Skip to content

UnicodeDecodeError: 'ascii' codec can't decode byte 0xe2 in position 11: ordinal not in range(128) #77

Description

@timini

File "/home/tim/Workspace/Development/hacks/pressmonitor/pressmon/articles/management/commands/collect_articles.py", line 27, in handle
article.nlp()
File "/home/tim/.virtualenvs/pressmon/lib/python2.7/site-packages/newspaper/article.py", line 307, in nlp
summary_sents = nlp.summarize(title=self.title, text=self.text)
File "/home/tim/.virtualenvs/pressmon/lib/python2.7/site-packages/newspaper/nlp.py", line 34, in summarize
sentences = split_sentences(text)
File "/home/tim/.virtualenvs/pressmon/lib/python2.7/site-packages/newspaper/nlp.py", line 146, in split_sentences
sentences = tokenizer.tokenize(text)
File "/home/tim/.virtualenvs/pressmon/lib/python2.7/site-packages/nltk/tokenize/punkt.py", line 1270, in tokenize
return list(self.sentences_from_text(text, realign_boundaries))
File "/home/tim/.virtualenvs/pressmon/lib/python2.7/site-packages/nltk/tokenize/punkt.py", line 1318, in sentences_from_text
return [text[s:e] for s, e in self.span_tokenize(text, realign_boundaries)]
File "/home/tim/.virtualenvs/pressmon/lib/python2.7/site-packages/nltk/tokenize/punkt.py", line 1309, in span_tokenize
return [(sl.start, sl.stop) for sl in slices]
File "/home/tim/.virtualenvs/pressmon/lib/python2.7/site-packages/nltk/tokenize/punkt.py", line 1348, in _realign_boundaries
for sl1, sl2 in _pair_iter(slices):
File "/home/tim/.virtualenvs/pressmon/lib/python2.7/site-packages/nltk/tokenize/punkt.py", line 355, in _pair_iter
for el in it:
File "/home/tim/.virtualenvs/pressmon/lib/python2.7/site-packages/nltk/tokenize/punkt.py", line 1324, in _slices_from_text
if self.text_contains_sentbreak(context):
File "/home/tim/.virtualenvs/pressmon/lib/python2.7/site-packages/nltk/tokenize/punkt.py", line 1369, in text_contains_sentbreak
for t in self._annotate_tokens(self._tokenize_words(text)):
File "/home/tim/.virtualenvs/pressmon/lib/python2.7/site-packages/nltk/tokenize/punkt.py", line 1504, in _annotate_second_pass
for t1, t2 in _pair_iter(tokens):
File "/home/tim/.virtualenvs/pressmon/lib/python2.7/site-packages/nltk/tokenize/punkt.py", line 354, in _pair_iter
prev = next(it)
File "/home/tim/.virtualenvs/pressmon/lib/python2.7/site-packages/nltk/tokenize/punkt.py", line 621, in _annotate_first_pass
for aug_tok in tokens:
File "/home/tim/.virtualenvs/pressmon/lib/python2.7/site-packages/nltk/tokenize/punkt.py", line 586, in _tokenize_words
for line in plaintext.split('\n'):
UnicodeDecodeError: 'ascii' codec can't decode byte 0xe2 in position 11: ordinal not in range(128)

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions