def tweets_large_geo():
# type: () -> Dict[str, List[Status]]
"""Return a static list of 300 tweets geotagged 20 miles from Chicago's center that is generated once and
re-used throughout the module's lifetime."""
return CachedTweets.scraper.scrape_terms(
{"flood", "fire", "house fire"},
count=100,
geocode=geobox_to_geocode(GEOBOX_CHICAGO, "20mi"))
# Maximum tweets to search for.
MAX_TWEETS = args.maxtweets if args.maxtweets else \
10
# Radius to search for tweets in.
TWEET_RADIUS = "50mi"
# Set up twitter auth.
twauth = TwitterAuthentication.autodetect_twitter_auth()
api = tweepy.API(twauth.oauth_handler,
wait_on_rate_limit=True,
wait_on_rate_limit_notify=True)
# Get Twitter geocode from Chicago's geobox.
geocode = geobox_to_geocode(GEOBOX_CHICAGO, TWEET_RADIUS)
# List of search terms to search for.
search_terms = get_fire_search_terms()
print(
"Scraping the top {n} tweets that reference search terms from our '{path}' datafile inside {geocode}"
.format(n=MAX_TWEETS,
path=os.path.basename(DataConfig.FIRE_HASHTAGS_DATA_PATH),
geocode=geocode))
# All tweets, sorted by search term
all_tweets = {}
# For all search terms,
for search_term in search_terms: # type: str
from pprint import pprint
from twitter_fire_scraper.scraper import Scraper
from twitter_fire_scraper.twitter import GEOBOX_CHICAGO
from twitter_fire_scraper.util import geobox_to_geocode, flatten_status_dict
if __name__ == '__main__':
scraper = Scraper()
terms = {"#pizza", "pizza", 'cat', '#cat'}
results = scraper.scrape_terms(terms=terms, count=3)
results = flatten_status_dict(results)
print("{} on all of twitter:".format(", ".join(terms)))
pprint(results)
results = scraper.scrape_terms(geocode=geobox_to_geocode(
GEOBOX_CHICAGO, "20mi"),
terms=terms,
count=3)
results = flatten_status_dict(results)
print("{} in chicago:".format(", ".join(terms)))
pprint(results)
# scraper = Scraper()
#
# results = scraper.scrape_accounts(accounts=['MABASIllinois','NWSChicago'])
#
# pprint(results)