dmoonfire/dosage
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Activity

Make tagre quote configurable.

Browse source
This commit is contained in:
Bastian Kleineidam 2012-10-11 15:43:29 +02:00
parent a63c66d737
commit 17a40d4fda
1 changed files with 7 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

9
dosagelib/util.py
View file

@ -23,7 +23,7 @@ has_curses = has_module("curses")
MAX_FILESIZE = 1024*1024*1 # 1MB MAX_FILESIZE = 1024*1024*1 # 1MB
def tagre(tag, attribute, value): def tagre(tag, attribute, value, quote='"'):
"""Return a regular expression matching the given HTML tag, attribute """Return a regular expression matching the given HTML tag, attribute
and value. It matches the tag and attribute names case insensitive, and value. It matches the tag and attribute names case insensitive,
and skips arbitrary whitespace and leading HTML attributes. The "<>" at and skips arbitrary whitespace and leading HTML attributes. The "<>" at
@ -34,6 +34,8 @@ def tagre(tag, attribute, value):
@ptype attribute: string @ptype attribute: string
@param value: the attribute value @param value: the attribute value
@ptype value: string @ptype value: string
@param quote: the attribute quote (default ")
@ptype quote: string
@return: the generated regular expression suitable for re.compile() @return: the generated regular expression suitable for re.compile()
@rtype: string @rtype: string
""" """
@ -41,8 +43,9 @@ def tagre(tag, attribute, value):
tag=case_insensitive_re(tag), tag=case_insensitive_re(tag),
attribute=case_insensitive_re(attribute), attribute=case_insensitive_re(attribute),
value=value, value=value,
quote=quote,
) )
return r'<\s*%(tag)s[^>]*\s+%(attribute)s\s*=\s*"%(value)s"[^>]*/?>' % attrs return r'<\s*%(tag)s\s+[^>]*%(attribute)s\s*=\s*%(quote)s%(value)s%(quote)s[^>]*>' % attrs
def case_insensitive_re(name): def case_insensitive_re(name):
@ -101,6 +104,8 @@ def fetchUrls(url, imageSearch, prevSearch=None):
out.write('matched previous URL %r' % prevUrl, 2) out.write('matched previous URL %r' % prevUrl, 2)
prevUrl = urlparse.urljoin(baseUrl, prevUrl) prevUrl = urlparse.urljoin(baseUrl, prevUrl)
else: else:
print data
out.write('no previous URL %s at %s' % (prevSearch.pattern, url), 2)
prevUrl = None prevUrl = None
return imageUrls, prevUrl return imageUrls, prevUrl
return imageUrls return imageUrls