• 1000 написали как
PLACE_LAT = 29.7604
PLACE_LON = -95.3698
PLACE_RAD = 200
Затем я попытался применить функцию, чтобы найти не менее 200 твитов, но я знаю, что с каждым запросом можно искать только 100. Мой код пока что ниже, однако этот код не сработал.
def retrieve_tweets(api, keyword, batch_count, total_count, latitude, longitude, radius):
"""
collects tweets using the Twitter search API
api: Twitter API instance
keyword: search keyword
batch_count: maximum number of tweets to collect per each request
total_count: maximum number of tweets in total
"""
# the collection of tweets to be returned
tweets_unfiltered = []
tweets = []
# the number of tweets within a single query
batch_count = str(batch_count)
'''
You are required to insert your own code where instructed to perform the first query to Twitter API.
Hint: revise the practical session on Twitter API on how to perform query to Twitter API.
'''
# per the first query, to obtain max_id_str which will be used later to query sub
resp = api.request('search/tweets', {'q': keywords,
'count': '100',
'lang':'en',
'result_type':'recent',
'geocode':'{PLACE_LAT},{PLACE_LONG},{PLACE_RAD}mi'.format(latitude, longitude, radius)})
# store the tweets in a list
# check first if there was an error
if ('errors' in resp.json()):
errors = resp.json()['errors']
if (errors[0]['code'] == 88):
print('Too many attempts to load tweets.')
print('You need to wait for a few minutes before accessing Twitter API again.')
if ('statuses' in resp.json()):
tweets_unfiltered += resp.json()['statuses']
tweets = [tweet for tweet in tweets_unfiltered if ((tweet['retweeted'] != True) and ('RT @' not in tweet['text']))]
# find the max_id_str for the next batch
ids = [tweet['id'] for tweet in tweets_unfiltered]
max_id_str = str(min(ids))
# loop until as many tweets as total_count is collected
number_of_tweets = len(tweets)
while number_of_tweets < total_count:
resp = api.request('search/tweets', {'q': keywords,
'count': '50',
'lang':'en',
'result_type': 'recent',
'max_id': max_id_str,
'geocode':'{PLACE_LAT},{PLACE_LONG},{PLACE_RAD}mi'.format(latitude, longitude, radius)}
)
if ('statuses' in resp.json()):
tweets_unfiltered += resp.json()['statuses']
tweets = [tweet for tweet in tweets_unfiltered if ((tweet['retweeted'] != True) and ('RT @' not in tweet['text']))]
ids = [tweet['id'] for tweet in tweets_unfiltered]
max_id_str = str(min(ids))
number_of_tweets = len(tweets)
print("{} tweets are collected for keyword {}. Last tweet created at {}".format(number_of_tweets,
keyword,
tweets[number_of_tweets-1]['created_at']))
return tweets
Мне нужно было только написать код, в котором говорилось: # Вставьте свой код. Какие изменения мне нужно внести, чтобы это работало
def retrieve_tweets(api, keyword, batch_count, total_count, latitude, longitude, radius):
"""
collects tweets using the Twitter search API
api: Twitter API instance
keyword: search keyword
batch_count: maximum number of tweets to collect per each request
total_count: maximum number of tweets in total
"""
# the collection of tweets to be returned
tweets_unfiltered = []
tweets = []
# the number of tweets within a single query
batch_count = str(batch_count)
'''
You are required to insert your own code where instructed to perform the first query to Twitter API.
Hint: revise the practical session on Twitter API on how to perform query to Twitter API.
'''
# per the first query, to obtain max_id_str which will be used later to query sub
resp = api.request('search/tweets', {'q': #INSERT YOUR CODE
'count': #INSERT YOUR CODE
'lang':'en',
'result_type':'recent',
'geocode':'{},{},{}mi'.format(latitude, longitude, radius)})
# store the tweets in a list
# check first if there was an error
if ('errors' in resp.json()):
errors = resp.json()['errors']
if (errors[0]['code'] == 88):
print('Too many attempts to load tweets.')
print('You need to wait for a few minutes before accessing Twitter API again.')
if ('statuses' in resp.json()):
tweets_unfiltered += resp.json()['statuses']
tweets = [tweet for tweet in tweets_unfiltered if ((tweet['retweeted'] != True) and ('RT @' not in tweet['text']))]
# find the max_id_str for the next batch
ids = [tweet['id'] for tweet in tweets_unfiltered]
max_id_str = str(min(ids))
# loop until as many tweets as total_count is collected
number_of_tweets = len(tweets)
while number_of_tweets < total_count:
resp = api.request('search/tweets', {'q': #INSERT YOUR CODE
'count': #INSERT YOUR CODE
'lang':'en',
'result_type': #INSERT YOUR CODE
'max_id': max_id_str,
'geocode': #INSERT YOUR CODE
)
if ('statuses' in resp.json()):
tweets_unfiltered += resp.json()['statuses']
tweets = [tweet for tweet in tweets_unfiltered if ((tweet['retweeted'] != True) and ('RT @' not in tweet['text']))]
ids = [tweet['id'] for tweet in tweets_unfiltered]
max_id_str = str(min(ids))
number_of_tweets = len(tweets)
print("{} tweets are collected for keyword {}. Last tweet created at {}".format(number_of_tweets,
keyword,
tweets[number_of_tweets-1]['created_at']))
return tweets