor-Tom-Co \n nn \n[09:22:51] Scraping from base.py:49\n https://westlothian.gov.uk/article/33898/Councillor-Paulin \n e-Orr \n[09:22:52] Scraping from base.py:49\n https://westlothian.gov.uk/article/33899/Councillor-Sally- \n Pattle \n[09:22:53] Scraping from base.py:49\n https://westlothian.gov.uk/article/34305/Councillor-Tony-B \n oyle \n[09:22:54] Scraping from base.py:49\n https://westlothian.gov.uk/article/34302/Councillor-Diane- \n Calder \n[09:22:55] Scraping from base.py:49\n https://westlothian.gov.uk/article/34303/Councillor-Janet- \n Campbell \n[09:22:56] Scraping from base.py:49\n https://westlothian.gov.uk/article/34304/Councillor-Angela \n -Doran-Timson \n[09:22:57] Scraping from base.py:49\n https://westlothian.gov.uk/article/34307/Councillor-Alison \n -Adamson \n Scraping from base.py:49\n https://westlothian.gov.uk/article/34306/Councillor-Robert \n -De-Bold \n[09:22:58] Scraping from base.py:49\n https://westlothian.gov.uk/article/34308/Councillor-Anne-M \n cMillan \n[09:22:59] Scraping from base.py:49\n https://westlothian.gov.uk/article/34309/Councillor-Andrew \n -Miller \n[09:23:00] Scraping from base.py:49\n https://westlothian.gov.uk/article/34311/Councillor-Lawren \n ce-Fitzpatrick \n[09:23:01] Scraping from base.py:49\n https://westlothian.gov.uk/article/34310/Councillor-Peter- \n Heggie \n[09:23:02] Scraping from base.py:49\n https://westlothian.gov.uk/article/34312/Councillor-Maria- \n MacAulay \n[09:23:03] Scraping from base.py:49\n https://westlothian.gov.uk/article/34313/Councillor-Moira- \n McKee-Shemilt \n Scraping from base.py:49\n https://westlothian.gov.uk/article/34317/Councillor-Damian \n -Doran-Timson \n[09:23:04] Scraping from base.py:49\n https://westlothian.gov.uk/article/34315/Councillor-Carl-J \n ohn \n[09:23:05] Scraping from base.py:49\n https://westlothian.gov.uk/article/34316/Councillor-Danny- \n Logue \n[09:23:06] Scraping from base.py:49\n https://westlothian.gov.uk/article/34314/Councillor-Veroni \n ca-Smith \n[09:23:07] Scraping from base.py:49\n https://westlothian.gov.uk/article/34318/Councillor-Paulin \n e-Clark \n[09:23:09] Scraping from base.py:49\n https://westlothian.gov.uk/article/34319/Councillor-Craig- \n Meek \n Scraping from base.py:49\n https://westlothian.gov.uk/article/34320/Councillor-Cathy- \n Muldoon \n[09:23:10] Scraping from base.py:49\n https://westlothian.gov.uk/article/34321/Councillor-Jim-Di \n ckson \n[09:23:11] Scraping from base.py:49\n https://westlothian.gov.uk/article/34322/Councillor-Mary-D \n ickson \n[09:23:12] Scraping from base.py:49\n https://westlothian.gov.uk/article/34323/Councillor-George \n -Paul \n[09:23:13] Scraping from base.py:49\n https://westlothian.gov.uk/article/34324/Councillor-Vacant \n list index out of range handlers.py:36\n Committing batch 1 consisting of 50 files base.py:297\n[09:23:15] Finished attempting to scrape: WLN 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/WLN-west-lothian/councillors.py\", line 37, in get_single_councillor\n councillor.email = soup.select(\"a[href^=mailto]\")[0].get_text(\nIndexError: list index out of range\n","start":"2024-10-06 09:22:39.217184","end":"2024-10-06 09:23:15.232429","duration":36}},{"council_id":"WSM","missing":false,"latest_run":{"status_code":1,"log_text":"[08:52:14] Fetching Scraper for: WSM handlers.py:23\n Begin attempting to scrape: WSM handlers.py:27\n Deleting existing data... base.py:257\n[08:52:15] Getting all files in Councillors... base.py:209\n Getting all files in Councillors/json... base.py:209\n ...found 54 files in Councillors/json base.py:225\n Getting all files in Councillors/raw... base.py:209\n ...found 54 files in Councillors/raw base.py:225\n ...found 109 files in Councillors base.py:225\n Deleting batch no. 1 consisting of 100 files base.py:236\n[08:52:16] Deleting batch no. 2 consisting of 9 files base.py:236\n[08:52:17] ...data deleted. base.py:264\n Scraping from base.py:49\n http://committees.westminster.gov.uk/mgWebService.asmx/Get \n CouncillorsByWard \n[08:52:47] timed out handlers.py:36\n Finished attempting to scrape: WSM 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: 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: timed out\n","start":"2024-10-06 08:52:14.526390","end":"2024-10-06 08:52:47.863038","duration":33}}] diff --git a/index.html b/index.html index 0cef8943c0..283d0b753f 100644 --- a/index.html +++ b/index.html @@ -49,10 +49,6 @@
[08:47:34] Fetching Scraper for: ABC handlers.py:23 + Begin attempting to scrape: ABC handlers.py:27 + Deleting existing data... base.py:257 +[08:47:35] Getting all files in Councillors... base.py:209 + Getting all files in Councillors/json... base.py:209 + ...found 16 files in Councillors/json base.py:225 + Getting all files in Councillors/raw... base.py:209 + ...found 16 files in Councillors/raw base.py:225 + ...found 33 files in Councillors base.py:225 + Deleting batch no. 1 consisting of 33 files base.py:236 +[08:47:36] ...data deleted. base.py:264 + Scraping from base.py:49 + https://www.armaghbanbridgecraigavon.gov.uk/councillors/ +[08:47:39] Committing batch 1 consisting of 32 files base.py:297 +[08:47:40] Finished attempting to scrape: ABC base.py:345 ++ + + + +
[09:47:31] Fetching Scraper for: ABC handlers.py:23 - Begin attempting to scrape: ABC handlers.py:27 -[09:47:32] Deleting existing data... base.py:257 - Getting all files in Councillors... base.py:209 - Getting all files in Councillors/json... base.py:209 - ...found 16 files in Councillors/json base.py:225 - Getting all files in Councillors/raw... base.py:209 -[09:47:33] ...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/ -[09:47:38] Committing batch 1 consisting of 32 files base.py:297 -[09:47:40] Finished attempting to scrape: ABC base.py:345 -- -