Merge pull request #25 from deanmalmgren/ps

.ps support

docs/index.rst

@@ -51,6 +51,8 @@ Currently supporting
 
 * ``.pdf`` via `pdftotext <http://poppler.freedesktop.org/>`__ (default) or `pdfminer <https://euske.github.io/pdfminer/>`__
 
+* ``.ps`` via `ps2text <http://pages.cs.wisc.edu/~ghost/doc/pstotext.htm>`__
+
 * ``.txt`` via python builtins
 
 Please recommend other file types by either mentioning them on the

docs/installation.rst

@@ -22,7 +22,7 @@ package manager before installing textract from pypi.
 
 .. code-block:: bash
 
-    apt-get install python-dev libxml2-dev libxslt1-dev antiword poppler-utils
+    apt-get install python-dev libxml2-dev libxslt1-dev antiword poppler-utils pstotext
     pip install textract
 
 
@@ -40,6 +40,11 @@ source code with homebrew and installing textract from pypi.
     brew link libxml2 libxslt
     pip install textract
 
+.. note::
+
+    ps2text is not currently a part of homebrew so ``.ps`` extraction
+    must be enabled by manually installing from source.
+
 .. note::
 
     Depending on how you have python configured on your system with
@@ -83,6 +88,9 @@ documenation about how to install the textract dependencies, please
       required by the ``.pdf`` parser (there is a pure python fallback
       that works if pdftotext isn't installed).
 
+    - `pstotext <http://pages.cs.wisc.edu/~ghost/doc/pstotext.htm>`__
+      is required by the ``.ps`` parser.
+
 2. Add a requirements file to the `requirements directory
    <https://github.com/deanmalmgren/textract/tree/master/requirements>`__
    of the project with the lower-cased name of your operating system

docs/python_package.rst

@@ -81,6 +81,14 @@ textract.parsers.pptx_parser module
     :undoc-members:
     :show-inheritance:
 
+textract.parsers.ps_parser module
+---------------------------------
+
+.. automodule:: textract.parsers.ps_parser
+    :members:
+    :undoc-members:
+    :show-inheritance:
+
 textract.parsers.txt_parser module
 ----------------------------------
 

requirements/debian

@@ -9,3 +9,6 @@ antiword
 
 # parse pdfs
 poppler-utils
+
+# parse postscript files
+pstotext

tests/run_functional_tests.sh

@@ -76,7 +76,9 @@ validate_example ${BASEDIR}/txt/little_bo_peep.txt 1c5fb4478d84c3b3296746e491895
 validate_example ${BASEDIR}/html/snow-fall.html acc2d8c49094e56474006cab3d3768eb
 validate_example ${BASEDIR}/html/what-we-do.html 1fb0263bf62317365cb30246d9e094be
 validate_example ${BASEDIR}/eml/example.eml cb59a5fad8ed8b849e15d53449b1de3f
+validate_example ${BASEDIR}/ps/example.ps bdd41be3e24d7ded69be1e5732f7c8fc
 validate_example ${BASEDIR}/json/json_is_my_best_friend.json dc0503f1b5a213d67cc08829b12df99e
 validate_example ${BASEDIR}/odt/i_heart_odt.odt f64b15c1acf5cebb1a91896221696da7
+
 # exit with the sum of the status
 exit ${EXIT_CODE}

textract/exceptions.py

@@ -19,8 +19,8 @@ def __init__(self, ext):
     def __str__(self):
         return self.render((
             'The filename extension %(ext)s is not yet supported by\n'
-            'textract. Please suggest this filename extension here:\n'
-            '    https://github.com/deanmalmgren/textract/issues'
+            'textract. Please suggest this filename extension here:\n\n'
+            '    https://github.com/deanmalmgren/textract/issues\n'
         ))
 
 

textract/parsers/ps_parser.py

@@ -0,0 +1,8 @@
+from ..shell import run
+
+
+def extract(filename, **kwargs):
+    """Extract text from postscript files using pstotext command.
+    """
+    pipe = run('pstotext %(filename)s' % locals())
+    return pipe.stdout.read()