fe50f94437
* problem was in trying to remove the outer <html> + </html> tags. * cleaned up the stringify function to be less magical, and more obviously correct. [Fix #35136297]
29 lines
1.0 KiB
Python
29 lines
1.0 KiB
Python
from itertools import chain
|
|
from lxml import etree
|
|
|
|
def stringify_children(node):
|
|
'''
|
|
Return all contents of an xml tree, without the outside tags.
|
|
e.g. if node is parse of
|
|
"<html a="b" foo="bar">Hi <div>there <span>Bruce</span><b>!</b></div><html>"
|
|
should return
|
|
"Hi <div>there <span>Bruce</span><b>!</b></div>"
|
|
|
|
fixed from
|
|
http://stackoverflow.com/questions/4624062/get-all-text-inside-a-tag-in-lxml
|
|
'''
|
|
# Useful things to know:
|
|
|
|
# node.tostring() -- generates xml for the node, including start
|
|
# and end tags. We'll use this for the children.
|
|
# node.text -- the text after the end of a start tag to the start
|
|
# of the first child
|
|
# node.tail -- the text after the end this tag to the start of the
|
|
# next element.
|
|
parts = [node.text]
|
|
for c in node.getchildren():
|
|
parts.append(etree.tostring(c, with_tail=True))
|
|
|
|
# filter removes possible Nones in texts and tails
|
|
return ''.join(filter(None, parts))
|