Walking the parse tree of extracted blocks in Dragnet

dragnet_block_children.py

import requests
from dragnet.models import content_extractor


u = 'https://github.com/seomoz/dragnet'
html = requests.get(u).content

blocks = content_extractor.analyze(html, blocks=True)

block_text = [block.text for block in blocks]

# block.features is a dict with interesting things extracted from the block
start_elements = [block.features['block_start_element'] for block in blocks]

# the first paragraph extracted by dragnet
element = start_elements[0] 
# all child nodes
element.xpath('//p/descendant::*')