Last active
June 30, 2020 11:11
-
-
Save 4lexLammers/907b0ccd888d0c0c2367ebd3af88bf23 to your computer and use it in GitHub Desktop.
Tweepy Project for Collecting Tweets
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
#Libraries | |
import tweepy | |
from textblob import TextBlob | |
import time | |
from prettytable import PrettyTable | |
from datetime import datetime | |
import sqlite3 | |
############################################################################### | |
""" | |
Search hashtag | |
""" | |
targettwitterhashtag = '#EconTwitter' | |
""" | |
Create SQL Table Database | |
""" | |
conn = sqlite3.connect(''+targettwitterhashtag+'.db') | |
c = conn.cursor() | |
try: | |
c.execute('CREATE TABLE '+targettwitterhashtag[1:]+' (n int, dbtweettext text, dbtweetlen int, dbtweetid int PRIMARY KEY, dbtweetdate date, dbtweetsource text, dbtweetlikes int, dbtweetretweets int, polarity real)') | |
except: | |
pass | |
############################################################################### | |
""" | |
Authentification | |
""" | |
consumer_key = | |
consumer_secret = | |
access_token = | |
access_token_secret = | |
#Consumer key and consumer secret to Tweepy's user authentication handler | |
auth = tweepy.OAuthHandler(consumer_key, consumer_secret) | |
#Access token and access secret to Tweepy's user authentication handler | |
auth.set_access_token(access_token, access_token_secret) | |
api = tweepy.API(auth, wait_on_rate_limit=True) | |
#Getting Geo ID for Germany | |
places = api.geo_search(query="GERMANY", granularity="country") | |
#Copy Germany id: fdcd221ac44fa326 | |
place_id = places[0].id | |
print('Germany id is: ',place_id) | |
#Switching to application authentication | |
auth = tweepy.AppAuthHandler(consumer_key, consumer_secret) | |
#Setting up new api wrapper, using authentication only | |
api = tweepy.API(auth, wait_on_rate_limit=True,wait_on_rate_limit_notify=True) | |
############################################################################### | |
x = PrettyTable() | |
x.field_names = ["Count", "Text", "Length", "ID", "Date", "Source", "Likes", "Retweets", "Polarity"] | |
n = 1 | |
for tweet in tweepy.Cursor(api.search, tweet_mode='extended', q='#EconTwitter -filter:retweets', lang="en").items(10): | |
print(tweet.full_text) | |
tweetid = tweet.id | |
tweetdate = tweet.created_at | |
source = tweet.source | |
likes = tweet.favorite_count | |
retweets = tweet.retweet_count | |
tweettext = tweet.full_text | |
length = len(tweettext) | |
polarity = round(TextBlob(tweettext).sentiment.polarity,4) | |
x.add_row([n, tweettext, len, tweetid, tweetdate, source, likes, retweets, polarity]) | |
c.execute("insert into "+targettwitterhashtag[1:]+" values (?,?,?,?,?,?,?,?,?)", (n, tweettext, length, tweetid, tweetdate, source, likes, retweets, polarity)) | |
n+=1 | |
print(x) | |
conn.commit() | |
c.close() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment