Created
July 20, 2014 04:44
-
-
Save klenwell/16dd32f4438c53042b6e to your computer and use it in GitHub Desktop.
Python script to search Stack Overflow by tags for questions still worth answering using API
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
""" | |
Search Stack Overflow by tags for questions still worth answering | |
References: | |
search API: http://api.stackexchange.com/docs/advanced-search | |
""" | |
import stackexchange | |
import pdb | |
from datetime import datetime, timedelta | |
import time | |
import json | |
# | |
# To get API key: https://stackapps.com/ | |
# | |
API_KEY = 'PASTE HERE' | |
def search(tag='python', exclude='.net'): | |
questions = [] | |
results = [] | |
interesting = [] | |
titles = [] | |
HOURS_FROM = 24 | |
HOURS_TO = 4 | |
MAX_ANSWERS = 1 | |
MIN_OWNER_KARMA = 20 | |
fromdate = int(time.mktime((datetime.now() - timedelta(hours=HOURS_FROM)).timetuple())) | |
todate = int(time.mktime((datetime.now() - timedelta(hours=HOURS_TO)).timetuple())) | |
questions = so.search( | |
accepted=False, | |
closed=False, | |
fromdate=fromdate, | |
todate=todate, | |
tagged=tag, | |
nottagged=exclude) | |
for question in questions: | |
title = question.json.get('title') | |
if title in titles: | |
continue | |
else: | |
titles.append(title) | |
owner = question.json.get('owner', {}) | |
result = dict( | |
question=title, | |
url=question.json.get('link'), | |
owner_karma=owner.get('reputation', 0), | |
owner_accept= owner.get('accept_rate', 0), | |
answers=question.json.get('answer_count', 999), | |
votes=question.json.get('score', -1), | |
tags=question.json.get('tags'), | |
createdat=question.creation_date | |
) | |
results.append(result) | |
if (result['owner_karma'] > MIN_OWNER_KARMA) and (result['answers'] <= MAX_ANSWERS) and ( | |
result['votes'] >= 0) and (result['owner_accept'] > 50): | |
interesting.append(result) | |
print("search returned %d results" % (len(results))) | |
print("search returned %d interesting results" % (len(interesting))) | |
return { | |
'all': results, | |
'interesting': interesting | |
} | |
def interesting(tag='kineticjs', exclude='.net'): | |
results = search(tag, exclude) | |
return iter(results['interesting']) | |
USAGE = """ | |
USAGE: | |
(Pdb) results = search('tag1;tag2') | |
(Pdb) len(results['all']) | |
(Pdb) len(results['interesting']) | |
(Pdb) results = interesting('tag1;tag2') | |
(Pdb) results.next() | |
SAMPLE TAGS: | |
ajax, jquery, python, javascript, php | |
""" | |
if __name__ == '__main__': | |
so = stackexchange.Site(stackexchange.StackOverflow, API_KEY) | |
print(USAGE) | |
pdb.set_trace() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment