async def example(q):
r = await asks.get('https://fr.wikipedia.org/wiki/'+q)
tree = html_text.parse_html(r.text)
cleaned_tree = html_text.cleaner.clean_html(tree)
print(html_text.etree_to_text(cleaned_tree))
f = html_text.etree_to_text(cleaned_tree)
return f
def test_webpages(page, extracted):
html = _load_file(page)
if not six.PY3:
# FIXME: produces '\xa0' in Python 2, but ' ' in Python 3
# this difference is ignored in this test.
# What is the correct behavior?
html = html.replace(' ', ' ')
expected = _load_file(extracted)
assert extract_text(html) == expected
tree = cleaner.clean_html(parse_html(html))
assert etree_to_text(tree) == expected
def _extract_textContent(self, node):
clean_node = cleaner.clean_html(node)
return html_text.etree_to_text(clean_node)