Question

我想将一个表存储在csv文件中，其中包含一行和两个变量： Variable one应为平均Polarity score，Variable two应为平均Subjectivity score

我收到错误：

"UnicodeEncodeError: 'ascii' codec can't encode character u'\u2026' in position 102: ordinal not in range(128)"
tweet.encode("utf-8")

这是print r生成的输出（Bellow，你可以看到我的代码）

Collecting tweets...
Done!
[[u'TILRobot', 'N/A', u'Source: U8\n\n(h/t &gt;&gt; htVs)\n\n#Japan w', 'No', '18:08', '11-09-2017', 103, 0.0, 0.0], [u'Rainmaker1973', u'Italy, North by Northwest', u'RT @Rainmaker1973: Happy 80th #birthday to Bob Crippen, former astronaut &amp; pilot of the first Space Shuttle flight \u2026', 'Yes', '18:07', '11-09-2017', 143, 0.35000000000000003, 0.4444444444444444], [u'_lanzz_', u'London', u"@Wicknes007\nBut yeah, she wasn't a looker, so probably deserves to have a few laughs at her\u2026", 'No', '18:05', '11-09-2017', 140, -0.2, 0.1]]

代码：

import tweepy
from textblob import TextBlob
import csv

def main(query, size):

    # Enter your Twitter credentials below

    consumer_key = ''
    consumer_secret = ''

    access_token = ''
    access_token_secret = ''

    auth = tweepy.OAuthHandler(consumer_key, consumer_secret)
    auth.set_access_token(access_token, access_token_secret)

    # Authenticates with Twitter

    api = tweepy.API(auth, wait_on_rate_limit=True)

    print("Collecting tweets...")

    tweets_array = []

    # Iterates through the collected Tweets and extracts the required info before appending them to an array

    for tweet in tweepy.Cursor(api.search,
                               q=query,
                               result_type="recent",
                               lang="en").items(size):
        userid = api.get_user(tweet.user.id)
        username = userid.screen_name

        if tweet.user.location:
            location = tweet.user.location
        else:
            location = "N/A"

        tweetText = tweet.text

        length = len(tweetText)

        analysis = TextBlob(tweet.text)
        polarity = analysis.sentiment.polarity
        subjectivity = analysis.sentiment.subjectivity

        datestamp = tweet.created_at
        time = datestamp.strftime("%H:%M")
        year = datestamp.strftime("%d-%m-%Y")

        if ('RT @' in tweet.text):
            retweet = "Yes"
        else:
            retweet = "No"

        tweets_array.append([username, location, tweetText, retweet, time, year, length, polarity, subjectivity])

    print("Done!")

    return tweets_array

def save_to_csv(tweets_list):
    print('Saving to CSV')

    # Writes out the tweets array to a CSV file

    with open("Twitter_Sentiment.csv", "wb") as f:
        writer = csv.DictWriter(f, fieldnames=["Username", "Location", "Tweet", "Retweet", "Time", "Year", "Length", "polarity", "subjectivity"], delimiter='|')
        writer.writeheader()
        writer = csv.writer(f, delimiter='|')
        writer.writerows(tweets_list)


if __name__ == '__main__':
    try:
        tweets_list = main("Wikipedia.org Twitter", 200)
        save_to_csv(tweets_list)

    except KeyboardInterrupt:
        print("Bye!")

writer.writerows（tweets_list）UnicodeEncodeError：＆＃39; ascii＆＃39;编解码器无法编码

0 个答案: