Skip to content

BUG: Updated pdf_document_pdfminer for API changes in pdfminer #4

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
davidastephens wants to merge 1 commit into
base: dev
Choose a base branch
from
Open

BUG: Updated pdf_document_pdfminer for API changes in pdfminer #4

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
14 changes: 6 additions & 8 deletions pdftables/pdf_document_pdfminer.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6,10 +6,12 @@
import collections

import pdfminer.pdfparser
import pdfminer.pdfdocument
import pdfminer.pdfinterp
import pdfminer.pdfdevice
import pdfminer.layout
import pdfminer.converter
import pdfminer.pdfpage

from .pdf_document import (
PDFDocument as BasePDFDocument,
Expand All @@ -28,13 +30,9 @@ class PDFDocument(BasePDFDocument):
@staticmethod
def _initialise(file_handle):

(doc, parser) = (pdfminer.pdfparser.PDFDocument(),
pdfminer.pdfparser.PDFParser(file_handle))
parser = pdfminer.pdfparser.PDFParser(file_handle)
doc = pdfminer.pdfdocument.PDFDocument(parser)

parser.set_document(doc)
doc.set_parser(parser)

doc.initialize('')
if not doc.is_extractable:
raise ValueError(
"pdfminer.pdfparser.PDFDocument is_extractable != True")
Expand Down Expand Up @@ -74,7 +72,7 @@ def get_pages(self):
return self._pages

def _construct_pages(self):
self._pages = [PDFPage(self, page) for page in self._doc.get_pages()]
self._pages = [PDFPage(self, page) for page in pdfminer.pdfpage.PDFPage.create_pages(self._doc)]

def get_page(self, page_number):
"""
Expand Down Expand Up @@ -105,7 +103,7 @@ class PDFPage(BasePDFPage):
"""

def __init__(self, parent_pdf_document, page):
assert isinstance(page, pdfminer.pdfparser.PDFPage), page.__class__
assert isinstance(page, pdfminer.pdfpage.PDFPage), page.__class__

self.pdf_document = parent_pdf_document
self._page = page
Expand Down