def getTweets_condensed(): v2 = "process_tweets_db.json" with open('recent_tweets.json', 'r+', encoding='utf8') as tweet_handle: for data_item in tweet_handle: tweetDetails = json.loads(data_item) stream_condenser = Condenser_Tweets(tweetDetails) if stream_condenser.text == '' or stream_condenser.location[ 0] == -1 or stream_condenser.location[1] == -1: continue else: data = stream_condenser.updatedJson() write_file(v2, data) print("Stream processed with Stream")
def get_historic_condensed(): v2 = "historic_dbdata.json" with open('1_2018.json', 'r+', encoding='utf8') as tweetFile: for lineNum, line in enumerate(tweetFile): if lineNum > 0: if "coordinates" in str(line): if str(line[-2]) == ',': line = line[:-2] elif str(line[-3:-1]) == "]}": break tweetDetails = json.loads(line) search_condenser = Condenser_Tweets(tweetDetails) data = search_condenser.updatedJson() write_file(v2, data)
def get_historic_condensed(): Path('historic_dbdata.json').touch() v2 = 'historic_dbdata.json' with open('twitter-melb.json', 'r+', encoding='utf8') as tweetFile: for lineNum, line in enumerate(tweetFile): if lineNum > 355000: if str(line[-2]) == ',': tweetDetails = json.loads(line[:-2]) search_condenser = Condenser_Tweets(tweetDetails) if search_condenser.text == '' or search_condenser.location[ 0] == -1 or search_condenser.location[1] == -1: continue else: data = search_condenser.updatedJson() write_file(v2, data)
def getTweets_condensed(): v2 = "process_tweets_db.json" with open('recent_tweets.json', 'r+', encoding='utf8') as tweet_handle: for data_item in tweet_handle: tweetDetails = json.loads(data_item) stream_condenser = Condenser_Tweets(tweetDetails) data = stream_condenser.updatedJson() write_file(v2, data) print("Stream processed with Stream") v3 = "user_tweets_db.json" with open('user_list_timeline.json', 'r+', encoding='utf8') as tweet_handle: for data_item in tweet_handle: tweetDetails = json.loads(data_item) search_condenser = Condenser_Tweets(tweetDetails) data = search_condenser.updatedJson() write_file(v3, data) print("Search processed tweets for database")
Created on Tue May 5 23:47:49 2020 @author: Sania Khan """ import json from Condenser import Condenser_Tweets def write_file(file, data): outfile = open(file, 'a+') outfile.write(json.dumps(data) + "\n") outfile.close() v2 = "process_tweets_db.json" if __name__ == "__main__": with open ('recent_tweets.json', 'r+', encoding='utf8') as tweet_handle: for data_item in tweet_handle: tweetDetails = json.loads(data_item) stream_condenser = Condenser_Tweets(tweetDetails) data = stream_condenser.updatedJson() with open(v2) as f: write_file(v2, data) with open ('user_list_timeline.json', 'r+', encoding='utf8') as tweet_handle: for data_item in tweet_handle: tweetDetails = json.loads(data_item) search_condenser = Condenser_Tweets(tweetDetails) data = search_condenser.updatedJson() with open(v2) as f: write_file(v2, data)