无法下载 Niek Sanders 的 Twitter 情绪语料库

Question

我正在关注有关 Twitter 情绪分析的教程。我已经在http://www.sananalytics.com/lab/twitter-sentiment/ 下载了代码。我按照步骤从 cmd 提示符运行 install.py，虽然它确实在“rawdata”文件夹中创建了 json 文件，但当我查看这些 json 文件时，它说：

{
    "errors": [
        {
            "message": "SSL is required",
            "code": 92
        }
    ]
}

install.py代码如下：

#
# Sanders-Twitter Sentiment Corpus Install Script
# Version 0.1
#
# Pulls tweet data from Twitter because ToS prevents distributing it directly.
#
# Right now we use unauthenticated requests, which are rate-limited to 150/hr.
# We use 125/hr to stay safe.  
#
# We could more than double the download speed by using authentication with
# OAuth logins.  But for now, this is too much of a PITA to implement.  Just let
# the script run over a weekend and you'll have all the data.
#
#   - Niek Sanders
#     njs@sananalytics.com
#     October 20, 2011
#
#
# Excuse the ugly code.  I threw this together as quickly as possible and I
# don't normally code in Python.
#
import csv, getpass, json, os, time, urllib


def get_user_params():

    user_params = {}

    # get user input params
    user_params['inList']  = raw_input( '\nInput file [./corpus.csv]: ' )
    user_params['outList'] = raw_input( 'Results file [./full-corpus.csv]: ' )
    user_params['rawDir']  = raw_input( 'Raw data dir [./rawdata/]: ' )

    # apply defaults
    if user_params['inList']  == '': 
        user_params['inList'] = './corpus.csv'
    if user_params['outList'] == '': 
        user_params['outList'] = './full-corpus.csv'
    if user_params['rawDir']  == '': 
        user_params['rawDir'] = './rawdata/'

    return user_params


def dump_user_params( user_params ):

    # dump user params for confirmation
    print 'Input:    '   + user_params['inList']
    print 'Output:   '   + user_params['outList']
    print 'Raw data: '   + user_params['rawDir']
    return


def read_total_list( in_filename ):

    # read total fetch list csv
    fp = open( in_filename, 'rb' )
    reader = csv.reader( fp, delimiter=',', quotechar='"' )

    total_list = []
    for row in reader:
        total_list.append( row )

    return total_list


def purge_already_fetched( fetch_list, raw_dir ):

    # list of tweet ids that still need downloading
    rem_list = []

    # check each tweet to see if we have it
    for item in fetch_list:

        # check if json file exists
        tweet_file = raw_dir + item[2] + '.json'
        if os.path.exists( tweet_file ):

            # attempt to parse json file
            try:
                parse_tweet_json( tweet_file )
                print '--> already downloaded #' + item[2]
            except RuntimeError:
                rem_list.append( item )
        else:
            rem_list.append( item )

    return rem_list


def get_time_left_str( cur_idx, fetch_list, download_pause ):

    tweets_left = len(fetch_list) - cur_idx
    total_seconds = tweets_left * download_pause

    str_hr = int( total_seconds / 3600 )
    str_min = int((total_seconds - str_hr*3600) / 60)
    str_sec = total_seconds - str_hr*3600 - str_min*60

    return '%dh %dm %ds' % (str_hr, str_min, str_sec)


def download_tweets( fetch_list, raw_dir ):

    # ensure raw data directory exists
    if not os.path.exists( raw_dir ):
        os.mkdir( raw_dir )

    # stay within rate limits
    max_tweets_per_hr  = 125
    download_pause_sec = 3600 / max_tweets_per_hr

    # download tweets
    for idx in range(0,len(fetch_list)):

        # current item
        item = fetch_list[idx]

        # print status
        trem = get_time_left_str( idx, fetch_list, download_pause_sec )
        print '--> downloading tweet #%s (%d of %d) (%s left)' % \
              (item[2], idx+1, len(fetch_list), trem)

        # pull data
        url = 'http://api.twitter.com/1/statuses/show.json?id=' + item[2]
        urllib.urlretrieve( url, raw_dir + item[2] + '.json' )

        # stay in Twitter API rate limits 
        print '    pausing %d sec to obey Twitter API rate limits' % \
              (download_pause_sec)
        time.sleep( download_pause_sec )

    return


def parse_tweet_json( filename ):

    # read tweet
    print 'opening: ' + filename
    fp = open( filename, 'rb' )

    # parse json
    try:
        tweet_json = json.load( fp )
    except ValueError:
        raise RuntimeError('error parsing json')

    # look for twitter api error msgs
    if 'error' in tweet_json:
        raise RuntimeError('error in downloaded tweet')

    # extract creation date and tweet text
    return [ tweet_json['created_at'], tweet_json['text'] ]


def build_output_corpus( out_filename, raw_dir, total_list ):

    # open csv output file
    fp = open( out_filename, 'wb' )
    writer = csv.writer( fp, delimiter=',', quotechar='"', escapechar='\\',
                         quoting=csv.QUOTE_ALL )

    # write header row
    writer.writerow( ['Topic','Sentiment','TweetId','TweetDate','TweetText'] )

    # parse all downloaded tweets
    missing_count = 0
    for item in total_list:

        # ensure tweet exists
        if os.path.exists( raw_dir + item[2] + '.json' ):

            try: 
                # parse tweet
                parsed_tweet = parse_tweet_json( raw_dir + item[2] + '.json' )
                full_row = item + parsed_tweet

                # character encoding for output
                for i in range(0,len(full_row)):
                    full_row[i] = full_row[i].encode("utf-8")

                # write csv row
                writer.writerow( full_row )

            except RuntimeError:
                print '--> bad data in tweet #' + item[2]
                missing_count += 1

        else:
            print '--> missing tweet #' + item[2]
            missing_count += 1

    # indicate success
    if missing_count == 0:
        print '\nSuccessfully downloaded corpus!'
        print 'Output in: ' + out_filename + '\n'
    else: 
        print '\nMissing %d of %d tweets!' % (missing_count, len(total_list))
        print 'Partial output in: ' + out_filename + '\n'

    return


def main():

    # get user parameters
    user_params = get_user_params()
    dump_user_params( user_params )

    # get fetch list
    total_list = read_total_list( user_params['inList'] )
    fetch_list = purge_already_fetched( total_list, user_params['rawDir'] )

    # start fetching data from twitter
    download_tweets( fetch_list, user_params['rawDir'] )

    # second pass for any failed downloads
    print '\nStarting second pass to retry any failed downloads';
    fetch_list = purge_already_fetched( total_list, user_params['rawDir'] )
    download_tweets( fetch_list, user_params['rawDir'] )

    # build output corpus
    build_output_corpus( user_params['outList'], user_params['rawDir'], 
                         total_list )

    return


if __name__ == '__main__':
    main()

Answer 1

对于任何其他谨慎的旅行者......

我注意到 KubiK888 没有链接他找到更新代码的位置。

A) 这是我在 github 上找到的 CSV 的完整上传 - https://raw.githubusercontent.com/zfz/twitter_corpus/master/full-corpus.csv

似乎有全部 6000 多条推文，在删除“不相关”推文后，它有 3000 多条观察结果。

B) 或者，这里是一个包含完整代码的存储库，其中有人更新了 Nick Sanders 的原始 0.1 版本以支持 twitter API 1.1（包括 oAUTH）

https://github.com/aweiand/TwitterSentiment/blob/71c007948b8fb854b1df0b2a3a32d2629653e74b/GetTwitterCorpus/getTweets.py

它还有各种格式的完整语料库： https://github.com/aweiand/TwitterSentiment/tree/71c007948b8fb854b1df0b2a3a32d2629653e74b/GetTwitterCorpus

Answer 2

显然，我发布的仍然在他们网站上的代码已经过时了。我从 Github 找到了更新的版本如下：

# This code is supporting material for the book
# Building Machine Learning Systems with Python
# by Willi Richert and Luis Pedro Coelho
# published by PACKT Publishing
#
# It is made available under the MIT License

#
# Sanders-Twitter Sentiment Corpus Install Script
# Version 0.1
#
# Pulls tweet data from Twitter because ToS prevents distributing it directly.
#
#   - Niek Sanders
#     njs@sananalytics.com
#     October 20, 2011
#
#

# In Sanders' original form, the code was using Twitter API 1.0.
# Now that Twitter moved to 1.1, we had to make a few changes.
# Cf. twitterauth.py for the details.

# Regarding rate limiting, please check
# https://dev.twitter.com/rest/public/rate-limiting

import sys
import csv
import json
import os
import time

try:
    import twitter
except ImportError:
    print("""\
You need to ...
    pip install twitter
If pip is not found you might have to install it using easy_install.
If it does not work on your system, you might want to follow instructions
at https://github.com/sixohsix/twitter, most likely:
  $ git clone https://github.com/sixohsix/twitter
  $ cd twitter
  $ sudo python setup.py install
""")

    sys.exit(1)

ckey = "xxxxx"
csecret = "xxxxx"
atoken = "xxxxx"
asecret = "xxxxx"

api = twitter.Twitter(auth=twitter.OAuth(consumer_key=ckey, consumer_secret=csecret,
                                         token=atoken, token_secret=asecret))

DATA_PATH = "data"

# for some reasons TWeets disappear. In this file we collect those
MISSING_ID_FILE = os.path.join(DATA_PATH, "missing.tsv")
NOT_AUTHORIZED_ID_FILE = os.path.join(DATA_PATH, "not_authorized.tsv")


def get_user_params(DATA_PATH):

    user_params = {}

    # get user input params
    user_params['inList'] = os.path.join(DATA_PATH, 'corpus.csv')
    user_params['outList'] = os.path.join(DATA_PATH, 'full-corpus.csv')
    user_params['rawDir'] = os.path.join(DATA_PATH, 'rawdata/')

    # apply defaults
    if user_params['inList'] == '':
        user_params['inList'] = './corpus.csv'
    if user_params['outList'] == '':
        user_params['outList'] = './full-corpus.csv'
    if user_params['rawDir'] == '':
        user_params['rawDir'] = './rawdata/'

    return user_params


def dump_user_params(user_params):

    # dump user params for confirmation
    print('Input:    ' + user_params['inList'])
    print('Output:   ' + user_params['outList'])
    print('Raw data: ' + user_params['rawDir'])


def read_total_list(in_filename):

    # read total fetch list csv
    fp = open(in_filename, 'rt')
    reader = csv.reader(fp, delimiter=',', quotechar='"')

    if os.path.exists(MISSING_ID_FILE):
        missing_ids = [line.strip()
                       for line in open(MISSING_ID_FILE, "r").readlines()]
    else:
        missing_ids = []

    if os.path.exists(NOT_AUTHORIZED_ID_FILE):
        not_authed_ids = [line.strip()
                          for line in open(NOT_AUTHORIZED_ID_FILE, "r").readlines()]
    else:
        not_authed_ids = []

    print("We will skip %i tweets that are not available or visible any more on twitter" % (
        len(missing_ids) + len(not_authed_ids)))

    ignore_ids = set(missing_ids + not_authed_ids)
    total_list = []

    for row in reader:
        if row[2] not in ignore_ids:
            total_list.append(row)

    return total_list


def purge_already_fetched(fetch_list, raw_dir):

    # list of tweet ids that still need downloading
    rem_list = []
    count_done = 0

    # check each tweet to see if we have it
    for item in fetch_list:

        # check if json file exists
        tweet_file = os.path.join(raw_dir, item[2] + '.json')
        if os.path.exists(tweet_file):

            # attempt to parse json file
            try:
                parse_tweet_json(tweet_file)
                count_done += 1
            except RuntimeError:
                print("Error parsing", item)
                rem_list.append(item)
        else:
            rem_list.append(item)

    print("We have already downloaded %i tweets." % count_done)

    return rem_list


def download_tweets(fetch_list, raw_dir):

    # ensure raw data directory exists
    if not os.path.exists(raw_dir):
        os.mkdir(raw_dir)

    # download tweets
    for idx in range(0, len(fetch_list)):
        # current item
        item = fetch_list[idx]
        print(item)

        print('--> downloading tweet #%s (%d of %d)' %
              (item[2], idx + 1, len(fetch_list)))

        try:
            #import pdb;pdb.set_trace()
            response = api.statuses.show(_id=item[2])

            if response.rate_limit_remaining <= 0:
                wait_seconds = response.rate_limit_reset - time.time()
                print("Rate limiting requests us to wait %f seconds" %
                      wait_seconds)
                time.sleep(wait_seconds+5)

        except twitter.TwitterError as e:
            fatal = True
            print(e)
            for m in json.loads(e.response_data.decode())['errors']:
                if m['code'] == 34:
                    print("Tweet missing: ", item)
                    with open(MISSING_ID_FILE, "at") as f:
                        f.write(item[2] + "\n")

                    fatal = False
                    break
                elif m['code'] == 63:
                    print("User of tweet '%s' has been suspended." % item)
                    with open(MISSING_ID_FILE, "at") as f:
                        f.write(item[2] + "\n")

                    fatal = False
                    break
                elif m['code'] == 88:
                    print("Rate limit exceeded.")
                    fatal = True
                    break
                elif m['code'] == 179:
                    print("Not authorized to view this tweet.")
                    with open(NOT_AUTHORIZED_ID_FILE, "at") as f:
                        f.write(item[2] + "\n")
                    fatal = False
                    break

            if fatal:
                raise
            else:
                continue

        with open(raw_dir + item[2] + '.json', "wt") as f:
            f.write(json.dumps(dict(response)) + "\n")

    return


def parse_tweet_json(filename):

    # read tweet
    fp = open(filename, 'r')

    # parse json
    try:
        tweet_json = json.load(fp)
    except ValueError as e:
        print(e)
        raise RuntimeError('error parsing json')

    # look for twitter api error msgs
    if 'error' in tweet_json or 'errors' in tweet_json:
        raise RuntimeError('error in downloaded tweet')

    # extract creation date and tweet text
    return [tweet_json['created_at'], tweet_json['text']]


def build_output_corpus(out_filename, raw_dir, total_list):

    # open csv output file
    fp = open(out_filename, 'wb')
    writer = csv.writer(fp, delimiter=',', quotechar='"', escapechar='\\',
                        quoting=csv.QUOTE_ALL)

    # write header row
    writer.writerow(
        ['Topic', 'Sentiment', 'TweetId', 'TweetDate', 'TweetText'])

    # parse all downloaded tweets
    missing_count = 0
    for item in total_list:

        # ensure tweet exists
        if os.path.exists(raw_dir + item[2] + '.json'):

            try:
                # parse tweet
                parsed_tweet = parse_tweet_json(raw_dir + item[2] + '.json')
                full_row = item + parsed_tweet

                # character encoding for output
                for i in range(0, len(full_row)):
                    full_row[i] = full_row[i].encode("utf-8")

                # write csv row
                writer.writerow(full_row)

            except RuntimeError:
                print('--> bad data in tweet #' + item[2])
                missing_count += 1

        else:
            print('--> missing tweet #' + item[2])
            missing_count += 1

    # indicate success
    if missing_count == 0:
        print('\nSuccessfully downloaded corpus!')
        print('Output in: ' + out_filename + '\n')
    else:
        print('\nMissing %d of %d tweets!' % (missing_count, len(total_list)))
        print('Partial output in: ' + out_filename + '\n')

    return


def main():
    # get user parameters
    user_params = get_user_params(DATA_PATH)
    print(user_params)
    dump_user_params(user_params)

    # get fetch list
    total_list = read_total_list(user_params['inList'])

    # remove already fetched or missing tweets
    fetch_list = purge_already_fetched(total_list, user_params['rawDir'])
    print("Fetching %i tweets..." % len(fetch_list))

    if fetch_list:
        # start fetching data from twitter
        download_tweets(fetch_list, user_params['rawDir'])

        # second pass for any failed downloads
        fetch_list = purge_already_fetched(total_list, user_params['rawDir'])
        if fetch_list:
            print('\nStarting second pass to retry %i failed downloads...' %
                  len(fetch_list))
            download_tweets(fetch_list, user_params['rawDir'])
    else:
        print("Nothing to fetch any more.")

    # build output corpus
    build_output_corpus(user_params['outList'], user_params['rawDir'],
                        total_list)


if __name__ == '__main__':
    main()