def get_table_header(self, soup_obj):
header_row = clean_find_all(soup_obj.thead.tr, ["th"])
header_row_text = [get_full_string(e) for e in header_row]
header_row_text = [
e.strip() for e in header_row_text
if e.strip() != "" and e.strip() != "#"
]
if header_row_text[0] != "Document Title":
header_row_text = ["Row Number"] + header_row_text
return (header_row_text)
def get_report_tables(soup_obj, *args, **kwargs):
tables = clean_find_all(soup_obj, ['section', {'class': 'card mb-2'}])
if len(tables) != 12:
raise Exception(
str(len(tables)) + " table headers found instead of 12!")
dict_table = {}
for table in tables:
df = DataTable(table, *args, **kwargs)
dict_table[df.title] = df
return (dict_table)
def get_rows_in_table(table_obj):
rows = clean_find_all(table_obj, ['tr', {'class': 'nowrap'}])
if len(rows) == 0:
return (None)
else:
return (rows)
def extract_columns(row_obj, colval="td"):
cols = clean_find_all(row_obj, [colval])
assert len(cols) > 0
extracted_cols = [col.extract() for col in cols]
return (extracted_cols)
def get_middleware_token(text):
soup_obj = BeautifulSoup(text)
l = clean_find_all(soup_obj, ['input', {'name': 'csrfmiddlewaretoken'}])
assert (len(l) == 1)
return (l[0]["value"])