Fix #21

[MRG] Update python-tk link

HISTORY.md

@@ -4,6 +4,11 @@ Release History
 master
 ------
 
+**Bugfixes**
+
+* Fix library discovery on Windows. [#32](https://github.com/camelot-dev/camelot/pull/32) by [KOLANICH](https://github.com/KOLANICH).
+* Fix calling convention of callback functions. [#34](https://github.com/camelot-dev/camelot/pull/34) by [KOLANICH](https://github.com/KOLANICH).
+
 0.7.3 (2019-07-07)
 ------------------
 

README.md

@@ -71,7 +71,7 @@ $ conda install -c conda-forge camelot-py
 
 ### Using pip
 
-After [installing the dependencies](https://camelot-py.readthedocs.io/en/master/user/install-deps.html) ([tk](https://packages.ubuntu.com/trusty/python-tk) and [ghostscript](https://www.ghostscript.com/)), you can simply use pip to install Camelot:
+After [installing the dependencies](https://camelot-py.readthedocs.io/en/master/user/install-deps.html) ([tk](https://packages.ubuntu.com/bionic/python/python-tk) and [ghostscript](https://www.ghostscript.com/)), you can simply use pip to install Camelot:
 
 <pre>
 $ pip install camelot-py[cv]
@@ -132,4 +132,8 @@ Camelot uses [Semantic Versioning](https://semver.org/). For the available versi
 
 This project is licensed under the MIT License, see the [LICENSE](https://github.com/camelot-dev/camelot/blob/master/LICENSE) file for details.
 
-<img src="http://i65.tinypic.com/9h4ajs.png" align="centre" />
+## Support the development
+
+You can support our work on Camelot with a one-time or monthly donation [on OpenCollective](https://opencollective.com/camelot). Organizations who use camelot can also sponsor the project for an acknowledgement on [our documentation site](https://camelot-py.readthedocs.io/en/master/) and this README.
+
+Special thanks to all the users, organizations and contributors that support Camelot!

camelot/ext/ghostscript/_gsprint.py

@@ -81,7 +81,9 @@ def delete_instance(instance):
     """
     return libgs.gsapi_delete_instance(instance)
 
-
+if sys.platform == "win32":
+    c_stdstream_call_t = WINFUNCTYPE(c_int, gs_main_instance, POINTER(c_char), c_int)
+else:
     c_stdstream_call_t = CFUNCTYPE(c_int, gs_main_instance, POINTER(c_char), c_int)
 
 
@@ -243,6 +245,9 @@ def __win32_finddll():
 
 if sys.platform == "win32":
     libgs = __win32_finddll()
+    if not libgs:
+        import ctypes.util
+        libgs = ctypes.util.find_library("".join(("gsdll", str(ctypes.sizeof(ctypes.c_voidp) * 8), ".dll"))) # finds in %PATH%
     if not libgs:
         raise RuntimeError("Please make sure that Ghostscript is installed")
     libgs = windll.LoadLibrary(libgs)

camelot/handlers.py

@@ -2,6 +2,7 @@
 
 import os
 import sys
+import copy
 
 from PyPDF2 import PdfFileReader, PdfFileWriter
 
@@ -89,50 +90,55 @@ class PDFHandler(object):
             P.extend(range(p["start"], p["end"] + 1))
         return sorted(set(P))
 
-    def _save_page(self, filepath, page, temp):
+    def _save_pages(self, filepath, pages, temp):
         """Saves specified page from PDF into a temporary directory.
 
         Parameters
         ----------
         filepath : str
             Filepath or URL of the PDF file.
-        page : int
+        pages : int
-            Page number.
+            Page numbers.
         temp : str
             Tmp directory.
 
         """
         with open(filepath, "rb") as fileobj:
-            infile = PdfFileReader(fileobj, strict=False)
+            infile_original = PdfFileReader(fileobj, strict=False)
-            if infile.isEncrypted:
+            if infile_original.isEncrypted:
-                infile.decrypt(self.password)
+                infile_original.decrypt(self.password)
-            fpath = os.path.join(temp, "page-{0}.pdf".format(page))
+
+            for page in pages:
+                # Ensure PdfFileReader object is unmodified
+                infile = copy.copy(infile_original)
+                fpath = os.path.join(temp, 'page-{0}.pdf'.format(page))
                 froot, fext = os.path.splitext(fpath)
                 p = infile.getPage(page - 1)
                 outfile = PdfFileWriter()
                 outfile.addPage(p)
-            with open(fpath, "wb") as f:
+                with open(fpath, 'wb') as f:
                      outfile.write(f)
+
+                # Orient rotated pages correctly
                 layout, dim = get_page_layout(fpath)
-            # fix rotated PDF
                 chars = get_text_objects(layout, ltype="char")
                 horizontal_text = get_text_objects(layout, ltype="horizontal_text")
                 vertical_text = get_text_objects(layout, ltype="vertical_text")
                 rotation = get_rotation(chars, horizontal_text, vertical_text)
-            if rotation != "":
+                if rotation != '':
-                fpath_new = "".join([froot.replace("page", "p"), "_rotated", fext])
+                    fpath_new = ''.join([froot.replace('page', 'p'), '_rotated', fext])
                     os.rename(fpath, fpath_new)
-                infile = PdfFileReader(open(fpath_new, "rb"), strict=False)
+                    infile = PdfFileReader(open(fpath_new, 'rb'), strict=False)
                     if infile.isEncrypted:
                         infile.decrypt(self.password)
                     outfile = PdfFileWriter()
                     p = infile.getPage(0)
-                if rotation == "anticlockwise":
+                    if rotation == 'anticlockwise':
                         p.rotateClockwise(90)
-                elif rotation == "clockwise":
+                    elif rotation == 'clockwise':
                         p.rotateCounterClockwise(90)
                     outfile.addPage(p)
-                with open(fpath, "wb") as f:
+                    with open(fpath, 'wb') as f:
                         outfile.write(f)
 
     def parse(
@@ -161,8 +167,7 @@ class PDFHandler(object):
         """
         tables = []
         with TemporaryDirectory() as tempdir:
-            for p in self.pages:
+            self._save_pages(self.filepath, self.pages, tempdir)
-                self._save_page(self.filepath, p, tempdir)
             pages = [
                 os.path.join(tempdir, "page-{0}.pdf".format(p)) for p in self.pages
             ]

docs/index.rst

@@ -30,6 +30,9 @@ Release v\ |version|. (:ref:`Installation <install>`)
 .. image:: https://badges.gitter.im/camelot-dev/Lobby.png
     :target: https://gitter.im/camelot-dev/Lobby
 
+.. image:: https://img.shields.io/badge/code%20style-black-000000.svg
+    :target: https://github.com/ambv/black
+
 **Camelot** is a Python library that makes it easy for *anyone* to extract tables from PDF files!
 
 .. note:: You can also check out `Excalibur`_, which is a web interface for Camelot!
@@ -83,6 +86,13 @@ See `comparison with other PDF table extraction libraries and tools`_.
 .. _ETL and data analysis workflows: https://gist.github.com/vinayak-mehta/e5949f7c2410a0e12f25d3682dc9e873
 .. _comparison with other PDF table extraction libraries and tools: https://github.com/camelot-dev/camelot/wiki/Comparison-with-other-PDF-Table-Extraction-libraries-and-tools
 
+Support us on OpenCollective
+----------------------------
+
+If Camelot helped you extract tables from PDFs, please consider supporting its development by `becoming a backer or a sponsor on OpenCollective`_!
+
+.. _becoming a backer or a sponsor on OpenCollective: https://opencollective.com/camelot
+
 The User Guide
 --------------
 

docs/user/install.rst

@@ -13,7 +13,7 @@ The easiest way to install Camelot is to install it with `conda`_, which is a pa
 
     $ conda install -c conda-forge camelot-py
 
-.. note:: Camelot is available for Python 2.7, 3.5 and 3.6 on Linux, macOS and Windows. For Windows, you will need to install ghostscript which you can get from their `downloads page`_.
+.. note:: Camelot is available for Python 2.7, 3.5, 3.6 and 3.7 on Linux, macOS and Windows. For Windows, you will need to install ghostscript which you can get from their `downloads page`_.
 
 .. _conda: https://conda.io/docs/
 .. _Anaconda: http://docs.continuum.io/anaconda/