finished scrapping all the data

This commit is contained in:
2023-04-12 22:05:16 +03:00
parent df548fa29d
commit 218a3d8135
10 changed files with 90845 additions and 22884 deletions

3
.gitignore vendored
View File

@@ -1 +1,2 @@
venv/* venv/*
logs/*

View File

@@ -0,0 +1,130 @@
{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Imported modules"
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
"import json\n",
"import scrapping\n",
"import psycopg2\n",
"from psycopg2.extras import execute_batch\n",
"import re\n",
"import logging\n",
"import datetime\n",
"import multiprocessing\n",
"import os\n",
"logging.basicConfig(\n",
" level=logging.INFO, filename=f'{datetime.datetime.now().strftime(\"%Y-%m-%d_%H-%M-%S\")}.log', filemode='w',\n",
" format='%(name)s - %(levelname)s - %(message)s', datefmt='%d-%b-%y %H:%M:%S')\n",
"# from psycopg2.extensions import register_adapter\n"
]
},
{
"cell_type": "code",
"execution_count": 29,
"metadata": {},
"outputs": [],
"source": [
"conn = psycopg2.connect(\"dbname='dh' user='dh' host='dh.saret.tk' password='qwerty'\")\n",
"connection = conn.cursor()\n",
"with open('project_list') as f:\n",
" for project in f.read().split('\\n'):\n",
" # connection = connection.execute(\"insert into raw_texts values (%(id_text)s, %(project_name)s, %(raw_text)s)\", scrap)\n",
" try:\n",
" scrap = scrapping.get_raw_english_texts_of_project(project)\n",
" except Exception:\n",
" logging.error(f\"Error in {project}:{Exception}\")\n",
" try:\n",
" execute_batch(\n",
" connection,\n",
" \"insert into raw_texts values (%(id_text)s, %(project_name)s, %(raw_text)s) ON CONFLICT DO NOTHING\",\n",
" scrap)\n",
" conn.commit()\n",
" except Exception:\n",
" with open(project, 'w') as f:\n",
" f.write(json.dumps(scrap))\n",
" logging.error(f\"Error in {project}:{Exception}\")"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [],
"source": [
"conn = psycopg2.connect(\"dbname='dh' user='dh' host='dh.saret.tk' password='qwerty'\")\n",
"connection = conn.cursor()\n",
"logging.basicConfig(\n",
" level=logging.INFO, filename=f'./now.log',\n",
" format='%(name)s - %(levelname)s - %(message)s')\n",
"logging.info('Start')\n",
"with open('project_list', encoding='unicode-escape') as f:\n",
" # project = f.read().split('\\n')[2]\n",
" for project in f.read().split('\\n'):\n",
" # connection = connection.execute(\"insert into raw_texts values (%(id_text)s, %(project_name)s, %(raw_text)s)\", scrap)\n",
" if os.path.exists(project):\n",
" with open(project) as f:\n",
" logging.info(f'reading {project}')\n",
" scrap = json.loads(f.read())\n",
" # scrap = json.loads(project)\n",
" execute_batch(\n",
" connection, \"insert into raw_texts values (%(id_text)s, %(project_name)s, %(raw_text)s) ON CONFLICT DO NOTHING\",\n",
" scrap)\n",
" conn.commit()\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# with open('cams') as file:\n",
"conn = psycopg2.connect(\"dbname='dh' user='dh' host='dh.saret.tk' password='qwerty'\")\n",
"connection = conn.cursor()\n",
"scrap = scrapping.get_raw_english_texts_of_project('saao')\n",
"execute_batch(\n",
" connection, \"insert into raw_texts values (%(id_text)s, %(project_name)s, %(raw_text)s) ON CONFLICT DO NOTHING\",\n",
" scrap)\n",
"conn.commit()\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.9.13"
}
},
"nbformat": 4,
"nbformat_minor": 2
}

View File

@@ -1,5 +0,0 @@
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

File diff suppressed because it is too large Load Diff

View File

@@ -1,447 +0,0 @@
root - INFO - Start
root - INFO - Start
root - INFO - reading adsd
root - INFO - reading aemw
root - INFO - reading akklove
root - INFO - reading asbp
root - INFO - reading atae
root - INFO - reading babcity
root - INFO - reading blms
root - INFO - reading btmao
root - INFO - reading btto
root - INFO - reading cams
root - INFO - reading ccpo
root - INFO - reading cdli
root - INFO - reading ckst
root - INFO - reading cmawro
root - INFO - reading contrib
root - INFO - reading dcclt
root - INFO - reading dccmt
root - INFO - reading doc
root - INFO - reading dsst
root - INFO - reading ecut
root - INFO - reading eisl
root - INFO - reading epsd2
root - INFO - reading etcsri
root - INFO - reading glass
root - INFO - reading hbtin
root - INFO - reading lacost
root - INFO - reading lovelyrics
root - INFO - reading neo
root - INFO - reading nere
root - INFO - reading nimrud
root - INFO - reading obel
root - INFO - reading obmc
root - INFO - reading obta
root - INFO - reading ogsl
root - INFO - reading oimea
root - INFO - reading pnao
root - INFO - reading qcat
root - INFO - reading riao
root - INFO - reading ribo
root - INFO - reading rimanum
root - INFO - reading rinap
root - INFO - reading saao
root - INFO - reading suhu
root - INFO - reading tcma
root - INFO - reading tsae
root - INFO - reading xcat
sroot - INFO - http://oracc.museum.upenn.edu/saao/saa01/P224395/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P224403/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P224417/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P224431/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P224433/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P224447/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P224485/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P224487/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P224587/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P313416/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P313417/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P313425/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P313427/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P313435/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P313437/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P313439/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P313447/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P313458/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P313487/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P313491/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P313497/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P313502/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P313505/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P313509/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P313511/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P313523/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P313527/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P313543/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P313551/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P313559/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P313571/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P313598/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P313600/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P313614/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P313623/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P313626/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P313627/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P313629/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P313644/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P313648/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P313660/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P313677/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P313684/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P313699/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P313719/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P313722/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P313726/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P313742/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P313748/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P313755/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P313759/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P313762/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P313807/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P313815/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P313832/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P313854/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P313864/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P313871/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P313874/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P313876/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P313878/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P313879/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P313885/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P313897/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P313904/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P313907/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P313915/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P313919/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P313923/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P313938/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P313947/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P313974/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P313975/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P314001/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P314003/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P314022/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P314026/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P314030/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P314032/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P314048/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P314051/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P314054/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P314056/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P314134/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P314144/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P314157/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P314211/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P314223/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P314227/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P314232/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P314238/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P314243/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P314248/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P314257/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P314260/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P314272/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P314273/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P314275/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P314282/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P314287/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P314297/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P314316/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334036/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334037/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334038/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334039/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334040/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334041/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334042/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334043/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334044/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334045/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334046/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334047/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334048/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334049/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334050/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334051/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334053/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334054/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334055/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334056/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334078/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334079/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334080/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334081/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334082/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334083/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334100/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334101/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334102/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334113/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334118/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334120/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334124/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334125/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334127/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334135/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334136/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334141/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334142/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334143/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334144/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334158/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334160/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334165/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334166/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334170/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334171/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334172/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334173/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334174/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334175/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334176/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334190/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334193/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334194/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334195/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334209/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334210/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334211/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334212/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334213/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334214/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334271/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334272/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334273/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334284/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334288/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334298/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334314/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334317/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334328/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334329/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334330/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334331/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334332/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334333/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334334/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334335/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334336/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334359/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334372/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334384/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334385/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334390/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334394/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334396/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334397/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334403/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334422/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334432/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334435/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334442/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334443/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334444/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334445/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334496/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334499/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334512/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334519/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334520/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334567/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334568/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334586/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334587/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334588/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334592/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334598/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334610/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334621/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334631/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334632/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334634/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334643/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334644/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334658/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334665/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334667/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334676/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334687/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334689/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334693/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334699/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334709/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334715/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334718/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334721/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334727/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334728/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334729/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334739/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334773/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334774/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334776/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334789/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334791/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334792/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334794/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334804/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334807/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334810/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334820/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334826/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334830/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334834/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334849/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334864/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334895/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334903/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334904/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334910/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334912/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334918/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334922/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P334923/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P336167/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P336172/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P336595/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P336596/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P336597/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P393855/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P393866/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/P428858/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa01/X010028/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa02/P237185/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa02/P240211/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa02/P296062/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa02/P314346/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa02/P334814/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa02/P336039/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa02/P336040/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa02/P336126/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa02/P336216/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa02/P336217/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa02/P336218/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa02/P336220/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa02/P336317/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa02/P500551/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa02/Q009186/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa03/P223388/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa03/P237351/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa03/P238051/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa03/P238321/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa03/P238357/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa03/P313430/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa03/P313818/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa03/P334919/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa03/P334925/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa03/P334926/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa03/P334929/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa03/P334930/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa03/P334931/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa03/P334932/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa03/P336128/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa03/P336130/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa03/P336144/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa03/P336149/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa03/P336150/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa03/P336151/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa03/P336158/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa03/P336161/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa03/P336175/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa03/P336225/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa03/P336226/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa03/P336234/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa03/P336242/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa03/P336243/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa03/P336244/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa03/P336245/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa03/P336291/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa03/P336306/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa03/P336599/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa03/P336600/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa03/P336601/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa03/P336602/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa03/P336603/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa03/P336604/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa03/P336605/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa03/P336606/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa03/P336607/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa03/P336608/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa03/P336609/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa03/P336796/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa03/P337164/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa03/P338360/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa03/P338383/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa03/P338404/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa03/P338675/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa03/P338681/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa03/Q009249/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa03/Q009250/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa04/P236925/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa04/P236926/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa04/P236927/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa04/P236928/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa04/P236929/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa04/P236937/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa04/P236943/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa04/P236955/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa04/P236956/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa04/P236960/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa04/P237009/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa04/P237018/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa04/P237027/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa04/P237030/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa04/P237053/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa04/P237081/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa04/P237119/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa04/P237127/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa04/P237128/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa04/P237168/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa04/P237173/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa04/P237190/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa04/P237191/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa04/P237203/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa04/P237208/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa04/P237209/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa04/P237210/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa04/P237212/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa04/P237213/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa04/P237222/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa04/P237224/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa04/P237231/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa04/P237355/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa04/P237358/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa04/P237360/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa04/P237361/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa04/P237362/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa04/P237363/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa04/P237364/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa04/P237365/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa04/P237366/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa04/P237367/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa04/P237369/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa04/P237370/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa04/P237371/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa04/P237372/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa04/P237373/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa04/P237374/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa04/P237376/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa04/P237377/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa04/P237378/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa04/P237380/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa04/P237383/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa04/P237386/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa04/P237387/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa04/P237405/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa04/P237410/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa04/P237412/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa04/P237413/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa04/P237416/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa04/P237417/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa04/P237423/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa04/P237435/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa04/P237443/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa04/P237449/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa04/P237461/html
root - INFO - http://oracc.museum.upenn.edu/saao/saa04/P237479/html

2300
2023-04-12_22-00-38.log Normal file

File diff suppressed because it is too large Load Diff

2300
missing_list.txt Normal file

File diff suppressed because it is too large Load Diff

View File

@@ -51,4 +51,4 @@ saao
suhu suhu
tcma tcma
tsae tsae
xcat xcat

File diff suppressed because it is too large Load Diff

View File

@@ -1,7 +1,7 @@
import json import json
from typing import Dict, List from typing import Dict, List
import requests import requests
from bs4 import BeautifulSoup from bs4 import BeautifulSoup, ResultSet
import os import os
from pathlib import Path from pathlib import Path
import re import re
@@ -31,6 +31,18 @@ def _load_json_from_path(json_path: str) -> Dict:
if os.stat(json_path).st_size != 0: # If the file is not empty: if os.stat(json_path).st_size != 0: # If the file is not empty:
return json.load(json_file) return json.load(json_file)
def _download_data_from_website(url: str) -> ResultSet:
try:
res = requests.get(url)
soup = BeautifulSoup(res.text, "html.parser")
return soup.find_all("span", {"class": "cell"})
except Exception as e:
logging.error(e)
return ResultSet()
def _clean_raw_text(results: ResultSet)->str:
return " ".join(["".join([content if isinstance(content, str) else content.text
for content in result.contents]) for result in results]).replace('\n', ' ')
def get_raw_english_texts_of_project(project_dirname: str, oracc_site: str = 'oracc.museum.upenn.edu') -> List[Dict]: def get_raw_english_texts_of_project(project_dirname: str, oracc_site: str = 'oracc.museum.upenn.edu') -> List[Dict]:
raw_jsons = list() raw_jsons = list()
@@ -44,8 +56,11 @@ def get_raw_english_texts_of_project(project_dirname: str, oracc_site: str = 'or
# for member in d.get('members').values(): # for member in d.get('members').values():
for filename in all_paths: for filename in all_paths:
cur_json = _load_json_from_path(filename) cur_json = _load_json_from_path(filename)
project_name = cur_json['project'] try:
project_name = cur_json['project']
except TypeError:
logging.error(f"Error in {filename}")
continue
# # Skip in case we are in saa project and the current sub project is not in neo-assyrian # # Skip in case we are in saa project and the current sub project is not in neo-assyrian
# if project_dirname == "saao" and project_name[-2:] not in SUB_PROJECTS_IN_NEO_ASS: # TODO: validate # if project_dirname == "saao" and project_name[-2:] not in SUB_PROJECTS_IN_NEO_ASS: # TODO: validate
# continue # continue
@@ -56,12 +71,7 @@ def get_raw_english_texts_of_project(project_dirname: str, oracc_site: str = 'or
# print(url) # print(url)
logging.info(url) logging.info(url)
try: try:
res = requests.get(url) raw_text = _clean_raw_text(_download_data_from_website(url))
soup = BeautifulSoup(res.text, "html.parser")
results = soup.find_all("span", {"class": "cell"})
raw_text = " ".join(["".join([content if isinstance(content, str) else content.text
for content in result.contents]) for result in results])
raw_text = raw_text.replace('\n', ' ')
if raw_text: if raw_text:
raw_jsons.append({ raw_jsons.append({
"id_text": cur_json['textid'], "id_text": cur_json['textid'],