def extract_bleach(text):
"""Extract tags from text in a form suitable for bleach."""
extractor = MarkupExtractor()
parser = HTMLParser(collect_ids=False, target=extractor)
parser.feed(text)
return {
"tags": extractor.found_tags,
"attributes": extractor.found_attributes
}
def parse_html(name, html):
"""
Parse the provided html to find a dataset
"""
parser = HTMLParser(encoding="UTF-8")
try:
parser.feed(html)
dom = parser.close()
except:
return {}
dataset = {
u'name': name,
u'title': get_title(dom),
u'notes': get_notes(dom),
u'owner_org': get_owner_org(dom),
u'resources': parse_resources(dom),
}
dataset.update(get_extra_meta(dom))
return dataset
def dm_to_html_v2(dmtext, klass=DMWalkState, tag=None):
mark = str(uuid.uuid4())
dmtext, has_blinds = fix_tags(dmtext)
p = HTMLParser()
p.feed(f"<div id='{mark}'>".encode("ascii"))
p.feed(dmtext)
p.feed(b"</div>")
doc = p.close()
root = doc.find(f".//div[@id = '{mark}']")
synth_root = klass(for_region=tag)
synth_root.ingest_element(root)
return synth_root
def dm_to_html(dmtext, tag=None):
mark = str(uuid.uuid4())
dmtext, has_blinds = fix_tags(dmtext)
p = HTMLParser()
p.feed(f"<div id='{mark}'>".encode("ascii"))
p.feed(dmtext)
p.feed(b"</div>")
doc = p.close()
root = doc.find(f".//div[@id = '{mark}']")
synth_root = DMWalkState(for_region=tag)
synth_root.ingest_element(root)
text = synth_root.get_html()
if has_blinds:
text = FIX_BLIND_TIMESTAMP_CODES.sub(fix_blind_ts, text)
return (
text,
list(synth_root.card_master_references) or None,
list(synth_root.image_references) or None,
)