doc = etk.create_document(sample_html,
mime_type="text/html",
url="http://ex.com/123")
my_table_extractor = TableExtractor()
d = doc.select_segments("$.raw_content")[0]
root = doc.select_segments("$")[0]
tables = doc.invoke_extractor(my_table_extractor, d)
for t in tables:
root.store_extractions([t], t.tag, group_by_tags=False)
table_data_extractor = EntityTableDataExtraction()
table_data_extractor.add_glossary(
etk.load_glossary("./resources/address_dict.txt"), "address")
table_data_extractor.add_glossary(
etk.load_glossary("./resources/calibre_dict.txt"), "caliber")
table_data_extractor.add_glossary(
etk.load_glossary("./resources/capacity_dict.txt"), "capacity")
table_data_extractor.add_glossary(
etk.load_glossary("./resources/manufacturer_dict.txt"), "manufacturer")
table_data_extractor.add_glossary(
etk.load_glossary("./resources/price_dict.txt"), "price")
tables = doc.select_segments("$.tables[*]")
root = doc.select_segments("$")[0]
for t in tables:
extractions = doc.invoke_extractor(table_data_extractor, t)
root.store_extractions(extractions, "table_data_extraction")
"description": "record linkage toolkit, implemented by Pedro, Mayank, Yixiang and several students."
}
],
"members": [
{
"name": "Dongyu Li",
"description": "03/05/2018: I went to USC on Aug 20th, 2016 and will graduate on 2018, May 11. My birthday is 29-04-1994."
}
]
}
etk = ETK()
doc = etk.create_document(sample_input)
# example for glossary extractor:
name_extractor = GlossaryExtractor(etk.load_glossary("./names.txt"), "name_extractor", etk.default_tokenizer, case_sensitive=False, ngrams=1)
descriptions = doc.select_segments("projects[*].description")
projects = doc.select_segments("projects[*]")
for d, p in zip(descriptions, projects):
print ("Iam d path: " + d.full_path)
names = doc.invoke_extractor(name_extractor, d)
p.store_extractions(names, "members")
# example for date extractor:
date_extractor = DateExtractor('test_date_parser')
member_descriptions = doc.select_segments("members[*].description")
members = doc.select_segments("members[*]")
for m_d, m in zip(member_descriptions, members):