2024-09-27 14:24:18 +02:00
from datetime import datetime
2024-09-27 17:11:21 +02:00
import json
import os
2024-09-27 14:24:18 +02:00
2024-09-27 14:53:16 +02:00
from src . scrub import scrub_web
2024-09-30 12:24:26 +02:00
from src . key3 import create_queries
2024-09-27 18:18:21 +02:00
from src . evaluate import sort_results , CLS_POOLING , MEAN_POOLING , MAX_POOLING
2024-09-27 14:24:18 +02:00
2024-09-27 18:18:21 +02:00
def hin_fetch ( subject , weights , pooling ) :
2024-09-27 17:11:21 +02:00
current_time = datetime . now ( ) . strftime ( " % m- %d _ % H- % M " )
data_path = f " web_data/ { hash ( subject ) } .json "
2024-09-27 21:38:44 +02:00
file_path = f " logs/run_ { current_time } _ { weights } { pooling } .md "
2024-09-27 17:11:21 +02:00
log_content = f " # Hin run, { current_time } \n \n Subject : { subject } \n \n "
2024-09-27 14:24:18 +02:00
2024-09-27 17:11:21 +02:00
results = [ ]
if os . path . exists ( data_path ) :
log_content + = f " ## Query results from { data_path } * \n \n "
print ( f " * Subject known from { data_path } " )
with open ( data_path , ' r ' , encoding = ' utf-8 ' ) as f :
results = json . load ( f )
else :
queries , keyword_log = create_queries ( subject )
log_content + = keyword_log
2024-09-27 14:24:18 +02:00
2024-09-27 17:11:21 +02:00
results , scrub_log = scrub_web ( queries )
log_content + = scrub_log
2024-09-27 14:24:18 +02:00
2024-09-27 17:11:21 +02:00
with open ( data_path , ' w ' , encoding = ' utf-8 ' ) as f :
json . dump ( results , f , ensure_ascii = False , indent = 4 )
log_content + = f " *Stored results in { data_path } * \n \n "
print ( f " \n * Stored results in { data_path } " )
2024-09-27 18:18:21 +02:00
sorted_results , results_log = sort_results ( subject , results , weights , pooling )
2024-09-27 17:11:21 +02:00
log_content + = results_log
print ( " ### Done ### \n " )
report = " ## Results \n "
# Print the top 10 results
for idx , result in enumerate ( sorted_results [ : 10 ] , 1 ) :
report + = f " \n Rank { idx } ( { result [ ' score ' ] : .4f } ): \n Title: { result [ ' title ' ] } \n URL: { result [ ' url ' ] } \n Snippet: { result [ ' snippet ' ] } \n " + " - " * 40
print ( report + " \n " )
# Create and save the file
with open ( file_path , ' w ' ) as file :
file . write ( log_content + report )
#subject = input("Enter subject : ")
2024-09-30 12:24:26 +02:00
#subject = "State of the art on the identification of wood structure natural frequencies. Influence of the mechanical properties and interest in sensitivity analysis as prospects for reverse identification method of wood elastic properties."
2024-09-27 21:38:44 +02:00
#subject = "Experiments, numerical models and optimization of carbon-epoxy plates damped by a frequency-dependent interleaved viscoelastic layer"
2024-09-30 12:24:26 +02:00
#subject = "Dynamic response of carbon-epoxy laminates including a perforated viscoelastic film"
subject = " tig welding of inconel 625 and influences on micro structures "
#subject = "Thermo-Mechanical Impact of temperature oscillations on bonding and metallization for SiC MOSFETs soldered on ceramic substrate"
2024-09-27 17:11:21 +02:00
2024-09-27 18:18:21 +02:00
# hin_fetch(subject, [title_weight, snippet_weight], [title_pooling, snippet_pooling])
2024-09-30 12:24:26 +02:00
hin_fetch ( subject , [ 2 , 1 ] , [ CLS_POOLING , MAX_POOLING ] )
#hin_fetch(subject, [1,0], [MEAN_POOLING,MAX_POOLING])
#hin_fetch(subject, [1,0], [MAX_POOLING, MAX_POOLING])
#hin_fetch(subject, [0,1], [CLS_POOLING, CLS_POOLING])
#hin_fetch(subject, [0,1], [CLS_POOLING, MEAN_POOLING])
#hin_fetch(subject, [0,1], [CLS_POOLING, MAX_POOLING])