from mechanize import Browser
br = Browser()
page = br.open('http://wow.interzet.ru/news.php?readmore=23')
br.form = br.forms().next()
print br.form
gives me the following error:
Traceback (most recent call last):
File "C:\Users\roddik\Desktop\mech.py", line 6, in <module>
br.form = br.forms().next()
File "build\bdist.win32\egg\mechanize\_mechanize.py", line 426, in forms
File "D:\py26\lib\site-package\mechanize-0.1.11-py2.6.egg\mechanize\_html.py", line 559, in forms
File "D:\py26\lib\site-packages\mechanize-0.1.11-py2.6.egg\mechanize\_html.py", line 225, in forms
File "D:\py26\lib\site-packages\clientform-0.2.10-py2.6.egg\ClientForm.py", line 967, in ParseResponseEx
File "D:\py26\lib\site-packages\clientform-0.2.10-py2.6.egg\ClientForm.py", line 1100, in _ParseFileEx
File "D:\py26\lib\site-packages\clientform-0.2.10-py2.6.egg\ClientForm.py", line 870, in feed
File "D:\py26\lib\sgmllib.py", line 104, in feed
self.goahead(0)
File "D:\py26\lib\sgmllib.py", line 138, in goahead
k = self.parse_starttag(i)
File "D:\py26\lib\sgmllib.py", line 290, in parse_starttag
self._convert_ref, attrvalue)
File "D:\py26\lib\sgmllib.py", line 302, in _convert_ref
return self.convert_charref(match.group(2)) or \
File "D:\py26\lib\site-packages\clientform-0.2.10-py2.6.egg\ClientForm.py", line 850, in convert_charref
File "D:\py26\lib\site-packages\clientform-0.2.10-py2.6.egg\ClientForm.py", line 244, in unescape_charref
ValueError: invalid literal for int() with base 10: 'e'
How can I fix it?
Edit:
I've fixed it this way. Is it ok? If not, how instead?
import ClientForm
from mechanize import Browser
def myunescape_charref(data, encoding):
if not str(data).isdigit(): return 0
name, base = data, 10
if name.startswith("x"):
name, base= name[1:], 16
uc = unichr(int(name, base))
if encoding is None:
return uc
else:
try:
repl = uc.encode(encoding)
except UnicodeError:
repl = "&#%s;" % data
return repl
ClientForm.unescape_charref = myunescape_charref
The problem is caused by urls like this
http://wow.zet/forum/index.php?showtopic=1197&pid=30419&st=0&#entry30419
ClientForm is looking for an integer after the &#
It is ok to have the # in the url, but it should be escaped in the html
as &# means a character encoding
Related
I'm trying to write a small python 3 utility script that checks to see if a file exists on my server.
So I have the code below that has a big array of string values that I pass to a simple function that returns the url and the response code.
However, when I run it I get all these errors I don't even know where to start:
$ python ReturnPath.py
Traceback (most recent call last):
File "ReturnPath.py", line 86, in <module>
checkResponse(u)
File "ReturnPath.py", line 5, in checkResponse
code = urllib.request.urlopen(url).getcode()
File "C:\Program Files\Python37\lib\urllib\request.py", line 222, in urlopen
return opener.open(url, data, timeout)
File "C:\Program Files\Python37\lib\urllib\request.py", line 510, in open
req = Request(fullurl, data)
File "C:\Program Files\Python37\lib\urllib\request.py", line 328, in __init__
self.full_url = url
File "C:\Program Files\Python37\lib\urllib\request.py", line 354, in full_url
self._parse()
File "C:\Program Files\Python37\lib\urllib\request.py", line 383, in _parse
raise ValueError("unknown url type: %r" % self.full_url)
ValueError: unknown url type: '"https://myserver.org/Media/CharacterAvatarImages/ae275ecb-183e-4e8d-8465-9d6d36c1323f.jpg"'
Here is my code:
import urllib.request
def checkResponse(url):
code = urllib.request.urlopen(url).getcode()
print(url + " = " + code)
return
arrCases = []
arrCases.extend([
"https://myserver.org/Media/CharacterAvatarImages/ae275ecb-183e-4e8d-8465-9d6d36c1323f.jpg",
"https://myserver.org/Media/CharacterAvatarImages/3ea92fa3-1ef0-4358-b38d-bb04e653aa53.jpg",
"https://myserver.org/Media/CharacterAvatarImages/7958a0e3-171b-46b5-875e-970368389bdf.jpg",
"https://myserver.org/Media/CharacterAvatarImages/e9a6cb00-6811-4b47-9aac-88480578dd44.jpg",
"https://myserver.org/Media/CharacterAvatarImages/73df88c3-b829-4519-9523-2bbe1f2c8549.jpg",
"https://myserver.org/Media/CharacterAvatarImages/61aa614b-5c95-487c-b4e3-783231b43677.jpg",
"https://myserver.org/Media/CharacterAvatarImages/8be7811f-18dc-4a81-a557-8b81605e3452.jpg",
"https://myserver.org/Media/CharacterAvatarImages/56539acb-2b1b-4410-a4bc-ac2eb0dc00fa.jpg",
"https://myserver.org/Media/CharacterAvatarImages/8bcf93fc-b435-4fd4-9c82-4aba78c58529.jpg",
])
for u in arrCases:
checkResponse(u)
What am I doing wrong?
You have to catch errors from broken URLs. I also increased speed through multiprocessing.Pool.
import urllib.request
from urllib.error import HTTPError, URLError
import multiprocessing
def checkResponse(url):
try:
code = urllib.request.urlopen(url, timeout=1).getcode()
except (HTTPError, URLError) as error:
print(url, " = ", error)
else:
print(url, " = ", code)
return
arrCases = []
arrCases.extend([
"https://i.stack.imgur.com/DsNOB.jpg",
"https://myserver.org/Media/CharacterAvatarImages/ae275ecb-183e-4e8d-8465-9d6d36c1323f.jpg",
"https://myserver.org/Media/CharacterAvatarImages/3ea92fa3-1ef0-4358-b38d-bb04e653aa53.jpg",
"https://myserver.org/Media/CharacterAvatarImages/7958a0e3-171b-46b5-875e-970368389bdf.jpg",
"https://myserver.org/Media/CharacterAvatarImages/e9a6cb00-6811-4b47-9aac-88480578dd44.jpg",
"https://myserver.org/Media/CharacterAvatarImages/73df88c3-b829-4519-9523-2bbe1f2c8549.jpg",
"https://myserver.org/Media/CharacterAvatarImages/61aa614b-5c95-487c-b4e3-783231b43677.jpg",
"https://myserver.org/Media/CharacterAvatarImages/8be7811f-18dc-4a81-a557-8b81605e3452.jpg",
"https://myserver.org/Media/CharacterAvatarImages/56539acb-2b1b-4410-a4bc-ac2eb0dc00fa.jpg",
"https://myserver.org/Media/CharacterAvatarImages/8bcf93fc-b435-4fd4-9c82-4aba78c58529.jpg",
])
with multiprocessing.Pool(processes=4) as pool:
pool.map(checkResponse, arrCases)
I have this code which checks if there's a provider specified, and a pem key, in order to send over an xml to a server:
#api.multi
def send_xml_file(self, envio_dte=None, file_name="envio",company_id=False):
if not company_id.dte_service_provider:
raise UserError(_("Not Service provider selected!"))
try:
signature_d = self.get_digital_signature_pem(
company_id)
seed = self.get_seed(company_id)
template_string = self.create_template_seed(seed)
seed_firmado = self.sign_seed(
template_string, signature_d['priv_key'],
signature_d['cert'])
token = self.get_token(seed_firmado,company_id)
_logger.info(_("Token is: {}").format(token))
except:
raise Warning(connection_status[response.e])
return {'sii_result': 'NoEnviado'}
On this line: _logger.info(_("Token is: {}").format(token)) is throwing me SyntaxError: invalid syntax this is my traceback:
Traceback (most recent call last):
File "/home/kristian/.virtualenvs/odoov9/lib/python2.7/site-packages/werkzeug/serving.py", line 177, in run_wsgi
execute(self.server.app)
File "/home/kristian/.virtualenvs/odoov9/lib/python2.7/site-packages/werkzeug/serving.py", line 165, in execute
application_iter = app(environ, start_response)
File "/home/kristian/odoov9/odoo-9.0c-20160712/openerp/service/server.py", line 246, in app
return self.app(e, s)
File "/home/kristian/odoov9/odoo-9.0c-20160712/openerp/service/wsgi_server.py", line 184, in application
return application_unproxied(environ, start_response)
File "/home/kristian/odoov9/odoo-9.0c-20160712/openerp/service/wsgi_server.py", line 170, in application_unproxied
result = handler(environ, start_response)
File "/home/kristian/odoov9/odoo-9.0c-20160712/openerp/http.py", line 1492, in __call__
self.load_addons()
File "/home/kristian/odoov9/odoo-9.0c-20160712/openerp/http.py", line 1513, in load_addons
m = __import__('openerp.addons.' + module)
File "/home/kristian/odoov9/odoo-9.0c-20160712/openerp/modules/module.py", line 61, in load_module
mod = imp.load_module('openerp.addons.' + module_part, f, path, descr)
File "/home/kristian/odoov9/solti/l10n_cl_dte/__init__.py", line 2, in <module>
from . import models, controllers, wizard
File "/home/kristian/odoov9/solti/l10n_cl_dte/models/__init__.py", line 2, in <module>
from . import invoice, partner, company, payment_term, sii_regional_offices
File "/home/kristian/odoov9/solti/l10n_cl_dte/models/invoice.py", line 500
_logger.info(_("Token is: {}").format(token))
^
SyntaxError: invalid syntax
I've checked for missing parenthesis, and stuff like that, but I still cannot figure it out.
Any ideas on this?
Thanks in advance!
Logger needs to be tabbed over, to be in the try block.
#api.multi
def send_xml_file(self, envio_dte=None, file_name="envio",company_id=False):
if not company_id.dte_service_provider:
raise UserError(_("Not Service provider selected!"))
try:
signature_d = self.get_digital_signature_pem(
company_id)
seed = self.get_seed(company_id)
template_string = self.create_template_seed(seed)
seed_firmado = self.sign_seed(
template_string, signature_d['priv_key'],
signature_d['cert'])
token = self.get_token(seed_firmado,company_id)
_logger.info(_("Token is: {}").format(token))
except:
# This is probably not doing what you expect
# raise will stop program execution, so the
# return will not actually return.
raise Warning(connection_status[response.e])
return {'sii_result': 'NoEnviado'}
I am trying to use the polyglot package for Named Entity Recognition in hebrew.
this is my code:
# -*- coding: utf8 -*-
import polyglot
from polyglot.text import Text, Word
from polyglot.downloader import downloader
downloader.download("embeddings2.iw")
text = Text(u"in france and in germany")
print(type(text))
text2 = Text(u"נסעתי מירושלים לתל אביב")
print(type(text2))
print(text.entities)
print(text2.entities)
this is the output:
<class 'polyglot.text.Text'>
<class 'polyglot.text.Text'>
[I-LOC([u'france']), I-LOC([u'germany'])]
Traceback (most recent call last):
File "C:/Python27/Lib/site-packages/IPython/core/pyglot.py", line 15, in <module>
print(text2.entities)
File "C:\Python27\lib\site-packages\polyglot\decorators.py", line 20, in __get__
value = obj.__dict__[self.func.__name__] = self.func(obj)
File "C:\Python27\lib\site-packages\polyglot\text.py", line 132, in entities
for i, (w, tag) in enumerate(self.ne_chunker.annotate(self.words)):
File "C:\Python27\lib\site-packages\polyglot\decorators.py", line 20, in __get__
value = obj.__dict__[self.func.__name__] = self.func(obj)
File "C:\Python27\lib\site-packages\polyglot\text.py", line 100, in ne_chunker
return get_ner_tagger(lang=self.language.code)
File "C:\Python27\lib\site-packages\polyglot\decorators.py", line 30, in memoizer
cache[key] = obj(*args, **kwargs)
File "C:\Python27\lib\site-packages\polyglot\tag\base.py", line 191, in get_ner_tagger
return NEChunker(lang=lang)
File "C:\Python27\lib\site-packages\polyglot\tag\base.py", line 104, in __init__
super(NEChunker, self).__init__(lang=lang)
File "C:\Python27\lib\site-packages\polyglot\tag\base.py", line 40, in __init__
self.predictor = self._load_network()
File "C:\Python27\lib\site-packages\polyglot\tag\base.py", line 109, in _load_network
self.embeddings = load_embeddings(self.lang, type='cw', normalize=True)
File "C:\Python27\lib\site-packages\polyglot\decorators.py", line 30, in memoizer
cache[key] = obj(*args, **kwargs)
File "C:\Python27\lib\site-packages\polyglot\load.py", line 61, in load_embeddings
p = locate_resource(src_dir, lang)
File "C:\Python27\lib\site-packages\polyglot\load.py", line 43, in locate_resource
if downloader.status(package_id) != downloader.INSTALLED:
File "C:\Python27\lib\site-packages\polyglot\downloader.py", line 738, in status
info = self._info_or_id(info_or_id)
File "C:\Python27\lib\site-packages\polyglot\downloader.py", line 508, in _info_or_id
return self.info(info_or_id)
File "C:\Python27\lib\site-packages\polyglot\downloader.py", line 934, in info
raise ValueError('Package %r not found in index' % id)
ValueError: Package u'embeddings2.iw' not found in index
The english worked but not the hebrew.
Whether I try to download the package u'embeddings2.iw' or not I get:
ValueError: Package u'embeddings2.iw' not found in index
I got it!
It seems like a bug to me.
The language detection defined the language as 'iw' which is the The former ISO 639 language code for Hebrew, and was changed to 'he'.
The text.entities did not recognize the iw code, so i changes it like so:
text2.hint_language_code = 'he'
I've just started using pycassa, so if this is a stupid question, I apologize upfront.
I have a column family with the following schema:
create column family MyColumnFamilyTest
with column_type = 'Standard'
and comparator = 'CompositeType(org.apache.cassandra.db.marshal.UTF8Type,org.apache.cassandra.db.marshal.UTF8Type,org.apache.cassandra.db.marshal.UTF8Type,org.apache.cassandra.db.marshal.TimeUUIDType)'
and default_validation_class = 'BytesType'
and key_validation_class = 'UTF8Type'
and read_repair_chance = 0.1
and dclocal_read_repair_chance = 0.0
and populate_io_cache_on_flush = false
and gc_grace = 864000
and min_compaction_threshold = 4
and max_compaction_threshold = 32
and replicate_on_write = true
and compaction_strategy = 'org.apache.cassandra.db.compaction.SizeTieredCompactionStrategy'
and caching = 'KEYS_ONLY'
and compression_options = {'sstable_compression' : 'org.apache.cassandra.io.compress.SnappyCompressor'};
When I try to do a get() with a valid key (works fine in cassandra-cli) I get:
Traceback (most recent call last):
File "<pyshell#19>", line 1, in <module>
cf.get('mykey',column_count=3)
File "/usr/local/lib/python2.7/dist-packages/pycassa-1.11.0-py2.7.egg/pycassa/columnfamily.py", line 664, in get
return self._cosc_to_dict(list_col_or_super, include_timestamp, include_ttl)
File "/usr/local/lib/python2.7/dist-packages/pycassa-1.11.0-py2.7.egg/pycassa/columnfamily.py", line 368, in _cosc_to_dict
ret[self._unpack_name(col.name)] = self._col_to_dict(col, include_timestamp, include_ttl)
File "/usr/local/lib/python2.7/dist-packages/pycassa-1.11.0-py2.7.egg/pycassa/columnfamily.py", line 444, in _unpack_name
return self._name_unpacker(b)
File "/usr/local/lib/python2.7/dist-packages/pycassa-1.11.0-py2.7.egg/pycassa/marshal.py", line 140, in unpack_composite
components.append(unpacker(bytestr[2:2 + length]))
File "/usr/local/lib/python2.7/dist-packages/pycassa-1.11.0-py2.7.egg/pycassa/marshal.py", line 374, in <lambda>
return lambda v: uuid.UUID(bytes=v)
File "/usr/lib/python2.7/uuid.py", line 144, in __init__
raise ValueError('bytes is not a 16-char string')
ValueError: bytes is not a 16-char string
Here's some more information I've discovered:
When using cassandra-cli I can see the data as:
% cassandra-cli -h 10.249.238.131
Connected to: "LocalDB" on 10.249.238.131/9160
Welcome to Cassandra CLI version 1.2.10-SNAPSHOT
Type 'help;' or '?' for help.
Type 'quit;' or 'exit;' to quit.
[default#unknown] use Keyspace;
[default#Keyspace] list ColumnFamily;
Using default limit of 100
Using default cell limit of 100
-------------------
RowKey: urn:keyspace:ColumnFamily:a36e8ab1-7032-4e4c-a53d-e3317f63a640:
=> (name=autoZoning:::, value=01, timestamp=1391298393966000)
=> (name=creationTime:::, value=00000143efd8b76e, timestamp=1391298393966000)
=> (name=inactive:::14fe78e0-8b9b-11e3-b171-005056b700bb, value=00, timestamp=1391298393966000)
=> (name=label:::14fe78e0-8b9b-11e3-b171-005056b700bb, value=726a6d2d766e782d76613031, timestamp=1391298393966000)
1 Row Returned.
Elapsed time: 16 msec(s).
Since it was unclear what was causing the exception, I decided to add a print prior to the 'return self._name_unpacker(b)' line in columnfamily.py and I see:
>>> cf.get(dict(cf.get_range(column_count=0,filter_empty=False)).keys()[0])
Attempting to unpack: <00>\rautoZoning<00><00><00><00><00><00><00><00><00><00>
Traceback (most recent call last):
File "<pyshell#172>", line 1, in <module>
cf.get(dict(cf.get_range(column_count=0,filter_empty=False)).keys()[0])
File "/usr/local/lib/python2.7/dist-packages/pycassa-1.11.0-py2.7.egg/pycassa/columnfamily.py", line 665, in get
return self._cosc_to_dict(list_col_or_super, include_timestamp, include_ttl)
File "/usr/local/lib/python2.7/dist-packages/pycassa-1.11.0-py2.7.egg/pycassa/columnfamily.py", line 368, in _cosc_to_dict
ret[self._unpack_name(col.name)] = self._col_to_dict(col, include_timestamp, include_ttl)
File "/usr/local/lib/python2.7/dist-packages/pycassa-1.11.0-py2.7.egg/pycassa/columnfamily.py", line 445, in _unpack_name
return self._name_unpacker(b)
File "/usr/local/lib/python2.7/dist-packages/pycassa-1.11.0-py2.7.egg/pycassa/marshal.py", line 140, in unpack_composite
components.append(unpacker(bytestr[2:2 + length]))
File "/usr/local/lib/python2.7/dist-packages/pycassa-1.11.0-py2.7.egg/pycassa/marshal.py", line 374, in <lambda>
return lambda v: uuid.UUID(bytes=v)
File "/usr/lib/python2.7/uuid.py", line 144, in __init__
raise ValueError('bytes is not a 16-char string')
ValueError: bytes is not a 16-char string
I have no idea where the extra characters are coming from around the column name. But that got me curious so I added another print in _cosc_to_dict in columnfamily.py and I see:
>>> cf.get(dict(cf.get_range(column_count=0,filter_empty=False)).keys()[0])
list_col_or_super is: []
list_col_or_super is: [ColumnOrSuperColumn(column=Column(timestamp=1391298393966000,
name='\x00\rautoZoning\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00', value='\x01', ttl=None),
counter_super_column=None, super_column=None, counter_column=None),
ColumnOrSuperColumn(column=Column(timestamp=1391298393966000,
name='\x00\x0ccreationTime\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00',
value='\x00\x00\x01C\xef\xd8\xb7n', ttl=None), counter_super_column=None, super_column=None,
counter_column=None), ColumnOrSuperColumn(column=Column(timestamp=1391298393966000,
name='\x00\x08inactive\x00\x00\x00\x00\x00\x00\x00\x00\x10\x14\xfex\xe0\x8b\x9b\x11\xe3\xb1q\x00PV\xb7\x00\xbb\x00', value='\x00', ttl=None), counter_super_column=None, super_column=None,
counter_column=None), ColumnOrSuperColumn(column=Column(timestamp=1391298393966000,
name='\x00\x05label\x00\x00\x00\x00\x00\x00\x00\x00\x10\x14\xfex\xe0\x8b\x9b\x11\xe3\xb1q\x00PV\xb7\x00\xbb\x00', value='thisIsATest', ttl=None), counter_super_column=None, super_column=None, counter_column=None)]
autoZoning unpack:
Traceback (most recent call last):
File "<stdin>", line 1, in <module>
File "/usr/local/lib64/python2.6/site-packages/pycassa-1.11.0-py2.6.egg/pycassa/columnfamily.py", line 666, in get
return self._cosc_to_dict(list_col_or_super, include_timestamp, include_ttl)
File "/usr/local/lib64/python2.6/site-packages/pycassa-1.11.0-py2.6.egg/pycassa/columnfamily.py", line 369, in _cosc_to_dict
ret[self._unpack_name(col.name)] = self._col_to_dict(col, include_timestamp, include_ttl)
File "/usr/local/lib64/python2.6/site-packages/pycassa-1.11.0-py2.6.egg/pycassa/columnfamily.py", line 446, in _unpack_name
return self._name_unpacker(b)
File "/usr/local/lib64/python2.6/site-packages/pycassa-1.11.0-py2.6.egg/pycassa/marshal.py", line 140, in unpack_composite
components.append(unpacker(bytestr[2:2 + length]))
File "/usr/local/lib64/python2.6/site-packages/pycassa-1.11.0-py2.6.egg/pycassa/marshal.py", line 374, in <lambda>
return lambda v: uuid.UUID(bytes=v)
File "/usr/lib64/python2.6/uuid.py", line 144, in __init__
raise ValueError('bytes is not a 16-char string')
ValueError: bytes is not a 16-char string
Am I correct in assuming that the extra characters around the column names are what is responsible for the 'ValueError: bytes is not a 16-char string' exception?
Also if I try to use the column name and select it I get:
>>> cf.get(u'urn:keyspace:ColumnFamily:a36e8ab1-7032-4e4c-a53d-e3317f63a640:',columns=['autoZoning:::'])
Traceback (most recent call last):
File "<pyshell#184>", line 1, in <module>
cf.get(u'urn:keyspace:ColumnFamily:a36e8ab1-7032-4e4c-a53d-e3317f63a640:',columns=['autoZoning:::'])
File "/usr/local/lib/python2.7/dist-packages/pycassa-1.11.0-py2.7.egg/pycassa/columnfamily.py", line 651, in get
cp = self._column_path(super_column, column)
File "/usr/local/lib/python2.7/dist-packages/pycassa-1.11.0-py2.7.egg/pycassa/columnfamily.py", line 383, in _column_path
self._pack_name(column, False))
File "/usr/local/lib/python2.7/dist-packages/pycassa-1.11.0-py2.7.egg/pycassa/columnfamily.py", line 426, in _pack_name
return self._name_packer(value, slice_start)
File "/usr/local/lib/python2.7/dist-packages/pycassa-1.11.0-py2.7.egg/pycassa/marshal.py", line 115, in pack_composite
packed = packer(item)
File "/usr/local/lib/python2.7/dist-packages/pycassa-1.11.0-py2.7.egg/pycassa/marshal.py", line 298, in pack_uuid
randomize=True)
File "/usr/local/lib/python2.7/dist-packages/pycassa-1.11.0-py2.7.egg/pycassa/util.py", line 75, in convert_time_to_uuid
'neither a UUID, a datetime, or a number')
ValueError: Argument for a v1 UUID column name or value was neither a UUID, a datetime, or a number
Any further thoughts?
Thanks,
Rob
Turns out that the problem wasn't with the key, it was being caused, in part, by a bug in pycassa that wasn't handling an empty (null) string in the column UUID. A short-term fix is in the answer in google groups:
https://groups.google.com/d/msg/pycassa-discuss/Vf_bSgDIi9M/KTA1kbE9IXAJ
The other part of the answer was to get at the columns by using tuples (with the UUID as a UUID and not a str) instead of a string with ':' separators because that's, as I found out, a cassandra-cli thing.
I am trying to split a huge pdf file into several small pdfs usinf pyPdf. I was trying with this oversimplified code:
from pyPdf import PdfFileWriter, PdfFileReader
inputpdf = PdfFileReader(file("document.pdf", "rb"))
for i in xrange(inputpdf.numPages):
output = PdfFileWriter()
output.addPage(inputpdf.getPage(i))
outputStream = file("document-page%s.pdf" % i, "wb")
output.write(outputStream)
outputStream.close()
but I got the follow error message:
Traceback (most recent call last):
File "./hltShortSummary.py", line 24, in <module>
for i in xrange(inputpdf.numPages):
File "/usr/lib/pymodules/python2.7/pyPdf/pdf.py", line 342, in <lambda>
numPages = property(lambda self: self.getNumPages(), None, None)
File "/usr/lib/pymodules/python2.7/pyPdf/pdf.py", line 334, in getNumPages
self._flatten()
File "/usr/lib/pymodules/python2.7/pyPdf/pdf.py", line 500, in _flatten
pages = catalog["/Pages"].getObject()
File "/usr/lib/pymodules/python2.7/pyPdf/generic.py", line 466, in __getitem__
return dict.__getitem__(self, key).getObject()
File "/usr/lib/pymodules/python2.7/pyPdf/generic.py", line 165, in getObject
return self.pdf.getObject(self).getObject()
File "/usr/lib/pymodules/python2.7/pyPdf/pdf.py", line 549, in getObject
retval = readObject(self.stream, self)
File "/usr/lib/pymodules/python2.7/pyPdf/generic.py", line 67, in readObject
return DictionaryObject.readFromStream(stream, pdf)
File "/usr/lib/pymodules/python2.7/pyPdf/generic.py", line 517, in readFromStream
value = readObject(stream, pdf)
File "/usr/lib/pymodules/python2.7/pyPdf/generic.py", line 58, in readObject
return ArrayObject.readFromStream(stream, pdf)
File "/usr/lib/pymodules/python2.7/pyPdf/generic.py", line 153, in readFromStream
arr.append(readObject(stream, pdf))
File "/usr/lib/pymodules/python2.7/pyPdf/generic.py", line 87, in readObject
return NumberObject.readFromStream(stream)
File "/usr/lib/pymodules/python2.7/pyPdf/generic.py", line 232, in readFromStream
return NumberObject(name)
ValueError: invalid literal for int() with base 10: ''
any ideas???
I think this is a bug in pypdf. Check out the source here. NumberObject.readFromStream expects an integer-like string, and isn't getting one. Probably the pdf in question is malformed in some unexpected way.
Try it this way
for i in xrange(inputpdf.getNumPages()):