def get_title(self):
"""
Extract the title of the Government Law Proposal.
Example title produced:
http://www.knesset.gov.il/Laws/Data/BillGoverment/538/538.pdf
2010.-ע"שתה ,(םיילילפה םיכילהה לועיי) (66 'סמ ןוקית) ילילפה ןידה רדס קוח תעצה
"""
if self._title is None:
all_title = reverse_numbers(''.join(asblocks(self.get_page_text(0))[-1]))
self._title = all_title[:all_title.find('. ')].strip().replace('\n', ' ')
return self._title
def get_title(self):
"""
Extract the title of the Government Law Proposal.
Example title produced:
http://www.knesset.gov.il/Laws/Data/BillGoverment/538/538.pdf
2010.-ע"שתה ,(םיילילפה םיכילהה לועיי) (66 'סמ ןוקית) ילילפה ןידה רדס קוח תעצה
"""
if self._title is None:
all_title = reverse_numbers(''.join(
asblocks(self.get_page_text(0))[-1]))
self._title = all_title[:all_title.find('. ')].strip().replace(
'\n', ' ')
return self._title
def num_blocks(filename, x=0, y=0, W=0, H=0):
return len(asblocks(filename, x=x, y=y, W=W, H=H))
def isempty(filename, x=0, y=0, W=0, H=0):
return len(asblocks(filename, x, y, W, H)) == 0
numbers = set('pages file_size'.split())
def convert(k, v):
if k in numbers: return int(v.split()[0])
return v
data = [(k, convert(k, v.strip()))
for k, v in ((camel_to_lower_case(k), v.strip()) for k, v in (
l.split(':', 1) for l in capture_output([PDFINFO, filename])))]
pdfinfo.__dict__.update(data)
return pdfinfo
def isempty(filename, x=0, y=0, W=0, H=0):
return len(asblocks(filename, x, y, W, H)) == 0
def num_blocks(filename, x=0, y=0, W=0, H=0):
return len(asblocks(filename, x=x, y=y, W=W, H=H))
if __name__ == '__main__':
# Test code - not used
filename = '538.pdf'
fulltext = asblocks(filename)
texts = [pdftotext(filename, x=x, W=1000) for x in xrange(100)]
checksums = [checksum(filename, x=x, W=1000) for x in xrange(100)]
for i in xrange(len(checksums) - 1):
if checksums[i] != checksums[i + 1]:
print "change at %s" % i
def asreversed_number_blocks(text):
return asblocks([reverse_numbers(l).strip() for l in text])
def num_blocks(filename, x=0, y=0, W=0, H=0):
return len(asblocks(filename, x=x,y=y,W=W,H=H))
def isempty(filename, x=0, y=0, W=0, H=0):
return len(asblocks(filename, x, y, W, H)) == 0
self.filename, self.pages, self.file_size, self.mod_date)
__repr__ = __str__
pdfinfo = PdfInfo()
pdfinfo.filename = filename
numbers = set('pages file_size'.split())
def convert(k, v):
if k in numbers: return int(v.split()[0])
return v
data = [(k, convert(k, v.strip())) for k, v in
((camel_to_lower_case(k), v.strip()) for k,v in
(l.split(':',1) for l in capture_output([PDFINFO, filename])))]
pdfinfo.__dict__.update(data)
return pdfinfo
def isempty(filename, x=0, y=0, W=0, H=0):
return len(asblocks(filename, x, y, W, H)) == 0
def num_blocks(filename, x=0, y=0, W=0, H=0):
return len(asblocks(filename, x=x,y=y,W=W,H=H))
if __name__ == '__main__':
# Test code - not used
filename = '538.pdf'
fulltext = asblocks(filename)
texts = [pdftotext(filename, x=x,W=1000) for x in xrange(100)]
checksums = [checksum(filename, x=x, W=1000) for x in xrange(100)]
for i in xrange(len(checksums)-1):
if checksums[i] != checksums[i+1]:
print "change at %s" % i
def asreversed_number_blocks(text):
return asblocks([reverse_numbers(l).strip() for l in text])
