I have a ploblem when i test data mining from twitter by i search data by word.
It error UnicodeEncodeError: 'ascii' codec can't encode characters in position 0-2: ordinal not in range(128)
from this code
retweet = "-filter:retweets"
query = "#Thailand" + retweet
df = pd.DataFrame(columns = ["create_at","user","location","text", "retweet_count", "favourite_count","hashtag","follower","source"])
for tweet in tweepy.Cursor(api.search, q = query,result_type="recent", tweet_mode='extended').items(100):
entity_hashtag = tweet.entities.get('hashtags')
hashtag = ""
for i in range(0, len(entity_hashtag)):
hashtag = hashtag + "/" + entity_hashtag[i]["text"]
re_count = tweet.retweet_count
create_at = tweet.created_at
user = tweet.user.screen_name
source = tweet.source
location = tweet.user.location
follower = tweet.user.followers_count
try:
text = tweet.retweeted_status.full_text
fav_count = tweet.retweeted_status.favorite_count
except:
text = tweet.full_text
fav_count = tweet.favorite_count
new_column = pd.Series([create_at,user,location,text, re_count, fav_count,hashtag,follower,source], index = df.columns)
df = df.append(new_column, ignore_index = True)
df.to_csv(date_time+".csv")
Why have this ploblem ?