boehmermann.py

import requests
import time
import json
url = "https://de.wikipedia.org/w/api.php?action=query&prop=revisions&titles=Jan_B%C3%B6hmermann&rvslots=*&rvprop=timestamp|user|content&rvlimit=max&format=json"
url2 = "https://de.wikipedia.org/w/api.php?action=query&prop=revisions&titles=Jan_B%C3%B6hmermann&rvslots=*&rvprop=timestamp|user|content&rvlimit=max&format=json&rvstart={}"
s = requests.Session()

USE_LOADED_DATA = False

if(not USE_LOADED_DATA):
	data = s.get(url=url).json()
	query_result = data["query"]
	query_result = query_result["pages"]
	query_result = query_result['2935829']
	revisions = query_result["revisions"]

	complete_revisions = []

	while(len(revisions) != 1):
		complete_revisions.extend(revisions)
		data = s.get(url=url2.format(complete_revisions[-1]["timestamp"])).json()
		revisions = data["query"]["pages"]["2935829"]["revisions"]
		print("fetched", len(revisions), "more revisions")
		time.sleep(0.4)

	with open("revisions.json", "w") as fout:
		json.dump(complete_revisions, fout)
else:
	with open("revisions.json", "r") as fin:
		complete_revisions = json.load(fin)

def contains_rainer(rev):
	if(not "*" in rev["slots"]["main"]):
		print(rev)
		return False
	return "Rainer" in rev["slots"]["main"]["*"]


containing_rainer = [rev for rev in complete_revisions if contains_rainer(rev)]
print("\n".join([c["timestamp"] for c in containing_rainer]))