収集した文章が表示されない

リアルタイムで収集したツイートから、url, 返信, RTを除去した後にリスト内の重複を削除したものを表示しようとしたら、以下のエラーが出ました。

解決に向けてお知恵をお貸しいただけますと幸いです。宜しくお願いします。

エラー

Traceback (most recent call last):
  File "honban.py", line 149, in <module>
    stream.sample()
  File "/Users/macuser/Workspaces/jxpress/trendword/.direnv/python-3.7.3/lib/python3.7/site-packages/tweepy/streaming.py", line 449, in sample
    self._start(is_async)
  File "/Users/macuser/Workspaces/jxpress/trendword/.direnv/python-3.7.3/lib/python3.7/site-packages/tweepy/streaming.py", line 389, in _start
    self._run()
  File "/Users/macuser/Workspaces/jxpress/trendword/.direnv/python-3.7.3/lib/python3.7/site-packages/tweepy/streaming.py", line 320, in _run
    six.reraise(*exc_info)
  File "/Users/macuser/Workspaces/jxpress/trendword/.direnv/python-3.7.3/lib/python3.7/site-packages/six.py", line 693, in reraise
    raise value
  File "/Users/macuser/Workspaces/jxpress/trendword/.direnv/python-3.7.3/lib/python3.7/site-packages/tweepy/streaming.py", line 289, in _run
    self._read_loop(resp)
  File "/Users/macuser/Workspaces/jxpress/trendword/.direnv/python-3.7.3/lib/python3.7/site-packages/tweepy/streaming.py", line 351, in _read_loop
    self._data(next_status_obj)
  File "/Users/macuser/Workspaces/jxpress/trendword/.direnv/python-3.7.3/lib/python3.7/site-packages/tweepy/streaming.py", line 323, in _data
    if self.listener.on_data(data) is False:
  File "/Users/macuser/Workspaces/jxpress/trendword/.direnv/python-3.7.3/lib/python3.7/site-packages/tweepy/streaming.py", line 54, in on_data
    if self.on_status(status) is False:
  File "honban.py", line 70, in on_status
    for i in corpus :
UnboundLocalError: local variable 'corpus' referenced before assignment

コード

renshu.py
1#上記省略
2    def on_status(self, status):
3        text = str(status.text)
4        
5#日本語ツイートをファイルに書き込んでいる + ツイートの数を表示
6        if status.lang == "ja":
7            with open("testd.txt", "a", encoding="utf-8") as f:
8                f.write(text)
9            with codecs.open("testd.txt", "r", "utf-8") as f:
10                num_lines = sum(1 for line in open("testd.txt"))#総文書数
11                corpus = f.read().split("\n")
12            if len(text) != 0:
13                self.count += 1
14
15        mecab = MeCab('-d /usr/local/lib/mecab/dic/mecab-ipadic-neologd')
16
17        stop_words = []
18        path = 'stop_words.txt'
19        with open(path) as g:
20            stop_words = g.readlines()
21
22        texts=[]
23        for i in corpus:
24            texts.append(re.sub(r"http\S+", "", i))
25            texts.append(re.sub(r"@(\w+) ", "", i))
26            texts.append(re.sub(r"(^RT.*)", "", i, flags=re.MULTILINE | re.DOTALL))
27            emoji_pattern = re.compile("["
28            u"\U0001F600-\U0001F64F"
29            u"\U0001F300-\U0001F5FF"
30            u"\U0001F680-\U0001F6FF"
31            u"\U0001F1E0-\U0001F1FF"
32            "]+", flags=re.UNICODE)
33            texts.append(emoji_pattern.sub("", i))
34        texts.append(i)
35        text = list(set(texts))
36        print(text)