foundit
/
compete_jobs
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

ky

prahul11 2023-10-17 17:16:23 +05:30
parent b45dde14ee
commit d37e1fdd46
1 changed files with 21 additions and 22 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

43
common_task.py
View File

@ -11,11 +11,11 @@ import time
import os
import sys
def upload_file_to_bucket(localFilePath, localFileName):
def upload_file_to_bucket(localFilePath, localFileName, today_date):
s3 = boto3.client('s3')
bucket_name = 'compete-syndication'
file_path = localFilePath
s3_key = f'naukri/{localFileName}'
s3_key = f'naukri/{today_date}/{localFileName}'
s3.upload_file(file_path, bucket_name, s3_key)
print(f'File "{file_path}" uploaded to S3 bucket "{bucket_name}" as "{s3_key}"')
@ -75,9 +75,9 @@ def find_second_latest_file(folder_path, search_pattern):
print("There are not enough files in the folder to find the second latest file.")
return None
def run_india_scraper():
current_date = datetime.now()
today_date = current_date.strftime('%d-%m-%Y')
def run_india_scraper(today_date):
# current_date = datetime.now()
# today_date = current_date.strftime('%d-%m-%Y')
india_search_input_file = "naukri/_industry_urls.csv"
india_search_output_file = f"india_data/daily_search_results/search_result_india_{today_date}.csv"
india_search_error_file = f"india_data/daily_error_folder/search_error_india_{today_date}.csv"
@ -110,16 +110,16 @@ def run_india_scraper():
stat.write(f"Jobdata program took {duration_hours:.2f} hours to run.\n")
current_date = datetime.now()
today_date = current_date.strftime('%d-%m-%Y')
upload_file_to_bucket(expired_output, f"Compete_1_India_Archieve_{today_date}.csv" )
upload_file_to_bucket(india_detail_file, f"Compete_1_India_Active_{today_date}.csv" )
upload_file_to_bucket(expired_output, f"Compete_1_India_Archieve_{today_date}.csv" , today_date)
upload_file_to_bucket(india_detail_file, f"Compete_1_India_Active_{today_date}.csv" , today_date)
def run_gulf_scraper():
def run_gulf_scraper(today_date):
gulfSearch()
folder_path = "gulf_data/daily_search_results/"
search_pattern = "search_result_gulf_*.csv"
last_file = find_second_latest_file(folder_path, search_pattern)
current_date = datetime.now()
today_date = current_date.strftime('%d-%m-%Y')
# current_date = datetime.now()
# today_date = current_date.strftime('%d-%m-%Y')
fresh_output = f"gulf_data/daily_process_folder/new_jobs_on_{today_date}.csv"
expired_output = f"gulf_data/daily_upload_folder/Compete_1_Gulf_Archieve_{today_date}.csv"
common_output = f"gulf_data/daily_common_folder/common_data_on_{today_date}.csv"
@ -139,16 +139,15 @@ def run_gulf_scraper():
if __name__ == "__main__":
# print("Choose which function to run:")
# print("1 for India Scraper")
# print("2 for Gulf scraper")
# choice = input("Enter your choice (1 or 2): ")
# if choice == "1":
# run_india_scraper()
# elif choice == "2":
# run_gulf_scraper()
# else:
# print("Invalid choice. Please enter 1 or 2.")
aws_access_key_id = 'AKIAWWHGITBE7XFXWA7U'
aws_secret_access_key = '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'
current_date = datetime.now()
today_date = current_date.strftime('%d-%m-%Y')
bucket_name = 'compete-syndication'
folder_name = f'naukri/{today_date}' # Replace with your desired folder name
s3 = boto3.client('s3', aws_access_key_id=aws_access_key_id, aws_secret_access_key=aws_secret_access_key)
folder_key = folder_name + '/' # Note the trailing slash
s3.put_object(Bucket=bucket_name, Key=folder_key)
if len(sys.argv) != 2:
print("Usage: python common_task.py [gulf|india]")
@ -157,9 +156,9 @@ if __name__ == "__main__":
option = sys.argv[1].lower()
if option == 'gulf':
run_gulf_scraper()
run_gulf_scraper(today_date)
elif option == 'india':
run_india_scraper()
run_india_scraper(today_date)
else:
print("Invalid argument. Please use 'gulf' or 'india' as the argument.")