Retrieve the last 100 revisions of a wikipedia article

wikipedia_revision_grabber.py

import synapseclient
from synapseclient import File, Project, Folder

syn = synapseclient.login()

## get latest 100 revisions of a wikipedia article
url = "http://en.wikipedia.org/w/api.php?action=query&titles=Crimea&prop=revisions&rvprop=ids|timestamp|flags|content&rvlimit=100&format=json"

response = requests.get(url)
crimea = response.json()

## make sure we got 100
print len(crimea['query']['pages']['163045']['revisions'])

## write to a file
with open('crimea.revisions.json', 'w') as f:
    json.dump(crimea, f)
project = syn.get('syn2489903')

## store in Synapse
syn.store(File('crimea.revisions.json', parent=project))