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

jyg

prahul11 2023-10-20 17:39:38 +05:30
parent 3949b0ef0c
commit 81664f692a
2 changed files with 9 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
common_task.py
View File

@ -94,7 +94,7 @@ def run_india_scraper(today_date):
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/Compete_1_India_Archieve_{today_date}.csv"
expired_output = f"india_data/daily_upload_folder/Compete_1_India_Archive_{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)
@ -110,7 +110,7 @@ def run_india_scraper(today_date):
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" , today_date)
upload_file_to_bucket(expired_output, f"Compete_1_India_Archive_{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(today_date):
@ -121,10 +121,10 @@ def run_gulf_scraper(today_date):
# 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"
expired_output = f"gulf_data/daily_upload_folder/Compete_1_Gulf_Archive_{today_date}.csv"
common_output = f"gulf_data/daily_common_folder/common_data_on_{today_date}.csv"
do_the_difference(gulf_search_file, last_file, "jdURL", fresh_output, expired_output, common_output)
upload_file_to_bucket(expired_output, f"Compete_1_Gulf_Archieve_{today_date}.csv" ,today_date)
upload_file_to_bucket(expired_output, f"Compete_1_Gulf_Archive_{today_date}.csv" ,today_date)
start_time = time.time()
gulf_detail_file = f"gulf_data/daily_upload_folder/Compete_1_Gulf_Active_{today_date}.csv"
gulf_detail_error_file = f"india_data/daily_error_folder/error_on_India_detail_{today_date}.txt"

6
naukri/search_india.py
View File

@ -93,12 +93,15 @@ class NaukriJobScraper:
total_pages = 1000
# self.stopcrawl = False
start_page = 1
error_count = 0
print(f"Starting for industry: {industry_name}, total pages: {total_pages}, start page: {start_page}")
while total_pages > 0:
# if self.stopcrawl:
# total_pages = 0
url = self.base_url.format(industry_name, start_page, industry_q)
if error_count >3:
total_pages -= 1
start_page += 1
try:
# print(url)
# response = requests.get(url, headers=self.headers, timeout=self.timeout,
@ -132,6 +135,7 @@ class NaukriJobScraper:
print(f"Industry: {industry_name}, pages remaining: {total_pages}, start page: {start_page}")
time.sleep(1)
except Exception as e1:
error_count +=1
logging.error(url + '\n'+ str(e1) + '\n')