Reads data from a Twitter account (tweet.js) and returns information about tweets filtered by year.

tweets_year_stats.py

import pandas as pd

from datetime import datetime

YEAR = '2019'

def str_to_datetime(str):
    return datetime.strptime(str, "%a %b %d %H:%M:%S %z %Y")


file_texts = open('texts.txt', 'w')
file_mentioned = open('mentioned.txt', 'w')
file_retweeted = open('retweeted.txt', 'w')
file_rts = open('RTs.txt', 'w')

data_raw = open('tweet.js').read().replace('false', 'False').replace('true', 'True')

while data_raw[0] != '[':
    data_raw = data_raw[1:]

data_eval = eval(data_raw)

data_dict = []

for d in data_eval:
    n = {}
    d = d['tweet']  # After API update (2019)
    for text in ['favorite_count', 'retweet_count', 'id', 'full_text', 'created_at']:
        n[text] = d[text]
    data_dict.append(n)

data = pd.DataFrame(data_dict)

data['year'] = data['created_at'].map(lambda s: s[-4:])
data = data[data['year'] == YEAR]  # Filter by year

data['retweet_count'] = data['retweet_count'].map(lambda s: int(s))
data['favorite_count'] = data['favorite_count'].map(lambda s: int(s))
data['popularity'] = data.apply(lambda i: i.favorite_count + i.retweet_count, axis=1)
data = data.sort_values(by=['popularity'], ascending=False)

tweets_texts = ([i for i in data['full_text']])
for text in tweets_texts:
    if 'RT' == text.split()[0]:
        file_retweeted.write(text.split()[1])
        file_retweeted.write('\n')
        file_rts.write(str(text.encode('utf8', 'ignore').decode('utf8')))
        file_rts.write('\n')
    else:
        file_texts.write(str(text.encode('utf8', 'ignore').decode('utf8')))
        file_texts.write('\n')
        for w in text.split():
            if w[0] == '@':
                file_mentioned.write(w)
                file_mentioned.write('\n')


print('\n\n')

print('   total tweets:  %7d' % (len(data)))
print('   RTs gotten:    %7d' % (sum(data['retweet_count'])))
print('   Favs gotten:   %7d' % (sum(data['favorite_count'])))


print('\n\n\n\nMOST POPULAR TWEETS\n\n\n')

c = 0
for index, row in data.iterrows():
    text = row['full_text']
    text = str(text.encode('utf8', 'ignore').decode('utf8'))
    print(text)
    print(f"    {row['created_at']}")
    print(f"    RTs: {row['retweet_count']}  Favs: {row['favorite_count']}")
    print('    ' + row['id'])
    print('\n')
    c += 1
    if c > 7:
        exit()