Check image urls using python-markdown
One approach would be to intercept the <img>
node at a lower level just after Markdown parses and constructs it:
import re
from markdown import Markdown
from markdown.inlinepatterns import ImagePattern, IMAGE_LINK_RE
RE_REMOTEIMG = re.compile('^(http|https):.+')
class CheckImagePattern(ImagePattern):
def handleMatch(self, m):
node = ImagePattern.handleMatch(self, m)
# check 'src' to ensure it is local
src = node.attrib.get('src')
if src and RE_REMOTEIMG.match(src):
print 'ILLEGAL:', m.group(9)
# or alternately you could raise an error immediately
# raise ValueError("illegal remote url: %s" % m.group(9))
return node
DATA = '''
![Alt text](/path/to/img.jpg)
![Alt text](http://remote.com/path/to/img.jpg)
'''
mk = Markdown()
# patch in the customized image pattern matcher with url checking
mk.inlinePatterns['image_link'] = CheckImagePattern(IMAGE_LINK_RE, mk)
result = mk.convert(DATA)
print result
Output:
ILLEGAL: http://remote.com/path/to/img.jpg
<p><img alt="Alt text" src="/path/to/img.jpg" />
<img alt="Alt text" src="http://remote.com/path/to/img.jpg" /></p>