Created
March 25, 2020 12:46
-
-
Save Nikhel1/ccd68015a2cf54cff971f1931c223a8f 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
import pandas as pd | |
import nltk | |
from tqdm import tnrange | |
import re | |
import gdelt | |
# Version 2 queries | |
gd2 = gdelt.gdelt(version=2) | |
# days | |
lengths = [31, 29, 20] #days in Jan, feb, Mar | |
lengths = [x + 1 for x in lengths] | |
# Getting data from gdelt | |
for i in range(1, len(lengths)+1): | |
month_str = str(i).zfill(2) | |
for j in range(1, lengths[i - 1]): | |
day_str = str(j).zfill(2) | |
results = gd2.Search(['2020 {} {}'.format(month_str, day_str)], table='events',coverage=True, output='pandas dataframe')#, translation=True) | |
df_path = "2020{}{}.csv".format(month_str, day_str) | |
results.to_csv("/Volumes/My Passport/Melbourne/Omdena/corona_virus/data/scrapped_articles_en_v2/" + df_path, index = None, header=True) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment