def retrieve_extraction(page_id,add_if_not_found=True):
print "retrieving Extraction for ....%s" % (page_id)
with app.test_request_context('/'): # this is to adjust for the fact that we are in celery content and not Flask context
app.preprocess_request()
extraction = Extraction.get_extraction_by_page_id(page_id)
if extraction is None:
if add_if_not_found: # add a page
extraction = Extraction.add_extraction(page_id)
else:
return extractionnotfound
else:
pass # do nothing
#<-->We will not do boilerpipe extraction here... We are going to simply put an extraction page
# But we will run a separate process that activates boilerpipe taking page.id and extraction.id.
#boilerpipe_extract_and_populate.delay(page_id,extraction.id)
#Using Rest API
'''rExt = requests.get("http://127.0.0.1:5000/extractions", params={"page_id":page_id})
