Last active
December 7, 2015 20:39
-
-
Save shentonfreude/ba36f6fe8a35314ff967 to your computer and use it in GitHub Desktop.
Page through AWS CloudSearch results by pages of a given size with Next and Prev links
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/env python3 | |
""" | |
We want to query of a page 'size' of N results and return them, and also a | |
'next' and 'previous' link. Those CloudSearch 'start' offsets are based on the | |
page (for our app, starting at 1) and the size. So with size=100: page=1 has | |
start=0, page=2 has start=100, page=10 has start=100. We don't want to return | |
'previous' if we're at page=1, and don't want to return 'next' if it's beyond | |
the maximum results 'found'. So if size=100 and found=543, the last page=5, | |
there is no page=6. More generally: lastpage = int(found / size). | |
""" | |
import boto3 | |
cs = boto3.client('cloudsearchdomain', | |
endpoint_url='https://search-mydomain.us-east-1.cloudsearch.amazonaws.com', | |
region_name='us-east-1') | |
def get_results_page(query, page=1, size=3): | |
# If page too low, asking CloudSearch will break it, return only 'next' | |
if page < 1: | |
return {'previous': None, 'next': 1, 'found': 0, 'results': []} | |
# page=1 is our app's first but CloudSearch is 0-based | |
start = (page - 1) * size | |
ret = cs.search(query=query, start=start, size=size) | |
found = ret['hits']['found'] | |
lastpage = int((found + size - 1) / size) | |
# If we ask for too high a page, we do get 'found' from results, return it | |
if page > lastpage: | |
return {'previous': lastpage, 'next': None, 'found': found, 'results': []} | |
hit = ret['hits']['hit'] | |
prevpage = None | |
nextpage = None | |
if page > 2: | |
prevpage = page - 1 | |
if page < lastpage: | |
nextpage = page + 1 | |
print('<{}] {} ({}) [{}> {}'.format( | |
prevpage or 'X', page, start, nextpage or 'X', ' | '.join([h['id'] for h in hit]))) | |
return {'previous': prevpage, | |
'next': nextpage, | |
'found': found, | |
'results': ' | '.join([h['id'] for h in hit]), | |
} | |
# Walk the pages starting with 1 and following the 'next' number | |
page = 1 | |
while True: | |
res = get_results_page('nasa', page) | |
if not res['next']: | |
break | |
page += 1 | |
res = get_results_page('nasa', page=1000) | |
print('Get page too far: {}'.format(res)) | |
print('Get prev page: {}'.format(get_results_page('nasa', page=res['previous']))) | |
res = get_results_page('nasa', page=0) | |
print('Get page too low: {}'.format(res)) | |
print('Get next page: {}'.format(get_results_page('nasa', page=res['next']))) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
I've got an off-by-one error in here I need to update