Parse a Markdown doc using mistune

parse_markdown_images.py

from __future__ import print_function

from collections import namedtuple

from mistune import Markdown

text = """"
# Sample using mistune to parse images from Markdown pages.

* This is a sample image: ![Alt text](/path/to/img.jpg "Optional title")
  * and here's another one: ![foo](http://foo/img.png)
"""

ImageInfo = namedtuple('ImageInfo', ['src', 'title', 'text'])


class ImageCaptureRenderer(object):
  """Implement a partial renderer that only unders image(...) and handles all other methods with a no_op."""

  def __init__(self, **kwargs):
    self.options = kwargs
    self.no_op = lambda *args, **kwargs: ''
    self.clear()

  def clear(self):
    self.images = []

  def image(self, src, title, text):
    self.images.append(ImageInfo(src, title, text))

  def __getattr__(self, name):
    return self.no_op


image_capture = ImageCaptureRenderer()
md = Markdown(renderer=image_capture)
md.parse(text)

for image in image_capture.images:
  print('{}, {}, {}'.format(image.src, image.title, image.text))