Merge branch 'msg-support'

docs/changelog.rst

@@ -13,6 +13,8 @@ latest changes in development for next release
 
 * support for ``.rtf`` files (`#84`_)
 
+* support for ``.msg`` files (`#87`_ and `#17`_ by `@anthonygarvan`_)
+
 
 1.2.0
 -----
@@ -198,6 +200,7 @@ latest changes in development for next release
 .. _#8: https://github.com/deanmalmgren/textract/issues/8
 .. _#9: https://github.com/deanmalmgren/textract/issues/9
 .. _#13: https://github.com/deanmalmgren/textract/issues/13
+.. _#17: https://github.com/deanmalmgren/textract/issues/17
 .. _#21: https://github.com/deanmalmgren/textract/issues/21
 .. _#25: https://github.com/deanmalmgren/textract/issues/25
 .. _#26: https://github.com/deanmalmgren/textract/issues/26
@@ -227,3 +230,4 @@ latest changes in development for next release
 .. _#79: https://github.com/deanmalmgren/textract/issues/79
 .. _#82: https://github.com/deanmalmgren/textract/issues/82
 .. _#84: https://github.com/deanmalmgren/textract/issues/84
+.. _#87: https://github.com/deanmalmgren/textract/issues/87

docs/index.rst

@@ -62,6 +62,8 @@ file types by either mentioning them on the `issue tracker
 
 * ``.mp3`` via `SpeechRecognition`_ and `sox`_
 
+* ``.msg`` via `msg-extractor`_
+
 * ``.odt`` via python builtins
 
 * ``.ogg`` via `SpeechRecognition`_ and `sox`_
@@ -90,6 +92,7 @@ file types by either mentioning them on the `issue tracker
 .. _antiword: http://www.winfield.demon.nl/
 .. _beautifulsoup4: http://beautiful-soup-4.readthedocs.org/en/latest/
 .. _ebooklib: https://github.com/aerkalov/ebooklib
+.. _msg-extractor: https://github.com/mattgwwalker/msg-extractor
 .. _pdfminer: https://euske.github.io/pdfminer/
 .. _pdftotext: http://poppler.freedesktop.org/
 .. _ps2text: http://pages.cs.wisc.edu/~ghost/doc/pstotext.htm

requirements/python

@@ -9,3 +9,4 @@ beautifulsoup4
 xlrd
 EbookLib
 SpeechRecognition>=1.1.0
+https://github.com/deanmalmgren/msg-extractor/zipball/pip-installable

setup.py

@@ -14,13 +14,18 @@
 github_url='https://github.com/deanmalmgren/textract'
 
 # read in the dependencies from the virtualenv requirements file
-dependencies = []
+dependencies, dependency_links = [], []
 filename = os.path.join("requirements", "python")
 with open(filename, 'r') as stream:
     for line in stream:
-        package = line.strip().split('#')[0]
-        if package:
-            dependencies.append(package)
+        line = line.strip()
+        if line.startswith("http"):
+            dependency_links.append(line)
+        else:
+            package = line.split('#')[0]
+            if package:
+                dependencies.append(package)
+
 
 setup(
     name=textract.__name__,
@@ -38,5 +43,6 @@
         'textract.parsers',
     ],
     install_requires=dependencies,
+    dependency_links=dependency_links,
     zip_safe=False,
 )

tests/msg/raw_text.txt

@@ -0,0 +1,15 @@
+Test for TIF files
+
+This is a test email to experiment with the MS Outlook MSG Extractor
+
+
+-- 
+
+
+Kind regards
+
+
+
+
+Brian Zhou
+

tests/test_msg.py

@@ -0,0 +1,7 @@
+import unittest
+
+import base
+
+
+class MsgTestCase(base.BaseParserTestCase, unittest.TestCase):
+    extension = 'msg'

textract/parsers/msg_parser.py

@@ -0,0 +1,12 @@
+from ExtractMsg import Message
+
+from .utils import BaseParser
+
+
+class Parser(BaseParser):
+    """Extract text from Microsoft Outlook files (.msg)
+    """
+
+    def extract(self, filename, **kwargs):
+        m = Message(filename)
+        return m.subject + '\n\n' + m.body