diff options
| author | Leonard Richardson <leonardr@segfault.org> | 2013-10-01 22:15:53 -0400 |
|---|---|---|
| committer | Leonard Richardson <leonardr@segfault.org> | 2013-10-01 22:15:53 -0400 |
| commit | c0de2023544605dc1940e4d24d493a14b5300066 (patch) | |
| tree | 73d5eeba9401dd3a174b7d8dc4aef3f13cbb5e62 /bs4/__init__.py | |
| parent | 6a06b9d998ea9502a93db14ebb65395b20c1b30f (diff) | |
Fixed a crash when a short input contains data not valid in
filenames. [bug=1232604]
Diffstat (limited to 'bs4/__init__.py')
| -rw-r--r-- | bs4/__init__.py | 13 |
1 files changed, 11 insertions, 2 deletions
diff --git a/bs4/__init__.py b/bs4/__init__.py index 6d44c95..341efc6 100644 --- a/bs4/__init__.py +++ b/bs4/__init__.py @@ -164,11 +164,20 @@ class BeautifulSoup(Tag): # involving passing non-markup to Beautiful Soup. # Beautiful Soup will still parse the input as markup, # just in case that's what the user really wants. - if isinstance(markup, unicode): + if (isinstance(markup, unicode) + and not os.path.supports_unicode_filenames): possible_filename = markup.encode("utf8") else: possible_filename = markup - if os.path.exists(possible_filename): + is_file = False + try: + is_file = os.path.exists(possible_filename) + except Exception, e: + # This is almost certainly a problem involving + # characters not valid in filenames on this + # system. Just let it go. + pass + if is_file: warnings.warn( '"%s" looks like a filename, not markup. You should probably open this file and pass the filehandle into Beautiful Soup.' % markup) if markup[:5] == "http:" or markup[:6] == "https:": |