def record_document_type_and_number(browser, abstract, document):
document_type, reception_number = access_document_type_and_number(
browser, abstract, document)
document.reception_number = reception_number
record_value(abstract, 'document type',
update_sentence_case_extras(title_strip(document_type)))
handle_reception_number(abstract, document)
def record_related_documents(browser, abstract, document):
related_documents_field = locate_element_by_class_name(
browser, abstract.county.record["Related Documents"],
"related documents", False, document)
related_documents = list_to_string(
related_documents_field.text.split('\n')[1:])
record_value(abstract, 'related documents', related_documents)
def record_name_data(abstract, document_table):
grantor_text, grantee_text = access_indexing_information(
abstract, document_table)
grantor = drop_superfluous_information(abstract, grantor_text)
grantee = drop_superfluous_information(abstract, grantee_text)
record_value(abstract, 'grantor', grantor)
record_value(abstract, 'grantee', grantee)
def record_indexing_information(abstract, document_table, document):
recording_date_field = locate_element_by_class_name(
document_table,
abstract.county.classes["Recording Date"],
"recording date",
document=document)
recording_date = date_from_string(recording_date_field.text[:10])
record_value(abstract, 'recording date', recording_date)
def handle_reception_number(abstract, document):
if validate_reception_number(document, document.reception_number):
record_value(abstract, 'reception number', document.reception_number)
else:
print(
f'Reception number "{document.reception_number}" does not match the expected value for '
f'{document.extrapolate_value()}, please review and press enter to continue...'
)
input()
def record_legal(browser, abstract, document):
legal_field = locate_element_by_class_name(browser,
abstract.county.record["Legal"],
"legal", False, document)
legal = list_to_string(legal_field.text.split('\n')[1:])
notes = access_notes(browser, abstract, document)
if notes == '' or notes == ' ':
record_value(abstract, 'legal', legal)
else:
record_value(abstract, 'legal', f'{notes}\n\n{legal}')
def record_parties(browser, abstract, document):
parties_container = locate_element_by_id(browser,
abstract.county.record["Parties"],
"parties", False, document)
parties_text_list = remove_empty_list_items(
parties_container.text.split('\n'))
midpoint = parties_text_list.index('Grantees')
grantor = list(map(title_strip, parties_text_list[1:midpoint]))
grantee = list(map(title_strip, parties_text_list[(midpoint + 1):]))
record_value(abstract, 'grantor', list_to_string(grantor))
record_value(abstract, 'grantee', list_to_string(grantee))
def record_legal_data(abstract, document_table):
table_rows = access_table_rows(abstract, document_table)
legal_data = table_rows[1].find_elements_by_tag_name(
abstract.county.tags["Index Table"][2])
if legal_data == []:
record_value(abstract, 'legal', search_errors[2])
else:
legal = legal_data[-1].text
if legal.endswith(search_errors[4]):
legal = legal.strip() # Running along with test 1
record_value(abstract, 'legal',
drop_superfluous_information(abstract, legal))
def record_legal(abstract, rows):
legal = check_rows(abstract, rows,
abstract.county.titles["Row Titles"]["legal"])
additional_legal = check_rows(
abstract, rows,
abstract.county.titles["Row Titles"]["additional_legal"])
if additional_legal != not_applicable:
if legal == not_applicable:
legal = additional_legal
elif additional_legal != legal:
legal = f'{legal}\n{additional_legal}'
record_value(abstract, 'legal', legal)
def build_document_download_information(browser, abstract, document):
access_download_information(browser, abstract, document)
while document.reception_number.strip() == '':
print('Browser did not correctly access reception number for '
f'{document.extrapolate_value()}, trying again...')
naptime()
access_download_information(browser, abstract, document)
record_value(abstract, 'reception number', document.reception_number)
# Below is necessary until better logic order is figured out for 'handle_document_image_status'
if len(abstract.dataframe['Reception Number']) != len(
abstract.dataframe['Comments']):
record_value(abstract, 'comments', '')
def record_grantee(abstract, rows):
grantee = check_rows(abstract, rows,
abstract.county.titles["Row Titles"]["grantee"])
if grantee == not_applicable:
grantee = check_rows(
abstract, rows,
abstract.county.titles["Row Titles"]["alt_grantee"])
if grantee == not_applicable:
grantee = check_rows(
abstract, rows,
abstract.county.titles["Row Titles"]["second_alt_grantee"])
record_value(abstract, 'grantee', grantee.title())
def record_related_documents(browser, abstract, document_table, document):
# If none then ... ? conditional -- need to test with some print statements to see general feedback first
related_table_rows = get_related_documents_table_rows(
browser, abstract, document_table, document)
related_documents_info = list(
map(partial(access_table_body, abstract=abstract), related_table_rows))
related_document_list = list(
map(access_title_case_text, related_documents_info))
# related_documents_info = list(map(access_table_body, related_table_rows))
# related_document_list = list(map(access_title_case_text, related_documents_info))
related_documents = "\n".join(related_document_list)
record_value(abstract, 'related documents',
drop_superfluous_information(abstract, related_documents))
def aggregate_document_information(abstract, document, rows):
access_reception_number(abstract, document, rows)
record_value(abstract, 'reception number', document.reception_number)
record_book_and_page(abstract, rows)
record_recording_date(abstract, rows)
record_document_type(abstract, rows)
record_grantor(abstract, rows)
record_grantee(abstract, rows)
record_related_documents(abstract, rows)
record_legal(abstract, rows)
record_empty_values(abstract,
['effective date', 'volume', 'document link'])
record_comments(abstract, document)
def record_indexing_data(abstract, document_table, document):
reception_field, recording_date = access_indexing_information(
abstract, document_table)
reception_number, book, page = split_reception_field(reception_field)
reception_number = reception_number.split('\n')[0]
set_document_download_values(abstract, document, reception_number)
record_value(abstract, 'reception number', reception_number)
record_value(abstract, 'book', book)
record_value(abstract, 'page', page)
record_value(abstract, 'recording date', recording_date[:10])
def record_legal(abstract, rows):
legal = check_rows(abstract, rows,
abstract.county.titles["Row Titles"]["legal"])
alt_legal = check_rows(abstract, rows,
abstract.county.titles["Row Titles"]["alt_legal"])
if legal == not_applicable and alt_legal == not_applicable:
record_value(abstract, 'legal', '')
else:
if legal == alt_legal or alt_legal == not_applicable:
record_value(abstract, 'legal', legal)
elif legal == not_applicable:
record_value(abstract, 'legal', alt_legal)
else:
combined_legal = f'{legal}\n{alt_legal}'
record_value(abstract, 'legal', combined_legal)
def record_related_documents(abstract, rows):
related_documents = check_rows(
abstract, rows,
abstract.county.titles["Row Titles"]["related_documents"])
alt_related_documents = check_rows(
abstract, rows,
abstract.county.titles["Row Titles"]["alt_related_documents"])
if related_documents == not_applicable and alt_related_documents == not_applicable:
record_value(abstract, 'related documents', '')
else:
if related_documents == alt_related_documents or alt_related_documents == not_applicable:
record_value(abstract, 'related documents', related_documents)
elif related_documents == not_applicable:
record_value(abstract, 'related documents', alt_related_documents)
else:
combined_related_documents = f'{related_documents}\n{alt_related_documents}'
record_value(abstract, 'related documents',
combined_related_documents)
def record_grantee(abstract, document_table, document):
grantee_text = document_table.text.split('\n')[1:]
grantee_list = list(map(title_strip, grantee_text))
grantee = update_sentence_case_extras(list_to_string(grantee_list))
record_value(abstract, 'grantee', grantee)
def record_book_and_page(abstract, row):
book_page_value = check_rows(
abstract, row, abstract.county.titles["Row Titles"]["book_and_page"])
if book_page_value == 'N/A':
record_value(abstract, 'book', '')
record_value(abstract, 'page', '')
else:
if book_page_value.startswith(abstract.county.other["Abbreviation"]):
book, page = book_page_value[
len(abstract.county.other["Abbreviation"]):].split("/")
book = book.strip()
page = page.strip()
if book == '0' and page == '0':
book = not_applicable
page = not_applicable
record_value(abstract, 'book', book)
record_value(abstract, 'page', page)
elif book_page_value == '':
record_value(abstract, 'book', '')
record_value(abstract, 'page', '')
else:
# Below seems unnecessary, check with testing
print(
f'Encountered unexpected value "{book_page_value}" when trying to record book & page.'
)
def record_reception_number(abstract, document, reception_number_text):
reception_number = reception_number_text[1:]
set_document_download_values(document, reception_number)
record_value(abstract, 'reception number', reception_number)
def record_book_and_page(abstract, book_and_page_text):
_, book, _, page = book_and_page_text.split(' ')
record_value(abstract, 'book', book)
record_value(abstract, 'page', page)
def record_grantee(abstract, rows):
grantee = check_rows(abstract, rows,
abstract.county.titles["Row Titles"]["grantee"])
record_value(abstract, 'grantee', title_strip(grantee))
def record_document_type(abstract, rows):
document_type = check_rows(
abstract, rows, abstract.county.titles["Row Titles"]["document_type"])
record_value(abstract, 'document type', title_strip(document_type))
def record_document_type(abstract, document_table):
document_type = access_title_case_text(document_table)
record_value(abstract, 'document type', document_type)
def record_book_and_page(abstract, rows):
book_and_page = check_rows(
abstract, rows, abstract.county.titles["Row Titles"]["book_and_page"])
if book_and_page == 'N/A':
record_value(abstract, 'book', '')
record_value(abstract, 'page', '')
else:
if book_and_page.startswith(abstract.county.other["Abbreviation"]):
book_and_page = book_and_page[len(abstract.county.
other["Abbreviation"]):]
book, page = book_and_page.replace("/", "").split()
if book == '0' and page == '0':
record_value(abstract, 'book', '')
record_value(abstract, 'page', '')
else:
record_value(abstract, 'book', book)
record_value(abstract, 'page', page)
def record_effective_date(abstract, effective_date_text):
effective_date = date_from_string(effective_date_text.split(' ')[-1])
record_value(abstract, 'effective date', effective_date)
def record_recording_date(abstract, recording_date_text):
recording_date = date_from_string(recording_date_text.split(' ')[2])
record_value(abstract, 'recording date', recording_date)
def record_document_type(browser, abstract, document):
document_type_field = locate_element_by_class_name(
browser, abstract.county.record["Document Type"], "document type",
False, document)
record_value(abstract, 'document type', document_type_field.text.title())
def record_related_documents(abstract, document_table, document):
related_documents_text = document_table.text.split('\n')[1:]
related_documents_list = list(map(title_strip, related_documents_text))
related_documents = list_to_string(related_documents_list)
record_value(abstract, 'related documents', related_documents)
def record_legal(abstract, document_table, document):
legal = title_strip(document_table.text)
record_value(abstract, 'legal', legal)
def record_recording_date(abstract, rows):
recording_date = check_rows(
abstract, rows, abstract.county.titles["Row Titles"]["recording_date"])
record_value(abstract, 'recording date', recording_date[:10])
