Classify the main topics

parent ed1d81ed
...@@ -294,7 +294,7 @@ def PdfBreaker(gz_url): ...@@ -294,7 +294,7 @@ def PdfBreaker(gz_url):
# print(json_object) # print(json_object)
return json_object return json_object
#Classify the main topic
def main_breaker(pubDate_, document=None, js=None): def main_breaker(pubDate_, document=None, js=None):
is_post_vacant = False is_post_vacant = False
is_examinations = False is_examinations = False
...@@ -331,10 +331,10 @@ def PdfBreaker(gz_url): ...@@ -331,10 +331,10 @@ def PdfBreaker(gz_url):
gazetteno = re.sub("[^0-9]", "", gazetteno) gazetteno = re.sub("[^0-9]", "", gazetteno)
pubDate = pubDate_ pubDate = pubDate_
print("date: ", pubDate) print("date: ", pubDate)
print('===============================================================') print('===================================================================')
print("gazette no -", gazetteno) print("gazette no -", gazetteno)
print('===============================================================') print('===================================================================')
#check the output
isScraped = Gazette.objects.all().filter(GazetteNo=gazetteno) isScraped = Gazette.objects.all().filter(GazetteNo=gazetteno)
isScrapedStr = str(isScraped) isScrapedStr = str(isScraped)
if isScrapedStr == '<QuerySet []>': if isScrapedStr == '<QuerySet []>':
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment