在将数据写入CSV文件时获取编码错误

Question

from tweetpy import *
import re
import json
from pprint import pprint
import csv
# Import the necessary methods from "twitter" library
from twitter import Twitter, OAuth, TwitterHTTPError, TwitterStream
# Variables that contains the user credentials to access Twitter API
ACCESS_TOKEN =  ''
ACCESS_SECRET = ''
CONSUMER_KEY = ''
CONSUMER_SECRET = ''
oauth = OAuth(ACCESS_TOKEN, ACCESS_SECRET, CONSUMER_KEY, CONSUMER_SECRET)
# Initiate the connection to Twitter Streaming API
twitter_stream = TwitterStream(auth=oauth)
# Get a sample of the public data following through Twitter
iterator = twitter_stream.statuses.filter(track="#kindle",language="en",replies="all")
 # Print each tweet in the stream to the screen
 # Here we set it to stop after getting 10000000 tweets.
 # You don't have to set it to stop, but can continue running
 # the Twitter API to collect data for days or even longer.
tweet_count = 10000000
file = "C:\Users\WELCOME\Desktop\twitterfeeds.csv"
with open(file,"w") as csvfile:
    fieldnames=['Username','Tweet','Timezone','Timestamp','Location']
    writer = csv.DictWriter(csvfile, fieldnames=fieldnames)
    writer.writeheader()
    for tweet in iterator:
        #pprint(tweet)
        username = str(tweet['user']['screen_name'])
        tweet_text = str(tweet['text'])
        user_timezone = str(tweet['user']['time_zone'])
        tweet_timestamp=str(tweet['created_at'])
        user_location = str(tweet['user']['location'])
        print tweet
        tweet_count -= 1
        writer.writerow({'Username':username,'Tweet':tweet_text,'Timezone':user_timezone,'Location':user_location,'Timestamp':tweet_timestamp})
        if tweet_count <= 0:
            break

我试图用列'username'，'Tweet'，'Timezone'，'Location'和'Timestamp'。

但是我收到以下错误：

tweet_text = str(tweet['text'])
UnicodeEncodeError: 'ascii' codec can't encode character u'u2026' in position 139: ordinal not in range(128).

我知道它是编码问题

1. 使用Python 3，因为Python 2 csv模块不能很好地编码。
2. 与encoding和newline选项一起使用open。
3. 删除str转换(在Python 3 str中已经是Unicode字符串。

结果：

with open(file,"w",encoding='utf8',newline='') as csvfile:
    fieldnames=['Username','Tweet','Timezone','Timestamp','Location']
    writer = csv.DictWriter(csvfile, fieldnames=fieldnames)
    writer.writeheader()
    for tweet in iterator:
        username = tweet['user']['screen_name']
        tweet_text = tweet['text']
        user_timezone = tweet['user']['time_zone']
        tweet_timestamp = tweet['created_at']
        user_location = tweet['user']['location']
            .
            .
            .

如果使用Python 2，请获取第三方unicodecsv模块克服csv缺点。

如果您真的想转换所有Unicode数据

tweet['text'].encode("ascii", "replace")
or
tweet['text'].encode("ascii", "ignore") # if you want skip char