added support for extracting text for html documents using beautifuls…

…oup4. fixes #7
deanmalmgren · Jul 23, 2014 · 39c7cf1 · 39c7cf1
1 parent 3dc299c
commit 39c7cf1
Show file tree

Hide file tree

Showing 9 changed files with 2,621 additions and 1 deletion.
diff --git a/Vagrantfile b/Vagrantfile
@@ -26,7 +26,6 @@ Vagrant.configure("2") do |config|
     vb.customize ["modifyvm", :id, "--memory", "2048"]
     override_config.vm.box = "precise64"
     override_config.vm.box_url = "http://files.vagrantup.com/precise64.box"
-    override_config.vm.network :forwarded_port, guest: 8000, host: 8000
   end
 
   # steps for provisioning so that these provisioning steps are

diff --git a/docs/changelog.rst b/docs/changelog.rst
@@ -9,6 +9,8 @@ track version numbers, where backwards incompatible changes
 latest
 ------
 
+* support for ``.html`` files (#7)
+
 
 0.3.0
 -----

diff --git a/docs/index.rst b/docs/index.rst
@@ -39,6 +39,8 @@ Currently supporting
 
 * ``.docx`` via `python-docx <https://python-docx.readthedocs.org/en/latest/>`__
 
+* ``.html`` via `beautifulsoup4 <http://beautiful-soup-4.readthedocs.org/en/latest/>`__
+
 * ``.pptx`` via `python-pptx <https://python-pptx.readthedocs.org/en/latest/>`__
 
 * ``.pdf`` via `pdftotext <http://poppler.freedesktop.org/>`__ (default) or `pdfminer <https://euske.github.io/pdfminer/>`__

diff --git a/docs/python_package.rst b/docs/python_package.rst
@@ -30,6 +30,13 @@ textract.parsers.docx
    :members:
 
 
+textract.parsers.html
+---------------------
+
+.. automodule:: textract.parsers.html
+   :members:
+
+
 textract.parsers.pdf
 ---------------------
 

diff --git a/requirements/python b/requirements/python
@@ -4,3 +4,4 @@ argcomplete
 python-pptx
 python-docx
 pdfminer==20140328
+beautifulsoup4