failing in saao

This commit is contained in:
2023-04-12 12:29:22 +03:00
parent faab62e768
commit f592236971
2 changed files with 413 additions and 1 deletions

View File

@@ -86,7 +86,20 @@
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [],
"outputs": [
{
"ename": "TypeError",
"evalue": "'NoneType' object is not subscriptable",
"output_type": "error",
"traceback": [
"\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[1;31mTypeError\u001b[0m Traceback (most recent call last)",
"Cell \u001b[1;32mIn[4], line 4\u001b[0m\n\u001b[0;32m 2\u001b[0m conn \u001b[39m=\u001b[39m psycopg2\u001b[39m.\u001b[39mconnect(\u001b[39m\"\u001b[39m\u001b[39mdbname=\u001b[39m\u001b[39m'\u001b[39m\u001b[39mdh\u001b[39m\u001b[39m'\u001b[39m\u001b[39m user=\u001b[39m\u001b[39m'\u001b[39m\u001b[39mdh\u001b[39m\u001b[39m'\u001b[39m\u001b[39m host=\u001b[39m\u001b[39m'\u001b[39m\u001b[39mdh.saret.tk\u001b[39m\u001b[39m'\u001b[39m\u001b[39m password=\u001b[39m\u001b[39m'\u001b[39m\u001b[39mqwerty\u001b[39m\u001b[39m'\u001b[39m\u001b[39m\"\u001b[39m)\n\u001b[0;32m 3\u001b[0m connection \u001b[39m=\u001b[39m conn\u001b[39m.\u001b[39mcursor()\n\u001b[1;32m----> 4\u001b[0m scrap \u001b[39m=\u001b[39m scrapping\u001b[39m.\u001b[39;49mget_raw_english_texts_of_project(\u001b[39m'\u001b[39;49m\u001b[39msaao\u001b[39;49m\u001b[39m'\u001b[39;49m)\n\u001b[0;32m 5\u001b[0m execute_batch(\n\u001b[0;32m 6\u001b[0m connection, \u001b[39m\"\u001b[39m\u001b[39minsert into raw_texts values (\u001b[39m\u001b[39m%(id_text)s\u001b[39;00m\u001b[39m, \u001b[39m\u001b[39m%(project_name)s\u001b[39;00m\u001b[39m, \u001b[39m\u001b[39m%(raw_text)s\u001b[39;00m\u001b[39m) ON CONFLICT DO NOTHING\u001b[39m\u001b[39m\"\u001b[39m,\n\u001b[0;32m 7\u001b[0m scrap)\n\u001b[0;32m 8\u001b[0m conn\u001b[39m.\u001b[39mcommit()\n",
"File \u001b[1;32mc:\\Users\\Saret\\Programming\\C#\\DH\\scrapping.py:46\u001b[0m, in \u001b[0;36mget_raw_english_texts_of_project\u001b[1;34m(project_dirname, oracc_site)\u001b[0m\n\u001b[0;32m 44\u001b[0m \u001b[39mfor\u001b[39;00m filename \u001b[39min\u001b[39;00m all_paths:\n\u001b[0;32m 45\u001b[0m cur_json \u001b[39m=\u001b[39m _load_json_from_path(filename)\n\u001b[1;32m---> 46\u001b[0m project_name \u001b[39m=\u001b[39m cur_json[\u001b[39m'\u001b[39;49m\u001b[39mproject\u001b[39;49m\u001b[39m'\u001b[39;49m]\n\u001b[0;32m 48\u001b[0m \u001b[39m# # Skip in case we are in saa project and the current sub project is not in neo-assyrian\u001b[39;00m\n\u001b[0;32m 49\u001b[0m \u001b[39m# if project_dirname == \"saao\" and project_name[-2:] not in SUB_PROJECTS_IN_NEO_ASS: # TODO: validate\u001b[39;00m\n\u001b[0;32m 50\u001b[0m \u001b[39m# continue\u001b[39;00m\n\u001b[0;32m 51\u001b[0m \n\u001b[0;32m 52\u001b[0m \u001b[39m# id_text = member.get('id_text', \"\") + member.get('id_composite', \"\")\u001b[39;00m\n\u001b[0;32m 53\u001b[0m \u001b[39m# html_dir = \"/\".join(path.parts[1:-1])\u001b[39;00m\n\u001b[0;32m 54\u001b[0m url \u001b[39m=\u001b[39m \u001b[39mf\u001b[39m\u001b[39m\"\u001b[39m\u001b[39mhttp://\u001b[39m\u001b[39m{\u001b[39;00moracc_site\u001b[39m}\u001b[39;00m\u001b[39m/\u001b[39m\u001b[39m{\u001b[39;00mproject_name\u001b[39m}\u001b[39;00m\u001b[39m/\u001b[39m\u001b[39m{\u001b[39;00mcur_json[\u001b[39m'\u001b[39m\u001b[39mtextid\u001b[39m\u001b[39m'\u001b[39m]\u001b[39m}\u001b[39;00m\u001b[39m/html\u001b[39m\u001b[39m\"\u001b[39m\n",
"\u001b[1;31mTypeError\u001b[0m: 'NoneType' object is not subscriptable"
]
}
],
"source": [
"# with open('cams') as file:\n",
"conn = psycopg2.connect(\"dbname='dh' user='dh' host='dh.saret.tk' password='qwerty'\")\n",