Skip to content

Fix parse() raising TypeError on text-mode file-like objects #594

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
afonsojanu wants to merge 1 commit into
base: releases
Choose a base branch
from
Open

Fix parse() raising TypeError on text-mode file-like objects #594

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 4 additions & 1 deletion feedparser/api.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -108,7 +108,10 @@ def _open_resource(url_file_stream_or_string, etag, modified, agent, referrer, h
"""

if hasattr(url_file_stream_or_string, 'read'):
return url_file_stream_or_string.read()
data = url_file_stream_or_string.read()
if not isinstance(data, bytes):
return data.encode('utf-8')
return data

if isinstance(url_file_stream_or_string, str) \
and urllib.parse.urlparse(url_file_stream_or_string)[0] in ('http', 'https', 'ftp', 'file', 'feed'):
Expand Down
16 changes: 16 additions & 0 deletions tests/runtests.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -378,6 +378,22 @@ def test_fileobj(self):
r = feedparser.api._open_resource(io.BytesIO(b''), '', '', '', '', [], {}, {})
self.assertEqual(r, b'')

def test_text_fileobj(self):
"""A text-mode file-like object (e.g. io.StringIO) must come back as bytes.

Everything downstream, starting with convert_to_utf8(), works with
raw bytes and matches against byte regex patterns, so returning the
str data untouched breaks parsing of any text-mode stream.
"""
r = feedparser.api._open_resource(io.StringIO('<feed></feed>'), '', '', '', '', [], {}, {})
self.assertEqual(r, b'<feed></feed>')

def test_parse_text_stringio(self):
text = '<rss version="2.0"><channel><item><title>hello</title></item></channel></rss>'
result = feedparser.parse(io.StringIO(text))
self.assertFalse(result.bozo)
self.assertEqual(result.entries[0].title, 'hello')

def test_feed(self):
f = feedparser.parse('feed://localhost:8097/tests/http/target.xml')
self.assertEqual(f.href, 'http://localhost:8097/tests/http/target.xml')
Expand Down