Created
June 5, 2019 14:57
-
-
Save JonathanReeve/838763012865ab785f8b304d4e5e0346 to your computer and use it in GitHub Desktop.
The Twitter Bot "Alternate DHSIs," which finds DHSI initialisms from Project Gutenberg texts.
This file contains 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
import re | |
import requests | |
import json | |
import time | |
import tweepy | |
from secrets import * | |
# This requires that you have a file, secrets.py | |
# Which contains the keys below. | |
auth = tweepy.OAuthHandler(CONSUMER_KEY, CONSUMER_SECRET) | |
auth.set_access_token(ACCESS_KEY, ACCESS_SECRET) | |
api = tweepy.API(auth) | |
lastTime = 0 | |
for i in range(49,50000): | |
print('Getting text with id: %s' % i) | |
metaResponse = requests.get('http://corpus-db.org/api/id/' + str(float(i))) | |
if metaResponse.ok: | |
metaParsed = json.loads(metaResponse.text) | |
if 'title' in metaParsed: | |
print('Title: ', metaParsed['title']) | |
else: | |
print('No title found.') | |
else: | |
print("Couldn't get metadata for id: %s" % i) | |
continue | |
textResponse = requests.get('http://corpus-db.org/api/id/' + str(float(i)) + '/fulltext') | |
if textResponse.ok: | |
textParsed = json.loads(textResponse.text) | |
if len(textParsed) > 0: | |
text = textParsed[0]['text'] if 'text' in textParsed[0] else '' | |
text = text.replace('\n', ' ') # Regex doesn't like to find things across newlines | |
matches = re.findall('\s([Dd]\w+\s[Hh]\w+\s[Ss]\w+\s[Ii]\w+)\s\w+', text, re.MULTILINE) | |
print('--------------- FOUND ----------------') | |
for match in matches: | |
timeSinceLast = time.time() - lastTime | |
while timeSinceLast < 3600: | |
print('Waiting...') | |
timeSinceLast = time.time() - lastTime | |
time.sleep(500) | |
tweet = "DHSI also stands for: \"" + match + "\" as found in " + metaParsed['title'] | |
tweet += ". See http://gutenberg.org/ebooks/%s for the full text. #DHSI19" % i | |
print(tweet) | |
api.update_status(tweet) | |
lastTime = time.time() | |
else: | |
print('No text here.') | |
else: | |
print("Couldn't get full text!") | |
continue |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment