revamped the wikipedia project
[wikipedia-api-cdsw] / wikipedia1-2.py
diff --git a/wikipedia1-2.py b/wikipedia1-2.py
new file mode 100644 (file)
index 0000000..98fd129
--- /dev/null
@@ -0,0 +1,33 @@
+import requests
+
+# raw string:
+# ?action=query&prop=revisions&titles=Python_(programming_language)&rvlimit=100&rvprop=timestamp|user&format=json')
+
+# parameter version which makes a little more sense
+parameters = {'action' : 'query',
+              'prop' : 'revisions',
+              'titles' : 'Python (programming language)',
+              'rvlimit' : 100,
+              'rvprop' : "timestamp|user",
+              'format' : 'json',
+              'continue' : ''}
+
+# run a white true loop
+while True:
+    wp_call = requests.get('https://en.wikipedia.org/w/api.php', params=parameters)
+    response = wp_call.json()
+    print(parameters)
+    print(response)
+
+    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
+            

Benjamin Mako Hill || Want to submit a patch?