hgj

common_task.py

@@ -94,11 +94,11 @@ def run_india_scraper():
     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"
+    expired_output = f"india_data/daily_upload_folder/Compete_1_India_Archieve_{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)
-    india_detail_file = f"india_data/daily_upload_folder/Compete_1_India_{today_date}.csv"
+    india_detail_file = f"india_data/daily_upload_folder/Compete_1_India_Active_{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) 
@@ -110,8 +110,8 @@ 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"expired_Compete_1_India_{today_date}.csv" )
+    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_{today_date}.csv" )
+    upload_file_to_bucket(india_detail_file, f"Compete_1_India_Active_{today_date}.csv" )
 
 def run_gulf_scraper():
     gulfSearch()
@@ -121,12 +121,12 @@ def run_gulf_scraper():
     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/expired_Compete_1_gulf_{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"
     do_the_difference(gulf_search_file, last_file, "jdURL", fresh_output, expired_output, common_output)
-    upload_file_to_bucket(expired_output, f"expired_Compete_1_Gulf_{today_date}.csv" )
+    upload_file_to_bucket(expired_output, f"Compete_1_Gulf_Archieve_{today_date}.csv" )
     start_time = time.time()
-    gulf_detail_file = f"gulf_data/daily_upload_folder/Compete_1_gulf_{today_date}.csv"
+    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"
     scraper = NaukriGulfJobDetailScraper(fresh_output, gulf_detail_file, gulf_detail_error_file)
     scraper.scrape()
@@ -135,7 +135,7 @@ def run_gulf_scraper():
     print(f"Jobdata program took {duration_hours:.2f} hours to run.")
     with open(f'gulf_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(gulf_detail_file, f"Compete_1_Gulf_{today_date}.csv" )
+    upload_file_to_bucket(gulf_detail_file, f"Compete_1_Gulf_Active_{today_date}.csv" )
 
 
 if __name__ == "__main__":

naukri/search_india.py

@@ -42,7 +42,7 @@ class NaukriJobScraper:
     "user-agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/116.0.0.0 Safari/537.36 Edg/116.0.1938.43",
     "content-encoding": "gzip",
     }   
-
+    stopcrawl = False
     # headers = { 
     # "appid": "109",
     # "systemid": "109"
@@ -62,6 +62,17 @@ class NaukriJobScraper:
         for job in json_data["jobDetails"]:
             parsed_item = {field: job.get(field, None) for field in self.keys_to_extract}
             parsed_data.append(parsed_item)
+            # with open('r,txt', 'w+', encoding='utf-8', newline='') as dr:
+            #     import json
+            #     dr.write(json.dumps(parsed_data))
+            # print(parsed_data)
+        days_ago_list = [x['footerPlaceholderLabel'] for x in parsed_data]
+        target = "7 Days Ago"
+        count = days_ago_list.count(target)
+        percentage = (count / len(days_ago_list)) * 100
+        if percentage > 60:
+            self.stopcrawl = True
+        
 
         with open(self.output_file_path, "a", newline="", encoding="utf-8") as csvfile:
             csv_writer = csv.DictWriter(csvfile, fieldnames=self.keys_to_extract)
@@ -79,10 +90,13 @@ class NaukriJobScraper:
                 industry_name=industry[1]
                 industry_q=industry[2]
                 total_pages = 1000
+                self.stopcrawl = False
                 start_page = 1
 
                 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)
                     try:
                         # print(url)