Created
September 4, 2019 13:26
-
-
Save bobturneruk/596809e0f4569e30e6e8a6f7198f1ad0 to your computer and use it in GitHub Desktop.
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
# Required libraries | |
from twython import Twython | |
import json | |
import pandas as pd | |
# Access Twitter API using twython | |
APP_KEY = '' # Use your API KEY | |
APP_SECRET = '' # Use your secret | |
twitter = Twython(APP_KEY, APP_SECRET, oauth_version=2) | |
ACCESS_TOKEN = twitter.obtain_access_token() | |
twitter = Twython(APP_KEY, access_token=ACCESS_TOKEN) | |
# Execute a search for "GMO" in English returning 100 records | |
twit_py_json=twitter.search(q='GMO',count=100,lang='en') #found I needed to set count or I get an incomplete .json string | |
# Save the .json file | |
jsonfile=open('jsonfile.json','w') | |
json.dump(twit_py_json,jsonfile) | |
jsonfile.close() | |
# Make a pandas dataframe | |
data_i_want=[] #empty list | |
for status in twit_py_json['statuses']: #loop through all tweets AKA statuses | |
data_i_want.append({'id':status['id'],'text':status['text']}) #take the "id" and "text" fields, and add to the empty list | |
data_i_want_df=pd.DataFrame(data_i_want) #turn the list into a dataframe | |
# Save the data to Excel (note that the data type of columns may not be respected) | |
data_i_want_df.to_excel('tweets.xlsx',sheet_name='GMO') |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment