Skip to content
Create a gist now

Instantly share code, notes, and snippets.

Embed URL


Subversion checkout URL

You can clone with
Download ZIP
Perform secondary index (2i) searches on Twitter hashtags stored in Riak and count all hashtags in the matching tweets.
import riak
Riak = riak.RiakClient(pb_port=10017, protocol='pbc')
TweetsBucket = Riak.bucket('tweets')
results = TweetsBucket.get_index("hashtags_bin", "android",
"androie", return_terms=False)
other_tags = {}
# With return_terms=False, each result will be simply a Riak
# key. Retrieve each object, iterate over and tally the associated
# index values
for riak_key in results.results:
riak_object = TweetsBucket.get(riak_key)
for index in riak_object.indexes:
if index[0] == 'hashtags_bin':
hashtag = index[1]
if hashtag in other_tags:
other_tags[hashtag] += 1
other_tags[hashtag] = 1
all_tags = other_tags.keys()
for tag in all_tags:
print '{0: >5}'.format(str(other_tags[tag])) + " " + tag
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Something went wrong with that request. Please try again.