def fixture(filename):
"""
Obtain a PDFDocument for fixtures/sample_data/{filename}, memoizing the
return result.
"""
global memoized
if filename in memoized:
return memoized.get(filename)
here = abspath(dirname(__file__))
fn = pjoin(here, "..", "fixtures", "sample_data", filename)
fd = open(fn, "rb")
memoized[filename] = PDFDocument(fd)
return memoized[filename]
def render_pdf(pdf_filename):
with open(pdf_filename, "rb") as fd:
doc = PDFDocument.from_fileobj(fd)
for page_number, page in enumerate(doc.get_pages()):
svg_file = "svgs/{0}_{1:02d}.svg".format(basename(pdf_filename), page_number)
png_file = "pngs/{0}_{1:02d}.png".format(basename(pdf_filename), page_number)
table_container = page_to_tables(page)
annotations = make_annotations(table_container)
render_page(pdf_filename, page_number, annotations, svg_file, png_file)
print "Rendered", svg_file, png_file
def render_pdf(pdf_filename):
with open(pdf_filename, "rb") as fd:
doc = PDFDocument.from_fileobj(fd)
for page_number, page in enumerate(doc.get_pages()):
svg_file = 'svgs/{0}_{1:02d}.svg'.format(basename(pdf_filename),
page_number)
png_file = 'pngs/{0}_{1:02d}.png'.format(basename(pdf_filename),
page_number)
table_container = page_to_tables(page)
annotations = make_annotations(table_container)
render_page(pdf_filename, page_number, annotations, svg_file,
png_file)
print "Rendered", svg_file, png_file
def check(path):
fileobj = open(path, "rb")
doc = PDFDocument.from_fileobj(fileobj)
tables = pdftables.page_to_tables(doc.get_page(0))
print tables
#pagenumber = 1
#SelectedPDF = "pdf_prc_prod_1_7_1288_acucar-vhp-vendido-mercado-externo_sao-paulo_mensal.pdf"
#pagenumber = 1
#SelectedPDF = "commodity-prices_en.pdf"
#pagenumber = 1
#SelectedPDF = "AnimalExampleTables.pdf" # 7 pages works fine in pdfminer, 4 for first test 2012.01.PosRpt.pdf
#pagenumber = 2
filepath = os.path.join(PDF_TEST_FILES, SelectedPDF)
pta.plotAllPages(fh)
doc = PDFDocument(open(filepath, 'rb'))
pdf_page = doc.get_page(pagenumber)
table, diagnosticData = page_to_tables(
pdf_page, ConfigParameters(
extend_y=False,
table_top_hint=table_top_hint,
table_bottom_hint=table_bottom_hint,
atomise=False))
fig, ax1 = pta.plotpage(diagnosticData)
result = StringIO()
(columns, rows) = get_dimensions(table)
result.write(" {} columns, {} rows\n".format(columns, rows))
def check(path):
fileobj = open(path, 'rb')
doc = PDFDocument.from_fileobj(fileobj)
tables = pdftables.page_to_tables(doc.get_page(0))
print tables
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)
filepath = 'CBSinglePage.pdf'
fileobj = open(filepath, 'rb')
# Then we create a PDF element from the file object:
import pdftables
from pdftables.pdf_document import PDFDocument
doc = PDFDocument.from_fileobj(fileobj)
#Then we use the get_page() method to select a single page from the document:
from pdftables.pdftables import page_to_tables
page = doc.get_page(12)
tables = page_to_tables(page)
#Now you have a TableContainer object, you can convert it to ASCII for quick previewing:
from pdftables.display import to_string
for table in tables:
print to_string(table.data)
#fh = pdftables.filehandleFromURL("http://www.candyusa.com/files/1st%20qtr%202013%20report.pdf")
#pagenumber = 1
#SelectedPDF = "pdf_prc_prod_1_7_1288_acucar-vhp-vendido-mercado-externo_sao-paulo_mensal.pdf"
#pagenumber = 1
#SelectedPDF = "commodity-prices_en.pdf"
#pagenumber = 1
#SelectedPDF = "AnimalExampleTables.pdf" # 7 pages works fine in pdfminer, 4 for first test 2012.01.PosRpt.pdf
#pagenumber = 2
filepath = os.path.join(PDF_TEST_FILES, SelectedPDF)
pta.plotAllPages(fh)
doc = PDFDocument(open(filepath, 'rb'))
pdf_page = doc.get_page(pagenumber)
table, diagnosticData = page_to_tables(
pdf_page,
ConfigParameters(extend_y=False,
table_top_hint=table_top_hint,
table_bottom_hint=table_bottom_hint,
atomise=False))
fig, ax1 = pta.plotpage(diagnosticData)
result = StringIO()
(columns, rows) = get_dimensions(table)
result.write(" {} columns, {} rows\n".format(columns, rows))
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)
