get_all_hits.py

import argparse, json
import simpleamt
import sys
"""
Run with --prod to get all the hits from production.
"""

def get_all_reviewable_hits(mtc):
    page_size = 50
    hits = mtc.get_reviewable_hits(page_size=page_size)
    print "Total results to fetch %s " % hits.TotalNumResults
    print "Request hits page %i" % 1
    total_pages = float(hits.TotalNumResults)/page_size
    int_total= int(total_pages)
    if(total_pages-int_total>0):
        total_pages = int_total+1
    else:
        total_pages = int_total
    pn = 1
    while pn < total_pages:
        pn = pn + 1
        print "Request hits page %i" % pn
        temp_hits = mtc.get_reviewable_hits(page_size=page_size,page_number=pn)
        hits.extend(temp_hits)
    return hits


if __name__ == '__main__':
  parser = argparse.ArgumentParser(parents=[simpleamt.get_parent_parser()])
  parser.add_argument('--reviewable', action='store_true', default=False)
  args = parser.parse_args()
  mtc = simpleamt.get_mturk_connection_from_args(args)
  hits = get_all_reviewable_hits(mtc) if args.reviewable else mtc.get_all_hits()
  hitIds = [h.HITId for h in hits]
  print "Got %i hits" % len(hitIds)
  for hitId in hitIds:
    print hitId