updated wikipedia project to fix windows encoding issue
[wikipedia-api-cdsw] / wikipedia2-2.py
1 import encoding_fix
2 import requests
3
4 # base url:
5 # https://en.wikipedia.org/w/api.php?action=query&prop=revisions&titles=%s&rvlimit=100&rvprop=timestamp|user&format=json
6
7 pages = ["Benjamin Mako Hill", "University of Washington", "Data science"]
8
9 parameters = {'action' : 'query',
10               'prop' : 'revisions',
11               'rvlimit' : 100,
12               'rvprop' : 'timestamp|user',
13               'format' : 'json',
14               'continue' : ''}
15         
16 for page_title in pages:
17     parameters['titles'] = page_title
18     
19     while True:
20         wp_call = requests.get('https://en.wikipedia.org/w/api.php', params=parameters)
21         response = wp_call.json()
22
23         for page_id in response["query"]["pages"].keys():
24             page_title = response["query"]["pages"][page_id]["title"]
25             revisions = response["query"]["pages"][page_id]["revisions"]
26
27             for rev in revisions:
28                 print(page_title + "\t" + rev["user"] + "\t" + rev["timestamp"])
29                 
30         if 'continue' in response:
31             parameters.update(response['continue'])
32         else:
33             break

Benjamin Mako Hill || Want to submit a patch?