def main(*args, **kwargs):
if len(kwargs) == 0:
print('No arguments/parameters passed. For more information on how to'\
'use OldTweetsScraper, you may pass "-help" as a parameter.')
return
# try:
opts = kwargs
r = args[0]
tweet_criteria = models.TweetCriteria()
for opt, value in opts.items():
if opt == 'username':
tweet_criteria.username = value
elif opt == 'since':
tweet_criteria.since = value
elif opt == 'until':
tweet_criteria.until = value
elif opt == 'query':
tweet_criteria.query = value
elif opt == 'max_tweets':
tweet_criteria.max_tweets = value
elif opt == 'language':
tweet_criteria.language = value
miner = controllers_q.Scraper()
r, status, result = miner.get_tweets(tweet_criteria, r)
print('Finished scraping data')
return r, status, result
def getTwitterData(start_date,
end_date,
max_per_day,
hashtag,
main_file='tweets_gathered.csv'):
run = True
start = datetime.datetime.strptime(start_date, '%Y-%m-%d')
end = datetime.datetime.strptime(end_date, '%Y-%m-%d')
step = datetime.timedelta(days=1)
while (start <= end):
start_date = str(start.date())
print("Processing: %s" % (start_date))
end_date = str((start + step).date())
tweet_criteria = models.TweetCriteria()
tweet_criteria.since = start_date
tweet_criteria.until = end_date
tweet_criteria.query = hashtag
tweet_criteria.max_tweets = int(max_per_day)
exporter = controllers.Exporter()
miner = controllers.Scraper()
miner.get_tweets(tweet_criteria,
buffer=exporter.output_to_file,
buffer_length=int(max_per_day))
exporter.close()
with open('tweets_gathered.csv') as f:
num_lines = sum(1 for line in f)
if (num_lines > 1):
if (run):
fout = open(main_file, "w")
for line in open("tweets_gathered.csv"):
fout.write(line)
else:
fout = open(main_file, "a")
f = open("tweets_gathered.csv")
for line in f.readlines()[1:]:
fout.write(line)
f.close()
fout.close()
run = False
start += step
def main(argv):
if len(argv) == 0:
print('No arguments/parameters passed. For more information on how to'\
'use OldTweetsScraper, you may pass "-help" as a parameter.')
return
if len(argv) == 1 and argv[0] == '-help':
instructions = 'You need to include parameters when running this file.'\
+ 'At least one of the following arguments must be used:'\
+ '\n query: query text to search for'\
+ '\n username: twitter username'\
+ '\n\nThe following arguments are optional and may be '\
+ 'passed simultaneously:'\
+ '\n since: lower bound for the date using format '\
+ 'YYYY-MM-DD'\
+ '\n until: upper bound for the date using format '\
+ 'YYYY-MM-DD'\
+ '\n max-tweets: maximum number of tweets to retrieve '\
+ '(default: 100)\n'
examples = '''
#Example 1 - Get tweets by username [barackobama] and set max tweets to 1
python main.py --username "barackobama" --max-tweets 1\n
#Example 2 - Get tweets by query [#marcosNotAHero]
python main.py --query "#marcosNotAHero" --max-tweets 1\n
#example 3 - Get tweets by query and bound dates [#BenhamRise, '2016-01-01', '2017-04-01']
python main.py --query "#BenhamRise" --since 2016-01-01 --until 2017-04-01
'''
print(instructions)
print(examples)
return
try:
opts, args = getopt.getopt(argv, '', ('username='******'since=',\
'until=', 'query=', 'max-tweets='))
tweet_criteria = models.TweetCriteria()
for opt, arg in opts:
if opt == '--username':
tweet_criteria.username = arg
elif opt == '--since':
tweet_criteria.since = arg
elif opt == '--until':
tweet_criteria.until = arg
elif opt == '--query':
tweet_criteria.query = arg
elif opt == '--max-tweets':
tweet_criteria.max_tweets = int(arg)
exporter = controllers.Exporter()
miner = controllers.Scraper()
miner.get_tweets(tweet_criteria, buffer = exporter.output_to_file)
exporter.close()
text = 'Finished scraping data. Output file generated'\
+' "tweets_gathered.csv"'
print(text);
except:
text = 'Unexpected error. Please try again. For more information on'\
+ ' how to use this script, use the -help argument.'
print(text)