def _test_sample_pdf(short_filename):
tables = get_tables_from_document(fixture(short_filename))
assert_equal(get_expected_number_of_tables(short_filename), len(tables))
for table_num, table in enumerate(tables):
table_filename = "{}_{}.txt".format(short_filename, table_num)
expected_filename = join(EXPECTED_DIR, table_filename)
actual_filename = join(ACTUAL_DIR, table_filename)
with open(actual_filename, 'w') as f:
f.write(to_string(table).encode('utf-8'))
diff_table_files(expected_filename, actual_filename)
def _test_sample_pdf(short_filename):
with open(join(SAMPLE_DIR, short_filename), "rb") as f:
tables = get_tables(f)
assert_equal(get_expected_number_of_tables(short_filename), len(tables))
for table_num, table in enumerate(tables):
table_filename = "{}_{}.txt".format(short_filename, table_num)
expected_filename = join(EXPECTED_DIR, table_filename)
actual_filename = join(ACTUAL_DIR, table_filename)
with open(actual_filename, "w") as f:
f.write(to_string(table).encode("utf-8"))
diff_table_files(expected_filename, actual_filename)
from pdftables.pdf_document import PDFDocument as pdfdoc
from pdftables.pdftables import page_to_tables
from pdftables.display import to_string
filepath = 'irregular-verbs-de.pdf'
fileobj = open(filepath, 'rb')
doc = pdfdoc.from_fileobj(fileobj)
page = doc.get_page(0)
tables = page_to_tables(page)
for table in tables:
print to_string(table.data)
from pdftables.pdf_document import PDFDocument as pdfdoc from pdftables.pdftables import page_to_tables from pdftables.display import to_string filepath = 'irregular-verbs-de.pdf' fileobj = open(filepath, 'rb') doc = pdfdoc.from_fileobj(fileobj) page = doc.get_page(0) tables = page_to_tables(page) for table in tables: print to_string(table.data)