diff options
| author | Jaime Marquínez Ferrándiz <jaime.marquinez.ferrandiz@gmail.com> | 2014-11-02 17:28:42 +0100 |
|---|---|---|
| committer | Jaime Marquínez Ferrándiz <jaime.marquinez.ferrandiz@gmail.com> | 2014-11-02 19:31:06 +0100 |
| commit | 4f195f55f0b734f2897319abf96c5542ce6212d4 (patch) | |
| tree | 0ad95ea47420d7ac5a2101cc37cc792c19d1c9dd | |
| parent | ac35c266868ddfd39f8b708f425e1baf2555e406 (diff) | |
Do not override stdlib html parser 'locatestarttagend' regex (fixes #4081)
'<a href="foo" ><img src="bar" / ></a>' wouldn't be parsed right (the problem is '/ >', '/>' worked fine).
We need to change it in python 2.6 (for example the description of youtube videos wouldn't be extracted).
| -rw-r--r-- | youtube_dl/utils.py | 4 |
1 files changed, 3 insertions, 1 deletions
diff --git a/youtube_dl/utils.py b/youtube_dl/utils.py index 233286de8..bdd637e48 100644 --- a/youtube_dl/utils.py +++ b/youtube_dl/utils.py @@ -152,7 +152,9 @@ def xpath_text(node, xpath, name=None, fatal=False): return n.text -compat_html_parser.locatestarttagend = re.compile(r"""<[a-zA-Z][-.a-zA-Z0-9:_]*(?:\s+(?:(?<=['"\s])[^\s/>][^\s/=>]*(?:\s*=+\s*(?:'[^']*'|"[^"]*"|(?!['"])[^>\s]*))?\s*)*)?\s*""", re.VERBOSE) # backport bugfix +if sys.version_info < (2, 7): + compat_html_parser.locatestarttagend = re.compile(r"""<[a-zA-Z][-.a-zA-Z0-9:_]*(?:\s+(?:(?<=['"\s])[^\s/>][^\s/=>]*(?:\s*=+\s*(?:'[^']*'|"[^"]*"|(?!['"])[^>\s]*))?\s*)*)?\s*""", re.VERBOSE) # backport bugfix + class BaseHTMLParser(compat_html_parser.HTMLParser): def __init(self): compat_html_parser.HTMLParser.__init__(self) |