X-Git-Url: https://projects.mako.cc/source/wikipedia-api-cdsw/blobdiff_plain/0f362a4d7e7268de901aceb97859c91a1d87a9d2..4f9f564e2fac44ff1330a1d4d5bb4c7424791306:/wikipedia-raw2.py diff --git a/wikipedia-raw2.py b/wikipedia-raw2.py new file mode 100644 index 0000000..c7eca1b --- /dev/null +++ b/wikipedia-raw2.py @@ -0,0 +1,22 @@ +import time +import simplejson as json +from urllib2 import urlopen + +url_base = 'https://en.wikipedia.org/w/api.php?action=query&prop=revisions&titles=%s&rvlimit=100&rvprop=timestamp|user&format=json' + +pages = ["Benjamin_Mako_Hill", "Python", "Data_science"] + +for page_title in pages: + + wp_call = urlopen(url_base % page_title) + response = json.loads(wp_call.read()) + + 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"] + + + time.sleep(3)