Hi I keep getting this error:
D:\WinPython-32bit-2.7.10.3\python-2.7.10>python TweetTest.py Twitter.json
Traceback (most recent call last):
File "TweetTest.py", line 60, in <module>
tweet = json.loads(line)
File "D:\WinPython-32bit-2.7.10.3\python-2.7.10\lib\json\__init__.py", line 338, in loads
return _default_decoder.decode(s)
File "D:\WinPython-32bit-2.7.10.3\python-2.7.10\lib\json\decoder.py", line 369, in decode
raise ValueError(errmsg("Extra data", s, end, len(s)))
ValueError: Extra data: line 1 column 4488 - line 1 column 99678411 (char 4487 - 99678410)
I have no idea what is wrong. My code is as follows:
import sys
import json
from collections import Counter
import re
from nltk.corpus import stopwords
import string
punctuation = list(string.punctuation)
stop = stopwords.words('english') + punctuation + ['rt', 'via']
emoticons_str = r"""
(?:
[:=;] # Eyes
[oO\-]? # Nose (optional)
[D\)\]\(\]/\\OpP] # Mouth
)"""
regex_str = [
emoticons_str,
r'<[^>]+>', # HTML tags
r'(?:@[\w_]+)', # @-mentions
r"(?:\#+[\w_]+[\w\'_\-]*[\w_]+)", # hash-tags
r'http[s]?://(?:[a-z]|[0-9]|[$-_@.&+]|[!*\(\),]|(?:%[0-9a-f][0-9a-f]))+', # URLs
r'(?:(?:\d+,?)+(?:\.?\d+)?)', # numbers
r"(?:[a-z][a-z'\-_]+[a-z])", # words with - and '
r'(?:[\w_]+)', # other words
r'(?:\S)' # anything else
]
tokens_re = re.compile(r'('+'|'.join(regex_str)+')', re.VERBOSE | re.IGNORECASE)
emoticon_re = re.compile(r'^'+emoticons_str+'$', re.VERBOSE | re.IGNORECASE)
def tokenize(s):
return tokens_re.findall(s)
def preprocess(s, lowercase=False):
tokens = tokenize(s)
if lowercase:
tokens = [token if emoticon_re.search(token) else token.lower() for token in tokens]
return tokens
if __name__ == '__main__':
fname = sys.argv[1]
with open(fname, 'r') as f:
count_all = Counter()
for line in f:
tweet = json.loads(line)
tokens = preprocess(tweet['text'])
count_all.update(tokens)
print(count_all.most_common(5))
This is the first two output of my JSON file. I have used a Tweet Stream listener to collect the tweets.
{"created_at":"Wed Apr 06 08:33:55 +0000 2016","id":717631408345333760,"id_str":"717631408345333760","text":"RT @whosharold: Hilary Clinton cannot be president pls she can't even hold her man down what makes ya think she gon hold the office down","source":"\u003ca href=\"http:\/\/twitter.com\/download\/iphone\" rel=\"nofollow\"\u003eTwitter for iPhone\u003c\/a\u003e","truncated":false,"in_reply_to_status_id":null,"in_reply_to_status_id_str":null,"in_reply_to_user_id":null,"in_reply_to_user_id_str":null,"in_reply_to_screen_name":null,"user":{"id":472387071,"id_str":"472387071","name":"BigGucciK 2x","screen_name":"KaisonThatBoy","location":"Bridgeport, CT","url":null,"description":null,"protected":false,"verified":false,"followers_count":1608,"friends_count":1219,"listed_count":8,"favourites_count":1293,"statuses_count":64337,"created_at":"Mon Jan 23 22:07:27 +0000 2012","utc_offset":-10800,"time_zone":"Atlantic Time (Canada)","geo_enabled":false,"lang":"en","contributors_enabled":false,"is_translator":false,"profile_background_color":"131516","profile_background_image_url":"http:\/\/abs.twimg.com\/images\/themes\/theme14\/bg.gif","profile_background_image_url_https":"https:\/\/abs.twimg.com\/images\/themes\/theme14\/bg.gif","profile_background_tile":true,"profile_link_color":"009999","profile_sidebar_border_color":"EEEEEE","profile_sidebar_fill_color":"EFEFEF","profile_text_color":"333333","profile_use_background_image":true,"profile_image_url":"http:\/\/pbs.twimg.com\/profile_images\/709500377104818182\/4vMu066C_normal.jpg","profile_image_url_https":"https:\/\/pbs.twimg.com\/profile_images\/709500377104818182\/4vMu066C_normal.jpg","profile_banner_url":"https:\/\/pbs.twimg.com\/profile_banners\/472387071\/1457000395","default_profile":false,"default_profile_image":false,"following":null,"follow_request_sent":null,"notifications":null},"geo":null,"coordinates":null,"place":null,"contributors":null,"retweeted_status":{"created_at":"Wed Apr 06 03:16:15 +0000 2016","id":717551464575401984,"id_str":"717551464575401984","text":"Hilary Clinton cannot be president pls she can't even hold her man down what makes ya think she gon hold the office down","source":"\u003ca href=\"http:\/\/twitter.com\/download\/iphone\" rel=\"nofollow\"\u003eTwitter for iPhone\u003c\/a\u003e","truncated":false,"in_reply_to_status_id":null,"in_reply_to_status_id_str":null,"in_reply_to_user_id":null,"in_reply_to_user_id_str":null,"in_reply_to_screen_name":null,"user":{"id":792436550,"id_str":"792436550","name":"sadboyz","screen_name":"whosharold","location":null,"url":null,"description":"platano maduro no vuelve a verde","protected":false,"verified":false,"followers_count":1285,"friends_count":979,"listed_count":11,"favourites_count":4877,"statuses_count":91425,"created_at":"Thu Aug 30 21:26:30 +0000 2012","utc_offset":-10800,"time_zone":"Atlantic Time (Canada)","geo_enabled":true,"lang":"en","contributors_enabled":false,"is_translator":false,"profile_background_color":"C0DEED","profile_background_image_url":"http:\/\/pbs.twimg.com\/profile_background_images\/773304539\/94dbc3d1558da7f1e3d2c6fffcb5d710.jpeg","profile_background_image_url_https":"https:\/\/pbs.twimg.com\/profile_background_images\/773304539\/94dbc3d1558da7f1e3d2c6fffcb5d710.jpeg","profile_background_tile":true,"profile_link_color":"0084B4","profile_sidebar_border_color":"FFFFFF","profile_sidebar_fill_color":"DDEEF6","profile_text_color":"333333","profile_use_background_image":true,"profile_image_url":"http:\/\/pbs.twimg.com\/profile_images\/714669878012219392\/9HmilvPG_normal.jpg","profile_image_url_https":"https:\/\/pbs.twimg.com\/profile_images\/714669878012219392\/9HmilvPG_normal.jpg","profile_banner_url":"https:\/\/pbs.twimg.com\/profile_banners\/792436550\/1458855437","default_profile":false,"default_profile_image":false,"following":null,"follow_request_sent":null,"notifications":null},"geo":null,"coordinates":null,"place":null,"contributors":null,"is_quote_status":false,"retweet_count":2,"favorite_count":7,"entities":{"hashtags":[],"urls":[],"user_mentions":[],"symbols":[]},"favorited":false,"retweeted":false,"filter_level":"low","lang":"en"},"is_quote_status":false,"retweet_count":0,"favorite_count":0,"entities":{"hashtags":[],"urls":[],"user_mentions":[{"screen_name":"whosharold","name":"sadboyz","id":792436550,"id_str":"792436550","indices":[3,14]}],"symbols":[]},"favorited":false,"retweeted":false,"filter_level":"low","lang":"en","timestamp_ms":"1459931635353"}
{"created_at":"Wed Apr 06 08:33:55 +0000 2016","id":717631409742020609,"id_str":"717631409742020609","text":"RT @WisegalGranny: HONY Just Destroyed Donald Trump\u2019s Dream Of Becoming President - https:\/\/t.co\/8GIDVa76bZ Oooo, that's gonna hurt! #Unite\u2026","source":"\u003ca href=\"https:\/\/roundteam.co\" rel=\"nofollow\"\u003eRoundTeam\u003c\/a\u003e","truncated":false,"in_reply_to_status_id":null,"in_reply_to_status_id_str":null,"in_reply_to_user_id":null,"in_reply_to_user_id_str":null,"in_reply_to_screen_name":null,"user":{"id":2846552432,"id_str":"2846552432","name":"Glenn Silva","screen_name":"GlennSilva76","location":"hawaii","url":null,"description":"Christian, Constitutional Conservative, Pro 1A 2A and RF, It's Time To Unite And Take Our Country Back! #NeverTrump\r\n#UniteWithCruz #CruzCrew #CruzToVictory","protected":false,"verified":false,"followers_count":1981,"friends_count":2408,"listed_count":99,"favourites_count":1819,"statuses_count":38301,"created_at":"Wed Oct 08 07:34:50 +0000 2014","utc_offset":null,"time_zone":null,"geo_enabled":false,"lang":"en","contributors_enabled":false,"is_translator":false,"profile_background_color":"C0DEED","profile_background_image_url":"http:\/\/abs.twimg.com\/images\/themes\/theme1\/bg.png","profile_background_image_url_https":"https:\/\/abs.twimg.com\/images\/themes\/theme1\/bg.png","profile_background_tile":false,"profile_link_color":"0084B4","profile_sidebar_border_color":"C0DEED","profile_sidebar_fill_color":"DDEEF6","profile_text_color":"333333","profile_use_background_image":true,"profile_image_url":"http:\/\/pbs.twimg.com\/profile_images\/691834454868889601\/1gkIbY1C_normal.jpg","profile_image_url_https":"https:\/\/pbs.twimg.com\/profile_images\/691834454868889601\/1gkIbY1C_normal.jpg","profile_banner_url":"https:\/\/pbs.twimg.com\/profile_banners\/2846552432\/1453447926","default_profile":true,"default_profile_image":false,"following":null,"follow_request_sent":null,"notifications":null},"geo":null,"coordinates":null,"place":null,"contributors":null,"retweeted_status":{"created_at":"Wed Apr 06 08:18:04 +0000 2016","id":717627418454966272,"id_str":"717627418454966272","text":"HONY Just Destroyed Donald Trump\u2019s Dream Of Becoming President - https:\/\/t.co\/8GIDVa76bZ Oooo, that's gonna hurt! #UniteWithCruz #NeverTrump","source":"\u003ca href=\"http:\/\/twitter.com\" rel=\"nofollow\"\u003eTwitter Web Client\u003c\/a\u003e","truncated":false,"in_reply_to_status_id":null,"in_reply_to_status_id_str":null,"in_reply_to_user_id":null,"in_reply_to_user_id_str":null,"in_reply_to_screen_name":null,"user":{"id":4726275950,"id_str":"4726275950","name":"Wisegal1958","screen_name":"WisegalGranny","location":null,"url":null,"description":null,"protected":false,"verified":false,"followers_count":475,"friends_count":290,"listed_count":73,"favourites_count":8976,"statuses_count":10881,"created_at":"Fri Jan 08 02:36:28 +0000 2016","utc_offset":null,"time_zone":null,"geo_enabled":false,"lang":"en","contributors_enabled":false,"is_translator":false,"profile_background_color":"F5F8FA","profile_background_image_url":"","profile_background_image_url_https":"","profile_background_tile":false,"profile_link_color":"2B7BB9","profile_sidebar_border_color":"C0DEED","profile_sidebar_fill_color":"DDEEF6","profile_text_color":"333333","profile_use_background_image":true,"profile_image_url":"http:\/\/pbs.twimg.com\/profile_images\/715082668770242561\/ohjXvK85_normal.jpg","profile_image_url_https":"https:\/\/pbs.twimg.com\/profile_images\/715082668770242561\/ohjXvK85_normal.jpg","default_profile":true,"default_profile_image":false,"following":null,"follow_request_sent":null,"notifications":null},"geo":null,"coordinates":null,"place":null,"contributors":null,"is_quote_status":false,"retweet_count":1,"favorite_count":0,"entities":{"hashtags":[{"text":"UniteWithCruz","indices":[114,128]},{"text":"NeverTrump","indices":[129,140]}],"urls":[{"url":"https:\/\/t.co\/8GIDVa76bZ","expanded_url":"http:\/\/www.parhlo.com\/hony-just-destroyed-trumps-dream-of-becoming-president\/?track=twb","display_url":"parhlo.com\/hony-just-dest\u2026","indices":[65,88]}],"user_mentions":[],"symbols":[]},"favorited":false,"retweeted":false,"possibly_sensitive":false,"filter_level":"low","lang":"en"},"is_quote_status":false,"retweet_count":0,"favorite_count":0,"entities":{"hashtags":[{"text":"UniteWithCruz","indices":[133,140]},{"text":"NeverTrump","indices":[139,140]}],"urls":[{"url":"https:\/\/t.co\/8GIDVa76bZ","expanded_url":"http:\/\/www.parhlo.com\/hony-just-destroyed-trumps-dream-of-becoming-president\/?track=twb","display_url":"parhlo.com\/hony-just-dest\u2026","indices":[84,107]}],"user_mentions":[{"screen_name":"WisegalGranny","name":"Wisegal1958","id":4726275950,"id_str":"4726275950","indices":[3,17]}],"symbols":[]},"favorited":false,"retweeted":false,"possibly_sensitive":false,"filter_level":"low","lang":"en","timestamp_ms":"1459931635686"}
Please help me. Thank you.
