59 lines
1.5 KiB
Python
59 lines
1.5 KiB
Python
#from phabricator import Phabricator
|
|
import os, sys
|
|
import json
|
|
import numpy as np
|
|
import pandas as pd
|
|
import requests
|
|
import re
|
|
import datetime
|
|
import time
|
|
from urllib.parse import quote_plus
|
|
|
|
from requests.auth import HTTPDigestAuth
|
|
from pygerrit2 import GerritRestAPI, HTTPBasicAuth
|
|
|
|
# GET /changes/?q=status:abandoned&q=before:{date}&q={TERM}
|
|
# GET https://gerrit.wikimedia.org/r/changes/?q=status:abandoned+visualeditor
|
|
|
|
def query_changes(
|
|
query_terms,
|
|
limit = 100,
|
|
api_url_base = 'https://gerrit.wikimedia.org/',
|
|
sleep = 10
|
|
):
|
|
|
|
time.sleep(sleep)
|
|
to_query = 1
|
|
after = None
|
|
|
|
data = []
|
|
|
|
while to_query == 1:
|
|
time.sleep(sleep)
|
|
joined_terms = "+".join(query_terms)
|
|
params = {
|
|
'q' : joined_terms,
|
|
}
|
|
|
|
api_url = f"{api_url_base}r/changes/?q={joined_terms}"
|
|
#add no-limit and API key somewhere
|
|
|
|
#auth = HTTPBasicAuth("ggonnemm", "1V6txZh5X+N3JpDMm5zqZM2M7ewA5D09g4ABOZAl5Q")
|
|
response = requests.get(api_url, headers={'Content-Type': 'application/json'})
|
|
|
|
result = json.load(response.text[5:])
|
|
#print(response.text)
|
|
## the data
|
|
data_tmp = result
|
|
data += data_tmp
|
|
print(data[-1])
|
|
## check if there are more results to query
|
|
break
|
|
return data
|
|
|
|
|
|
if __name__ == "__main__":
|
|
query_strings = ['before:2016-12-31', 'visualeditor']
|
|
results = query_changes(query_strings)
|
|
print(results)
|