X-Git-Url: https://projects.mako.cc/source/wikipedia-api-cdsw/blobdiff_plain/f17f0a3f63dd03d70cdc693da0bda53a1e85671b..99337ede51f8abbcf0663e7c93672f70f9b6ddd9:/wikipedia2-2.py diff --git a/wikipedia2-2.py b/wikipedia2-2.py new file mode 100644 index 0000000..4dc2f30 --- /dev/null +++ b/wikipedia2-2.py @@ -0,0 +1,32 @@ +import requests + +# base url: +# https://en.wikipedia.org/w/api.php?action=query&prop=revisions&titles=%s&rvlimit=100&rvprop=timestamp|user&format=json + +pages = ["Benjamin Mako Hill", "University of Washington", "Data science"] + +parameters = {'action' : 'query', + 'prop' : 'revisions', + 'rvlimit' : 100, + 'rvprop' : 'timestamp|user', + 'format' : 'json', + 'continue' : ''} + +for page_title in pages: + parameters['titles'] = page_title + + while True: + wp_call = requests.get('https://en.wikipedia.org/w/api.php', params=parameters) + response = wp_call.json() + + for page_id in response["query"]["pages"].keys(): + page_title = response["query"]["pages"][page_id]["title"] + revisions = response["query"]["pages"][page_id]["revisions"] + + for rev in revisions: + print(page_title + "\t" + rev["user"] + "\t" + rev["timestamp"]) + + if 'continue' in response: + parameters.update(response['continue']) + else: + break