t1
This commit is contained in:
5
2023-04-12_01-39-28.log
Normal file
5
2023-04-12_01-39-28.log
Normal file
@@ -0,0 +1,5 @@
|
||||
root - INFO - http://oracc.iaas.upenn.edu/ario/Q006653/html
|
||||
root - INFO - http://oracc.iaas.upenn.edu/ario/Q006654/html
|
||||
root - INFO - http://oracc.iaas.upenn.edu/ario/Q006655/html
|
||||
root - INFO - http://oracc.iaas.upenn.edu/ario/Q007129/html
|
||||
root - INFO - http://oracc.iaas.upenn.edu/ario/Q007130/html
|
Binary file not shown.
@@ -10,7 +10,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 30,
|
||||
"execution_count": 1,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
@@ -29,7 +29,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 17,
|
||||
"execution_count": 2,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
@@ -39,8 +39,8 @@
|
||||
"traceback": [
|
||||
"\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
|
||||
"\u001b[1;31mTypeError\u001b[0m Traceback (most recent call last)",
|
||||
"Cell \u001b[1;32mIn[17], line 5\u001b[0m\n\u001b[0;32m 3\u001b[0m \u001b[39mwith\u001b[39;00m \u001b[39mopen\u001b[39m(\u001b[39m'\u001b[39m\u001b[39mproject_list\u001b[39m\u001b[39m'\u001b[39m) \u001b[39mas\u001b[39;00m f:\n\u001b[0;32m 4\u001b[0m \u001b[39mfor\u001b[39;00m project \u001b[39min\u001b[39;00m f\u001b[39m.\u001b[39mread()\u001b[39m.\u001b[39msplit(\u001b[39m'\u001b[39m\u001b[39m\\n\u001b[39;00m\u001b[39m'\u001b[39m):\n\u001b[1;32m----> 5\u001b[0m scrap \u001b[39m=\u001b[39m scrapping\u001b[39m.\u001b[39;49mget_raw_english_texts_of_project(project)\n\u001b[0;32m 6\u001b[0m \u001b[39m# connection = connection.execute(\"insert into raw_texts values (%(id_text)s, %(project_name)s, %(raw_text)s)\", scrap)\u001b[39;00m\n\u001b[0;32m 7\u001b[0m \u001b[39mtry\u001b[39;00m:\n",
|
||||
"File \u001b[1;32mc:\\Users\\Saret\\Programming\\C#\\DH\\scrapping.py:43\u001b[0m, in \u001b[0;36mget_raw_english_texts_of_project\u001b[1;34m(project_dirname)\u001b[0m\n\u001b[0;32m 41\u001b[0m \u001b[39mfor\u001b[39;00m filename \u001b[39min\u001b[39;00m all_paths:\n\u001b[0;32m 42\u001b[0m cur_json \u001b[39m=\u001b[39m _load_json_from_path(filename)\n\u001b[1;32m---> 43\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 45\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 46\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 47\u001b[0m \u001b[39m# continue\u001b[39;00m\n\u001b[0;32m 48\u001b[0m \n\u001b[0;32m 49\u001b[0m \u001b[39m# id_text = member.get('id_text', \"\") + member.get('id_composite', \"\")\u001b[39;00m\n\u001b[0;32m 50\u001b[0m \u001b[39m# html_dir = \"/\".join(path.parts[1:-1])\u001b[39;00m\n\u001b[0;32m 51\u001b[0m url \u001b[39m=\u001b[39m \u001b[39mf\u001b[39m\u001b[39m\"\u001b[39m\u001b[39mhttp://oracc.iaas.upenn.edu/\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",
|
||||
"Cell \u001b[1;32mIn[2], line 6\u001b[0m\n\u001b[0;32m 3\u001b[0m \u001b[39mwith\u001b[39;00m \u001b[39mopen\u001b[39m(\u001b[39m'\u001b[39m\u001b[39mproject_list\u001b[39m\u001b[39m'\u001b[39m) \u001b[39mas\u001b[39;00m f:\n\u001b[0;32m 4\u001b[0m \u001b[39mfor\u001b[39;00m project \u001b[39min\u001b[39;00m f\u001b[39m.\u001b[39mread()\u001b[39m.\u001b[39msplit(\u001b[39m'\u001b[39m\u001b[39m\\n\u001b[39;00m\u001b[39m'\u001b[39m):\n\u001b[0;32m 5\u001b[0m \u001b[39m# connection = connection.execute(\"insert into raw_texts values (%(id_text)s, %(project_name)s, %(raw_text)s)\", scrap)\u001b[39;00m\n\u001b[1;32m----> 6\u001b[0m scrap \u001b[39m=\u001b[39m scrapping\u001b[39m.\u001b[39;49mget_raw_english_texts_of_project(project)\n\u001b[0;32m 7\u001b[0m \u001b[39mtry\u001b[39;00m:\n\u001b[0;32m 8\u001b[0m execute_batch(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)\u001b[39m\u001b[39m\"\u001b[39m, scrap)\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)\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://oracc.iaas.upenn.edu/\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"
|
||||
]
|
||||
}
|
||||
@@ -50,8 +50,8 @@
|
||||
"connection = conn.cursor()\n",
|
||||
"with open('project_list') as f:\n",
|
||||
" for project in f.read().split('\\n'):\n",
|
||||
" scrap = scrapping.get_raw_english_texts_of_project(project)\n",
|
||||
" # connection = connection.execute(\"insert into raw_texts values (%(id_text)s, %(project_name)s, %(raw_text)s)\", scrap)\n",
|
||||
" scrap = scrapping.get_raw_english_texts_of_project(project)\n",
|
||||
" try:\n",
|
||||
" execute_batch(connection, \"insert into raw_texts values (%(id_text)s, %(project_name)s, %(raw_text)s)\", scrap)\n",
|
||||
" conn.commit()\n",
|
||||
|
@@ -7490,3 +7490,8 @@ INFO:root:Start
|
||||
CRITICAL:root:fuck
|
||||
INFO:root:Start
|
||||
INFO:root:Start
|
||||
INFO:root:http://oracc.iaas.upenn.edu/ario/Q006653/html
|
||||
INFO:root:http://oracc.iaas.upenn.edu/ario/Q006654/html
|
||||
INFO:root:http://oracc.iaas.upenn.edu/ario/Q006655/html
|
||||
INFO:root:http://oracc.iaas.upenn.edu/ario/Q007129/html
|
||||
INFO:root:http://oracc.iaas.upenn.edu/ario/Q007130/html
|
||||
|
Reference in New Issue
Block a user