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

Compare commits

base: foundit:ea660b5d9b3fdd8a9f498c9f0205da5677f08f61
Branches Tags
foundit:main
..
compare: foundit:070a07b66cdce292ac228440d74c81e4b0549e40
Branches Tags
foundit:main

2 Commits
ea660b5d9b ... 070a07b66c

Author SHA1 Message Date
prahul11 070a07b66c h 2023-10-14 11:09:35 +05:30
prahul11 8b694d4fdf s 2023-10-13 21:39:56 +05:30
1 changed files with 17 additions and 17 deletions
Show Stats Expand all files Collapse all files

34
common_task.py
View File

@ -79,7 +79,7 @@ def run_india_scraper():
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"
india_search_stats_file = f"india_data/stats_india_{today_date}.txt"
# india_search_stats_file = f"india_data/daily_stats_folder/stats_india_search_{today_date}.txt"
# start_time = time.time()
# scraper = NaukriJobScraper(india_search_input_file, india_search_output_file, india_search_error_file)
# scraper.scrape()
@ -88,24 +88,24 @@ def run_india_scraper():
# print(f"Search program took {duration_hours:.2f} hours to run.")
# with open(india_search_stats_file, "a") as stat:
# stat.write(f"Search program took {duration_hours:.2f} hours to run. \n")
folder_path = "india_data/daily_search_results/"
search_pattern = "search_result_india_*.csv"
last_file = find_second_latest_file(folder_path, search_pattern)
fresh_output = f"india_data/daily_process_folder/new_jobs_on_{today_date}.csv"
# folder_path = "india_data/daily_search_results/"
# search_pattern = "search_result_india_*.csv"
# last_file = find_second_latest_file(folder_path, search_pattern)
# fresh_output = f"india_data/daily_process_folder/new_jobs_on_{today_date}.csv"
expired_output = f"india_data/daily_upload_folder/expired_Compete_1_India_{today_date}.csv"
common_output = f"india_data/daily_common_folder/common_data_on_{today_date}.csv"
do_the_difference(india_search_output_file, last_file, 'jdURL',
fresh_output, expired_output, common_output)
# common_output = f"india_data/daily_common_folder/common_data_on_{today_date}.csv"
# do_the_difference(india_search_output_file, last_file, 'jdURL',
# fresh_output, expired_output, common_output)
india_detail_file = f"india_data/daily_upload_folder/Compete_1_India_{today_date}.csv"
india_detail_error_file = f"india_data/daily_error_folder/error_on_India_detail_{today_date}.txt"
start_time = time.time()
scraper = NaukriJobDetailScraper(fresh_output, india_detail_file, india_detail_error_file)
scraper.scrape()
end_time = time.time()
duration_hours = (end_time - start_time) / 3600
print(f"Jobdata program took {duration_hours:.2f} hours to run.")
with open(f'india_data/daily_stats_folder/stats_file_of_{today_date}.txt', "a") as stat:
stat.write(f"Jobdata program took {duration_hours:.2f} hours to run.\n")
# india_detail_error_file = f"india_data/daily_error_folder/error_on_India_detail_{today_date}.txt"
# start_time = time.time()
# scraper = NaukriJobDetailScraper(fresh_output, india_detail_file, india_detail_error_file)
# scraper.scrape()
# end_time = time.time()
# duration_hours = (end_time - start_time) / 3600
# print(f"Jobdata program took {duration_hours:.2f} hours to run.")
# with open(f'india_data/daily_stats_folder/stats_file_of_{today_date}.txt', "a") as stat:
# stat.write(f"Jobdata program took {duration_hours:.2f} hours to run.\n")
upload_file_to_bucket(expired_output, f"expired_Compete_1_India_{today_date}.csv" )
upload_file_to_bucket(india_detail_file, f"Compete_1_India_{today_date}.csv" )