html2text-2016.1.8/ 0000755 0001750 0001750 00000000000 12643763140 014600 5 ustar ubuntu ubuntu 0000000 0000000 html2text-2016.1.8/README.md 0000644 0001750 0001750 00000006250 12616413406 016057 0 ustar ubuntu ubuntu 0000000 0000000 # html2text
[](http://travis-ci.org/Alir3z4/html2text)
[](https://coveralls.io/r/Alir3z4/html2text)
[](https://pypi.python.org/pypi/html2text/)
[](https://pypi.python.org/pypi/html2text/)
[](https://pypi.python.org/pypi/html2text/)
[](https://pypi.python.org/pypi/html2text/)
[](https://pypi.python.org/pypi/html2text/)
[](https://pypi.python.org/pypi/html2text/)
html2text is a Python script that converts a page of HTML into clean, easy-to-read plain ASCII text. Better yet, that ASCII also happens to be valid Markdown (a text-to-HTML format).
Usage: `html2text [(filename|url) [encoding]]`
| Option | Description
|--------------------------------------------------------|---------------------------------------------------
| `--version` | Show program's version number and exit
| `-h`, `--help` | Show this help message and exit
| `--ignore-links` | Don't include any formatting for links
|`--escape-all` | Escape all special characters. Output is less readable, but avoids corner case formatting issues.
| `--reference-links` | Use reference links instead of links to create markdown
| `--mark-code` | Mark preformatted and code blocks with [code]...[/code]
For a complete list of options see the [docs](docs/usage.md)
Or you can use it from within `Python`:
```
>>> import html2text
>>>
>>> print(html2text.html2text("Zed's dead baby, Zed's dead.
"))
**Zed's** dead baby, _Zed's_ dead.
```
Or with some configuration options:
```
>>> import html2text
>>>
>>> h = html2text.HTML2Text()
>>> # Ignore converting links from HTML
>>> h.ignore_links = True
>>> print h.handle("Hello, world!")
Hello, world!
>>> print(h.handle("
Hello, world!"))
Hello, world!
>>> # Don't Ignore links anymore, I like links
>>> h.ignore_links = False
>>> print(h.handle("
Hello, world!"))
Hello, [world](http://earth.google.com/)!
```
*Originally written by Aaron Swartz. This code is distributed under the GPLv3.*
## How to install
`html2text` is available on pypi
https://pypi.python.org/pypi/html2text
```
$ pip install html2text
```
## How to run unit tests
PYTHONPATH=$PYTHONPATH:. coverage run --source=html2text setup.py test -v
To see the coverage results:
coverage combine
coverage html
then open the `./htmlcov/index.html` file in your browser.
## Documentation
Documentation lives [here](docs/index.md)
html2text-2016.1.8/html2text.egg-info/ 0000755 0001750 0001750 00000000000 12643763140 020225 5 ustar ubuntu ubuntu 0000000 0000000 html2text-2016.1.8/html2text.egg-info/not-zip-safe 0000644 0001750 0001750 00000000001 12471110761 022445 0 ustar ubuntu ubuntu 0000000 0000000
html2text-2016.1.8/html2text.egg-info/SOURCES.txt 0000644 0001750 0001750 00000004747 12643763140 022125 0 ustar ubuntu ubuntu 0000000 0000000 AUTHORS.rst
COPYING
ChangeLog.rst
MANIFEST.in
README.md
setup.cfg
setup.py
html2text/__init__.py
html2text/cli.py
html2text/compat.py
html2text/config.py
html2text/utils.py
html2text.egg-info/PKG-INFO
html2text.egg-info/SOURCES.txt
html2text.egg-info/dependency_links.txt
html2text.egg-info/entry_points.txt
html2text.egg-info/not-zip-safe
html2text.egg-info/top_level.txt
test/GoogleDocMassDownload.html
test/GoogleDocMassDownload.md
test/GoogleDocSaved.html
test/GoogleDocSaved.md
test/GoogleDocSaved_two.html
test/GoogleDocSaved_two.md
test/__init__.py
test/abbr_tag.html
test/abbr_tag.md
test/anchors.html
test/anchors.md
test/apos_element.html
test/apos_element.md
test/blockquote_example.html
test/blockquote_example.md
test/bodywidth_newline.html
test/bodywidth_newline.md
test/bold_inside_link.html
test/bold_inside_link.md
test/css_import_no_semicolon.html
test/css_import_no_semicolon.md
test/decript_tage.html
test/decript_tage.md
test/doc_with_table.html
test/doc_with_table.md
test/doc_with_table_bypass.html
test/doc_with_table_bypass.md
test/emdash-para.html
test/emdash-para.md
test/empty-link.html
test/empty-link.md
test/flip_emphasis.html
test/flip_emphasis.md
test/header_tags.html
test/header_tags.md
test/horizontal_rule.html
test/horizontal_rule.md
test/html-escaping.html
test/html-escaping.md
test/html_entities_out_of_text.html
test/html_entities_out_of_text.md
test/images_to_alt.html
test/images_to_alt.md
test/images_with_size.html
test/images_with_size.md
test/img-tag-with-link.html
test/img-tag-with-link.md
test/invalid_start.html
test/invalid_start.md
test/invalid_unicode.html
test/invalid_unicode.md
test/link_titles.html
test/link_titles.md
test/list_tags_example.html
test/list_tags_example.md
test/mark_code.html
test/mark_code.md
test/nbsp.html
test/nbsp.md
test/nbsp_unicode.html
test/nbsp_unicode.md
test/no_inline_links_example.html
test/no_inline_links_example.md
test/no_inline_links_images_to_alt.html
test/no_inline_links_images_to_alt.md
test/no_inline_links_nested.html
test/no_inline_links_nested.md
test/no_wrap_links.html
test/no_wrap_links.md
test/no_wrap_links_no_inline_links.html
test/no_wrap_links_no_inline_links.md
test/normal.html
test/normal.md
test/normal_escape_snob.html
test/normal_escape_snob.md
test/pre.html
test/pre.md
test/preformatted_in_list.html
test/preformatted_in_list.md
test/protect_links.html
test/protect_links.md
test/single_line_break.html
test/single_line_break.md
test/test_html2text.py
test/test_memleak.py
test/url-escaping.html
test/url-escaping.md html2text-2016.1.8/html2text.egg-info/PKG-INFO 0000644 0001750 0001750 00000002115 12643763137 021327 0 ustar ubuntu ubuntu 0000000 0000000 Metadata-Version: 1.1
Name: html2text
Version: 2016.1.8
Summary: Turn HTML into equivalent Markdown-structured text.
Home-page: https://github.com/Alir3z4/html2text/
Author: Alireza Savand
Author-email: alireza.savand@gmail.com
License: GNU GPL 3
Description: UNKNOWN
Platform: OS Independent
Classifier: Development Status :: 5 - Production/Stable
Classifier: Intended Audience :: Developers
Classifier: License :: OSI Approved :: GNU General Public License (GPL)
Classifier: Operating System :: OS Independent
Classifier: Programming Language :: Python
Classifier: Programming Language :: Python :: 2
Classifier: Programming Language :: Python :: 2.4
Classifier: Programming Language :: Python :: 2.5
Classifier: Programming Language :: Python :: 2.6
Classifier: Programming Language :: Python :: 2.7
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.0
Classifier: Programming Language :: Python :: 3.1
Classifier: Programming Language :: Python :: 3.2
Classifier: Programming Language :: Python :: 3.3
Classifier: Programming Language :: Python :: 3.4
html2text-2016.1.8/html2text.egg-info/entry_points.txt 0000644 0001750 0001750 00000000104 12643763137 023524 0 ustar ubuntu ubuntu 0000000 0000000
[console_scripts]
html2text=html2text.cli:main
html2text-2016.1.8/html2text.egg-info/dependency_links.txt 0000644 0001750 0001750 00000000001 12643763137 024301 0 ustar ubuntu ubuntu 0000000 0000000
html2text-2016.1.8/html2text.egg-info/top_level.txt 0000644 0001750 0001750 00000000012 12643763137 022756 0 ustar ubuntu ubuntu 0000000 0000000 html2text
html2text-2016.1.8/ChangeLog.rst 0000644 0001750 0001750 00000010071 12643762527 017170 0 ustar ubuntu ubuntu 0000000 0000000 2016.1.8
=========
----
* Feature #99: Removed duplicated initialisation.
* Fix #100: Get element style key error.
* Fix #101: Fix error end tag pop exception
* , , now rendered as ~~text~~.
2015.11.4
=========
----
* Fix #38: Long links wrapping controlled by `--no-wrap-links`.
* Note: `--no-wrap-links` implies `--reference-links`
* Feature #83: Add callback-on-tag.
* Fix #87: Decode errors can be handled via command line.
* Feature #95: Docs, decode errors spelling mistake.
* Fix #84: Make bodywidth kwarg overridable using config.
2015.6.21
=========
----
* Fix #31: HTML entities stay inside link.
* Fix #71: Coverage detects command line tests.
* Fix #39: Documentation update.
* Fix #61: Functionality added for optional use of automatic links.
* Feature #80: ``title`` attribute is preserved in both inline and reference links.
* Feature #82: More command line options. See docs.
2015.6.12
=========
----
* Feature #76: Making ``pre`` blocks clearer for further automatic formatting.
* Fix #71: Coverage detects tests carried out in ``subprocesses``
2015.6.6
========
----
* Fix #24: ``3.200.3`` vs ``2014.7.3`` output quirks.
* Fix #61. Malformed links in markdown output.
* Feature #62: Automatic version number.
* Fix #63: Nested code, anchor bug.
* Fix #64: Proper handling of anchors with content that starts with tags.
* Feature #67: Documentation all over the module.
* Feature #70: Adding tests for the module.
* Fix #73: Typo in config documentation.
2015.4.14
=========
----
* Feature #59: Write image tags with height and width attrs as raw html to retain dimensions
2015.4.13
=========
----
* Feature #56: Treat '-' file parameter as stdin.
* Feature #57: Retain escaping of html except within code or pre tags.
2015.2.18
=========
----
* Fix #38: Anchor tags with empty text or with `![]()
` tags inside are no longer stripped.
2014.12.29
==========
----
* Feature #51: Add single line break option.
This feature is useful for ensuring that lots of extra line breaks do not
end up in the resulting Markdown file in situations like Evernote .enex
exports. Note that this only works properly if ``body-width`` is set
to ``0``.
2014.12.24
==========
----
* Feature #49: Added a images_to_alt option to discard images and keep only their alt.
* Feature #50: Protect links, surrounding them with angle brackets to avoid breaking...
* Feature: Add ``setup.cfg`` file.
2014.12.5
=========
----
* Feature: Update `README.md` with usage examples.
* Fix #35: Remove `py_modules` from `setup.py`.
* Fix #36: Excludes tests from being installed as a separate module.
* Fix #37: Don't hardcode the path to the installed binary.
* Fix: Readme typo in running cli.
* Feature #40: Extract cli part to ``cli`` module.
* Feature #42: Bring python version compatibility to ``compat.py`` module.
* Feature #41: Extract utility/helper methods to ``utils`` module.
* Fix #45: Does not accept standard input when running under Python 3.
* Feature: Clean up ``ChangeLog.rst`` for version and date numbers.
2014.9.25
=========
----
* Feature #29, #27: Add simple table support with bypass option.
* Fix #20: Replace project website with: http://alir3z4.github.io/html2text/ .
2014.9.8
========
----
* Fix #28: missing ``html2text`` package in installation.
2014.9.7
========
----
* Fix ``unicode``/``type`` error in memory leak unit-test.
* Feature #16: Remove ``install_deps.py``.
* Feature #17: Add status badges via pypin.
* Feature #18: Add ``Python`` ``3.4`` to travis config file.
* Feature #19: Bring ``html2text`` to a separate module and take out the ``conf``/``constant`` variables.
* Feature #21: Remove meta vars from ``html2text.py`` file header.
* Fix: Fix TypeError when parsing tags like 
. Fixed in #25.
2014.7.3
========
----
* Fix #8: Remove ``How to do a release`` section from README.md.
* Fix #11: Include test directory markdown, html files.
* Fix #13: memory leak in using ``handle`` while keeping the old instance of ``html2text``.
2014.4.5
========
----
* Fix #1: Add ``ChangeLog.rst`` file.
* Fix #2: Add ``AUTHORS.rst`` file.
html2text-2016.1.8/test/ 0000755 0001750 0001750 00000000000 12643763140 015557 5 ustar ubuntu ubuntu 0000000 0000000 html2text-2016.1.8/test/html_entities_out_of_text.md 0000644 0001750 0001750 00000000047 12616413406 023366 0 ustar ubuntu ubuntu 0000000 0000000 [allas: Country Manager](http://thth)
html2text-2016.1.8/test/doc_with_table_bypass.html 0000664 0001750 0001750 00000001066 12471110237 022772 0 ustar ubuntu ubuntu 0000000 0000000
This is a test document
With some text, code, bolds and italics.
This is second header
Displaynone text
| Header 1 |
Header 2 |
Header 3 |
| Content 1 |
Content 2 |
 Image! |
html2text-2016.1.8/test/anchors.html 0000644 0001750 0001750 00000000427 12534002430 020070 0 ustar ubuntu ubuntu 0000000 0000000 Processing hyperlinks
Additional hyperlink tests!
Bold Link
filename.py
The source code is called magic.py
html2text-2016.1.8/test/no_inline_links_nested.html 0000644 0001750 0001750 00000000077 12616413406 023162 0 ustar ubuntu ubuntu 0000000 0000000 thisthat
html2text-2016.1.8/test/invalid_unicode.md 0000644 0001750 0001750 00000000004 12616413406 021224 0 ustar ubuntu ubuntu 0000000 0000000 Br
html2text-2016.1.8/test/html_entities_out_of_text.html 0000644 0001750 0001750 00000000073 12616413406 023731 0 ustar ubuntu ubuntu 0000000 0000000 állás: Country Manager
html2text-2016.1.8/test/__init__.py 0000664 0001750 0001750 00000000000 12471110237 017650 0 ustar ubuntu ubuntu 0000000 0000000 html2text-2016.1.8/test/emdash-para.md 0000664 0001750 0001750 00000001403 12471110237 020253 0 ustar ubuntu ubuntu 0000000 0000000 Bacon ipsum dolor sit amet pork chop id pork belly ham hock, sed meatloaf eu
exercitation flank quis veniam officia. Chuck dolor esse, occaecat est elit
drumstick ground round tri-tip nisi. Eu fugiat drumstick leberkas magna.
Turducken frankfurter nisi aute shank--
--irure ex esse id, ham commodo meatloaf pig pariatur ut cow. Officia salami
in fatback voluptate boudin ullamco beef ribs shank. Duis spare ribs pork
chop, ad leberkas reprehenderit id voluptate salami ham ut in ut cillum
turducken. Nisi ribeye tail capicola dolore andouille. Short ribs id beef
ribs, et nulla ground round do sunt dolore. Dolore nisi ullamco veniam sunt.
Duis brisket drumstick, dolor fatback filet mignon meatloaf laboris tri-tip
speck chuck ball tip voluptate ullamco laborum.
\--
html2text-2016.1.8/test/css_import_no_semicolon.html 0000664 0001750 0001750 00000000662 12471110237 023371 0 ustar ubuntu ubuntu 0000000 0000000
NBSP handling test #1
CSS @import statement without semicolon handling test
Lorem ipsum dolor sit amet, consectetur adipisicing elit, sed do eiusmod tempor incididunt ut labore et dolore magna aliqua.
html2text-2016.1.8/test/blockquote_example.html 0000644 0001750 0001750 00000000130 12616413406 022317 0 ustar ubuntu ubuntu 0000000 0000000
The time has come, the Walrus said, to speak of many things.
html2text-2016.1.8/test/test_memleak.py 0000664 0001750 0001750 00000001557 12471110237 020605 0 ustar ubuntu ubuntu 0000000 0000000 import sys
if sys.version_info[:2] < (2, 7):
import unittest2 as unittest
else:
import unittest
import logging
logging.basicConfig(format='%(levelname)s:%(funcName)s:%(message)s',
level=logging.DEBUG)
import html2text
class TestMemleak(unittest.TestCase):
"""
See https://github.com/Alir3z4/html2text/issues/13 for more
information on this.
"""
def setUp(self):
self.instr = 'miow '
def test_same_string(self):
h2t = html2text.HTML2Text()
result = h2t.handle(self.instr)
# Now, we shouldn't get leak of the previous run to the new one
self.assertEqual(h2t.handle(self.instr), result)
def test_empty_string(self):
h2t = html2text.HTML2Text()
h2t.handle(self.instr)
# And even less when the input is empty
self.assertEqual(h2t.handle(''), '\n\n')
html2text-2016.1.8/test/normal.md 0000664 0001750 0001750 00000001205 12471110237 017361 0 ustar ubuntu ubuntu 0000000 0000000 # test doc
first issue
* bit
* _**bold italic**_
* orange
* apple
* final
text to separate lists
1. now with numbers
2. the prisoner
1. not an _italic number_
2. a **bold human** being
3. end
**bold**
_italic_
def func(x):
if x < 1:
return 'a'
return 'b'
Some `fixed width text` here
_`italic fixed width text`_
2012\. Now that was a good year. So was 2011. That's all.
3.14159 is an approximation of pi.
\+ not + a list item
+foo
\- foo - bar
-foo
not a header
\--
not a hr
\---
\- - -
c:\tmp, \\\server\path, \\_/, foo\bar, #\\#, \\\\#
html2text-2016.1.8/test/doc_with_table.md 0000664 0001750 0001750 00000000465 12471110237 021047 0 ustar ubuntu ubuntu 0000000 0000000 # This is a test document
With some text, `code`, **bolds** and _italics_.
## This is second header
Displaynone text
Header 1 | Header 2 | Header 3
---|---|---
Content 1 | Content 2 |  Image!
Content 1 | Content 2 |  Image!
html2text-2016.1.8/test/no_inline_links_nested.md 0000644 0001750 0001750 00000000100 12616413406 022601 0 ustar ubuntu ubuntu 0000000 0000000 [[this][1]that][2]
[1]: /test2/
[2]: http://google.com
html2text-2016.1.8/test/html-escaping.md 0000644 0001750 0001750 00000000233 12534002430 020615 0 ustar ubuntu ubuntu 0000000 0000000 Escaped HTML like <div> or & should remain escaped on output
...unless that escaped HTML is in a tag
`...or a tag`
html2text-2016.1.8/test/decript_tage.md 0000644 0001750 0001750 00000000053 12643762105 020531 0 ustar ubuntu ubuntu 0000000 0000000 ~~something~~ ~~something~~ ~~something~~
html2text-2016.1.8/test/bodywidth_newline.html 0000664 0001750 0001750 00000000557 12471110237 022164 0 ustar ubuntu ubuntu 0000000 0000000 Another theory is that magician and occultist Aliester Crowley created the beast while
attempting to summon evil spirits at his house on the edge of the
lake in the early 1900′s. I met a local woman who
prefers this explanation.
html2text-2016.1.8/test/normal_escape_snob.md 0000664 0001750 0001750 00000001267 12471110237 021732 0 ustar ubuntu ubuntu 0000000 0000000 # test doc
first issue
* bit
* _**bold italic**_
* orange
* apple
* final
text to separate lists
1. now with numbers
2. the prisoner
1. not an _italic number_
2. a **bold human** being
3. end
**bold**
_italic_
text with \_underscore but not \_italicized
def func(x):
if x < 1:
return 'a'
return 'b'
Some `fixed width text` here
_`italic fixed width text`_
2012\. Now that was a good year. So was 2011. That's all.
3.14159 is an approximation of pi.
\+ not + a list item
+foo
\- foo - bar
-foo
not a header
\--
not a hr
\---
\- - -
c:\tmp, \\\server\path, \\\_/, foo\bar, \#\\\#, \\\\\#
html2text-2016.1.8/test/GoogleDocSaved.html 0000644 0001750 0001750 00000007430 12616413406 021273 0 ustar ubuntu ubuntu 0000000 0000000
Sandbox
test doc
first issue
-
bit
-
bold italic
-
orange
-
apple
-
final
text to separate lists
-
now with numbers
-
the prisoner
-
not an
italic number
-
a
bold human
being
-
end
bold
italic
def func(x):
if x < 1:
return 'a'
return 'b'
Some
fixed width text
here
italic fixed width text
html2text-2016.1.8/test/html-escaping.html 0000644 0001750 0001750 00000000262 12534002430 021163 0 ustar ubuntu ubuntu 0000000 0000000 Escaped HTML like <div> or & should remain escaped on output
...unless that escaped HTML is in a <pre> tag
...or a <code> tag html2text-2016.1.8/test/apos_element.md 0000644 0001750 0001750 00000000003 12616413406 020542 0 ustar ubuntu ubuntu 0000000 0000000 '
html2text-2016.1.8/test/blockquote_example.md 0000644 0001750 0001750 00000000100 12616413406 021750 0 ustar ubuntu ubuntu 0000000 0000000 > The time has come, the Walrus said, to speak of many things.
html2text-2016.1.8/test/flip_emphasis.md 0000644 0001750 0001750 00000000026 12616413406 020717 0 ustar ubuntu ubuntu 0000000 0000000 *Something* __else__
html2text-2016.1.8/test/url-escaping.md 0000664 0001750 0001750 00000002030 12471110237 020457 0 ustar ubuntu ubuntu 0000000 0000000 # Markdown-sensible characters processing
This test checks special characters processing inside URLs: parenthesis and
brackets should be escaped to keep markdown image and anchor syntax safe and
sound.
* [Some MSDN link using parenthesis](http://msdn.microsoft.com/en-us/library/system.drawing.drawing2d\(v=vs.110\))
* [Google search result URL with unescaped brackets](https://www.google.ru/search?q=\[brackets are cool\])
* [Yet another test for [brackets], {curly braces} and (parenthesis) processing inside the anchor](https://www.google.ru/search?q='\[\({}\)\]')
* Use automatic links like when the URL is the label
* Exempt [non-absolute_URIs](non-absolute_URIs) from automatic link detection
And here are images with tricky attribute values:
)
![\[banana\]](http://placehold.it/350x150#\[banana\])
![\(\[{}\]\)](http://placehold.it/350x150#\(\[{}\]\))
)
html2text-2016.1.8/test/list_tags_example.html 0000644 0001750 0001750 00000001232 12616413406 022144 0 ustar ubuntu ubuntu 0000000 0000000
- Definition List
- A list of terms and their definitions/descriptions.
- Ordered List
- A numbered list.
- Unordered List
- An unnumbered list.
Example 2
- Vocals
- Bruce Dickinson
- Guitar
- Adrian Smith
- Dave Murray
- Janick Gers
- Bass
- Steve Harris
- Drums
- Nicko McBrain
- some item
- Some other item
- some item
- Some other item
- some item
- some item
- somthing else here
- some item
html2text-2016.1.8/test/mark_code.html 0000644 0001750 0001750 00000000232 12616413406 020363 0 ustar ubuntu ubuntu 0000000 0000000
Normal text with 'pre' code block.
import os
def function():
a = 1
Normal text continues.
html2text-2016.1.8/test/empty-link.html 0000664 0001750 0001750 00000000302 12471110237 020523 0 ustar ubuntu ubuntu 0000000 0000000 Processing empty hyperlinks
This test checks wheter empty hyperlinks still appear in the markdown result.
html2text-2016.1.8/test/bold_inside_link.html 0000644 0001750 0001750 00000000111 12616414143 021722 0 ustar ubuntu ubuntu 0000000 0000000 Text
sample
html2text-2016.1.8/test/nbsp.md 0000664 0001750 0001750 00000001060 12471110237 017032 0 ustar ubuntu ubuntu 0000000 0000000 # NBSP handling test #1
In this test all NBSPs will be replaced with ordinary spaces (unicode_snob =
False).
Lorem ipsum dolor sit amet, consectetur adipisicing elit, sed do eiusmod
tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam,
quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo
consequat.
Duis aute irure dolor in reprehenderit in voluptate velit esse cillum dolore
eu fugiat nulla pariatur. Excepteur sint occaecat cupidatat non proident, sunt
in culpa qui officia deserunt mollit anim id est laborum.
html2text-2016.1.8/test/normal_escape_snob.html 0000664 0001750 0001750 00000004430 12471110237 022271 0 ustar ubuntu ubuntu 0000000 0000000
Normal
test doc
first issue
text to separate lists
-
now with numbers
-
the prisoner
-
not an italic number
-
a bold human being
-
end
bold
italic
text with _underscore but not _italicized
def func(x):
if x < 1:
return 'a'
return 'b'
Some fixed width text here
italic fixed width text
2012. Now that was a good year. So was 2011. That's all.
3.14159 is an approximation of pi.
+ not + a list item
+foo
- foo - bar
-foo
not a header
--
not a hr
---
- - -
c:\tmp, \\server\path, \_/, foo\bar, #\#, \\#
html2text-2016.1.8/test/nbsp_unicode.html 0000664 0001750 0001750 00000001424 12471110237 021110 0 ustar ubuntu ubuntu 0000000 0000000
NBSP handling test #2
NBSP handling test #2
In this test all NBSPs will be replaced with unicode non-breaking spaces (unicode_snob = True).
Lorem ipsum dolor sit amet, consectetur adipisicing elit, sed do eiusmod
tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam,
quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo
consequat.
Duis aute irure dolor in reprehenderit in voluptate velit esse
cillum dolore eu fugiat nulla pariatur. Excepteur sint occaecat cupidatat non
proident, sunt in culpa qui officia deserunt mollit anim id est laborum.
html2text-2016.1.8/test/abbr_tag.md 0000644 0001750 0001750 00000000051 12616413406 017633 0 ustar ubuntu ubuntu 0000000 0000000 TLA xyz
*[TLA]: Three Letter Acronym
html2text-2016.1.8/test/pre.html 0000664 0001750 0001750 00000000370 12471110237 017225 0 ustar ubuntu ubuntu 0000000 0000000
initial crowsed pre handling test #1
a
b
c
Ensure that HTML that starts with a crowded <pre>
is converted to reasonable Markdown.
html2text-2016.1.8/test/flip_emphasis.html 0000644 0001750 0001750 00000000035 12616413406 021263 0 ustar ubuntu ubuntu 0000000 0000000 Something
else
html2text-2016.1.8/test/images_to_alt.html 0000664 0001750 0001750 00000000440 12471110237 021244 0 ustar ubuntu ubuntu 0000000 0000000
html2text-2016.1.8/test/link_titles.html 0000644 0001750 0001750 00000000167 12616413406 020767 0 ustar ubuntu ubuntu 0000000 0000000 first example
second example
html2text-2016.1.8/test/header_tags.md 0000644 0001750 0001750 00000000161 12616413406 020342 0 ustar ubuntu ubuntu 0000000 0000000 # H1
## H2
### H3
#### H4
##### H5
###### H6
####### H7
######## H8
######### H9
H10 H11 H12 NO number
html2text-2016.1.8/test/doc_with_table_bypass.md 0000664 0001750 0001750 00000000537 12471110237 022430 0 ustar ubuntu ubuntu 0000000 0000000 # This is a test document
With some text, `code`, **bolds** and _italics_.
## This is second header
Displaynone text
|
Header 1
|
Header 2
|
Header 3
|
|
Content 1
|
Content 2
|
 Image!
|
html2text-2016.1.8/test/invalid_unicode.html 0000644 0001750 0001750 00000000015 12616413406 021572 0 ustar ubuntu ubuntu 0000000 0000000 B�r
html2text-2016.1.8/test/protect_links.html 0000664 0001750 0001750 00000000136 12471110237 021317 0 ustar ubuntu ubuntu 0000000 0000000 foo html2text-2016.1.8/test/no_wrap_links_no_inline_links.html 0000644 0001750 0001750 00000000223 12616413406 024536 0 ustar ubuntu ubuntu 0000000 0000000 And here is a long link I had at hand.
html2text-2016.1.8/test/doc_with_table.html 0000664 0001750 0001750 00000001313 12471110237 021404 0 ustar ubuntu ubuntu 0000000 0000000
This is a test document
With some text, code, bolds and italics.
This is second header
Displaynone text
| Header 1 |
Header 2 |
Header 3 |
| Content 1 |
Content 2 |
Image! |
| Content 1 |
Content 2 |
Image! |
html2text-2016.1.8/test/list_tags_example.md 0000644 0001750 0001750 00000000664 12616413406 021610 0 ustar ubuntu ubuntu 0000000 0000000 Definition List
A list of terms and their definitions/descriptions.
Ordered List
A numbered list.
Unordered List
An unnumbered list.
#### Example 2
Vocals
Bruce Dickinson
Guitar
Adrian Smith
Dave Murray
Janick Gers
Bass
Steve Harris
Drums
Nicko McBrain
* some item
* Some other item
* some item
1. Some other item
2. some item
3. some item
* somthing else here
* some item
html2text-2016.1.8/test/empty-link.md 0000664 0001750 0001750 00000000232 12471110237 020161 0 ustar ubuntu ubuntu 0000000 0000000 # Processing empty hyperlinks
This test checks wheter empty hyperlinks still appear in the markdown result.
[](http://some.link)
[](http://some.link)
html2text-2016.1.8/test/nbsp_unicode.md 0000664 0001750 0001750 00000001107 12471110237 020542 0 ustar ubuntu ubuntu 0000000 0000000 # NBSP handling test #2
In this test all NBSPs will be replaced with unicode non-breaking spaces
(unicode_snob = True).
Lorem ipsum dolor sit amet, consectetur adipisicing elit, sed do eiusmod
tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam,
quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo
consequat.
Duis aute irure dolor in reprehenderit in voluptate velit esse cillum dolore
eu fugiat nulla pariatur. Excepteur sint occaecat cupidatat non proident, sunt
in culpa qui officia deserunt mollit anim id est laborum.
html2text-2016.1.8/test/emdash-para.html 0000664 0001750 0001750 00000001437 12471110237 020626 0 ustar ubuntu ubuntu 0000000 0000000 Bacon ipsum dolor sit amet pork chop id pork belly ham hock, sed meatloaf eu exercitation flank quis veniam officia. Chuck dolor esse, occaecat est elit drumstick ground round tri-tip nisi. Eu fugiat drumstick leberkas magna. Turducken frankfurter nisi aute shank—
—irure ex esse id, ham commodo meatloaf pig pariatur ut cow. Officia salami in fatback voluptate boudin ullamco beef ribs shank. Duis spare ribs pork chop, ad leberkas reprehenderit id voluptate salami ham ut in ut cillum turducken. Nisi ribeye tail capicola dolore andouille. Short ribs id beef ribs, et nulla ground round do sunt dolore. Dolore nisi ullamco veniam sunt. Duis brisket drumstick, dolor fatback filet mignon meatloaf laboris tri-tip speck chuck ball tip voluptate ullamco laborum.
--
html2text-2016.1.8/test/normal.html 0000664 0001750 0001750 00000004335 12471110237 017734 0 ustar ubuntu ubuntu 0000000 0000000
Normal
test doc
first issue
text to separate lists
-
now with numbers
-
the prisoner
-
not an italic number
-
a bold human being
-
end
bold
italic
def func(x):
if x < 1:
return 'a'
return 'b'
Some fixed width text here
italic fixed width text
2012. Now that was a good year. So was 2011. That's all.
3.14159 is an approximation of pi.
+ not + a list item
+foo
- foo - bar
-foo
not a header
--
not a hr
---
- - -
c:\tmp, \\server\path, \_/, foo\bar, #\#, \\#
html2text-2016.1.8/test/apos_element.html 0000644 0001750 0001750 00000000065 12616413406 021116 0 ustar ubuntu ubuntu 0000000 0000000
'
html2text-2016.1.8/test/no_inline_links_example.html 0000644 0001750 0001750 00000000504 12616413406 023326 0 ustar ubuntu ubuntu 0000000 0000000 Googler
No href
No href but title available
Example
link text
html2text-2016.1.8/test/pre.md 0000664 0001750 0001750 00000000156 12471110237 016663 0 ustar ubuntu ubuntu 0000000 0000000
a
b
c
Ensure that HTML that starts with a crowded `` is converted to reasonable
Markdown.
html2text-2016.1.8/test/nbsp.html 0000664 0001750 0001750 00000001412 12471110237 017377 0 ustar ubuntu ubuntu 0000000 0000000
NBSP handling test #1
NBSP handling test #1
In this test all NBSPs will be replaced with ordinary spaces (unicode_snob = False).
Lorem ipsum dolor sit amet, consectetur adipisicing elit, sed do eiusmod
tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam,
quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo
consequat.
Duis aute irure dolor in reprehenderit in voluptate velit esse
cillum dolore eu fugiat nulla pariatur. Excepteur sint occaecat cupidatat non
proident, sunt in culpa qui officia deserunt mollit anim id est laborum.
html2text-2016.1.8/test/anchors.md 0000644 0001750 0001750 00000000320 12534002430 017514 0 ustar ubuntu ubuntu 0000000 0000000 # Processing hyperlinks
Additional hyperlink tests!
[**Bold Link**](http://some.link)
[`filename.py`](http://some.link/filename.py) [The source code is called
`magic.py`](http://some.link/magicsources.py)
html2text-2016.1.8/test/images_with_size.html 0000644 0001750 0001750 00000001151 12616413406 021772 0 ustar ubuntu ubuntu 0000000 0000000 
![]()
html2text-2016.1.8/test/protect_links.md 0000664 0001750 0001750 00000000130 12471110237 020745 0 ustar ubuntu ubuntu 0000000 0000000 [foo]()
html2text-2016.1.8/test/img-tag-with-link.html 0000664 0001750 0001750 00000001244 12471110237 021671 0 ustar ubuntu ubuntu 0000000 0000000 Processing images with links
This test checks images with associated links.
)
![[banana]](http://placehold.it/350x150#[banana])
![([{}])](http://placehold.it/350x150#([{}]))
html2text-2016.1.8/test/bodywidth_newline.md 0000664 0001750 0001750 00000000434 12471110237 021612 0 ustar ubuntu ubuntu 0000000 0000000 Another theory is that magician and occultist [Aliester Crowley](http://en.wikipedia.org/wiki/Aleister_Crowley) created the beast while attempting to summon evil spirits at his house on the edge of the lake in the early 1900′s. **I met a local woman who prefers this explanation.**
html2text-2016.1.8/test/preformatted_in_list.html 0000664 0001750 0001750 00000000170 12471110237 022652 0 ustar ubuntu ubuntu 0000000 0000000
- Run this command:
ls -l *.html
- ?
- Profit!
html2text-2016.1.8/test/bold_inside_link.md 0000644 0001750 0001750 00000000056 12616414204 021364 0 ustar ubuntu ubuntu 0000000 0000000 [**Text**](link.htm) [**sample**](/nothing/)
html2text-2016.1.8/test/preformatted_in_list.md 0000664 0001750 0001750 00000000105 12471110237 022304 0 ustar ubuntu ubuntu 0000000 0000000 * Run this command:
ls -l *.html
* ?
* Profit!
html2text-2016.1.8/test/invalid_start.md 0000664 0001750 0001750 00000000105 12471110237 020732 0 ustar ubuntu ubuntu 0000000 0000000 1. The ol has an invalid start
2. This should just be ignored
html2text-2016.1.8/test/GoogleDocMassDownload.html 0000644 0001750 0001750 00000013521 12616413406 022622 0 ustar ubuntu ubuntu 0000000 0000000
Sandbox
test doc
first issue
-
bit
-
bold italic
-
orange
-
apple
-
final
text to separate lists
-
now with numbers
-
the prisoner
-
not an
italic number
-
a
bold human
being
-
end
bold
italic
def func(x):
if x < 1:
return 'a'
return 'b'
Some
fixed width text
here
italic fixed width text
html2text-2016.1.8/test/images_to_alt.md 0000664 0001750 0001750 00000000132 12471110237 020676 0 ustar ubuntu ubuntu 0000000 0000000 [ ALT TEXT ](http://example.com)
[ALT TEXT](http://example.com)
html2text-2016.1.8/test/header_tags.html 0000644 0001750 0001750 00000000404 12616413406 020706 0 ustar ubuntu ubuntu 0000000 0000000
H1
H2
H3
H4
H5
H6
H7
H8
H9
H10
H11
H12
NO number
html2text-2016.1.8/test/single_line_break.md 0000664 0001750 0001750 00000000042 12471110237 021523 0 ustar ubuntu ubuntu 0000000 0000000 Hello world.
And hello html2text.
html2text-2016.1.8/test/single_line_break.html 0000664 0001750 0001750 00000000306 12471110237 022072 0 ustar ubuntu ubuntu 0000000 0000000
Hello world.
And hello html2text.
html2text-2016.1.8/test/no_wrap_links_no_inline_links.md 0000644 0001750 0001750 00000000212 12616413406 024170 0 ustar ubuntu ubuntu 0000000 0000000 And [here](http://bugs.debian.org/cgi-bin/pkgreport.cgi?tag=multiarch;users=debian-dpkg@lists.debian.org) is a long link I had at hand.
html2text-2016.1.8/test/img-tag-with-link.md 0000664 0001750 0001750 00000000665 12471110237 021333 0 ustar ubuntu ubuntu 0000000 0000000 # Processing images with links
This test checks images with associated links.
[)](http://some.link)
[![\[banana\]](http://placehold.it/350x150#\[banana\])](http://some.link)
[](http://some.link)
[![\(\[{}\]\)](http://placehold.it/350x150#\(\[{}\]\))](http://some.link)
[)](http://some.link)
html2text-2016.1.8/test/invalid_start.html 0000664 0001750 0001750 00000000250 12471110237 021277 0 ustar ubuntu ubuntu 0000000 0000000
- The ol has an invalid start
- This should just be ignored
html2text-2016.1.8/test/no_wrap_links.md 0000644 0001750 0001750 00000000211 12616413406 020735 0 ustar ubuntu ubuntu 0000000 0000000 And [here](http://bugs.debian.org/cgi-bin/pkgreport.cgi?tag=multiarch;users=debian-dpkg@lists.debian.org) is a long link I had at hand.
html2text-2016.1.8/test/test_html2text.py 0000644 0001750 0001750 00000012244 12616413406 021123 0 ustar ubuntu ubuntu 0000000 0000000 import codecs
import glob
import os
import re
import subprocess
import sys
if sys.version_info[:2] < (2, 7):
import unittest2 as unittest
else:
import unittest
import logging
logging.basicConfig(format='%(levelname)s:%(funcName)s:%(message)s',
level=logging.DEBUG)
import html2text
def test_module(fn, google_doc=False, **kwargs):
h = html2text.HTML2Text()
h.fn = fn
if google_doc:
h.google_doc = True
h.ul_item_mark = '-'
h.body_width = 0
h.hide_strikethrough = True
for k, v in kwargs.items():
setattr(h, k, v)
result = get_baseline(fn)
inf = open(fn)
actual = h.handle(inf.read())
inf.close()
return result, actual
def test_command(fn, *args):
args = list(args)
cmd = [sys.executable, '-m', 'html2text.__init__']
if '--googledoc' in args:
args.remove('--googledoc')
cmd += ['-g', '-d', '-b', '0', '-s']
if args:
cmd.extend(args)
cmd += [fn]
result = get_baseline(fn)
pid = subprocess.Popen(cmd, stdout=subprocess.PIPE)
out, _ = pid.communicate()
actual = out.decode('utf8')
if os.name == 'nt':
# Fix the unwanted CR to CRCRLF replacement
# during text pipelining on Windows/cygwin
actual = re.sub(r'\r+', '\r', actual)
actual = actual.replace('\r\n', '\n')
return result, actual
def test_function(fn, **kwargs):
with open(fn) as inf:
actual = html2text.html2text(inf.read(), **kwargs)
result = get_baseline(fn)
return result, actual
def get_dump_name(fn, suffix):
return '%s-%s_output.md' % (os.path.splitext(fn)[0], suffix)
def get_baseline_name(fn):
return os.path.splitext(fn)[0] + '.md'
def get_baseline(fn):
name = get_baseline_name(fn)
f = codecs.open(name, mode='r', encoding='utf8')
out = f.read()
f.close()
return out
class TestHTML2Text(unittest.TestCase):
pass
def generate_test(fn):
def test_mod(self):
self.maxDiff = None
result, actual = test_module(fn, **module_args)
self.assertEqual(result, actual)
def test_cmd(self):
# Because there is no command-line option to control unicode_snob
if 'unicode_snob' not in module_args:
self.maxDiff = None
result, actual = test_command(fn, *cmdline_args)
self.assertEqual(result, actual)
def test_func(self):
result, actual = test_function(fn, **func_args)
self.assertEqual(result, actual)
module_args = {}
cmdline_args = []
func_args = {}
base_fn = os.path.basename(fn).lower()
if base_fn.startswith('google'):
module_args['google_doc'] = True
cmdline_args.append('--googledoc')
if base_fn.find('unicode') >= 0:
module_args['unicode_snob'] = True
if base_fn.find('flip_emphasis') >= 0:
module_args['emphasis_mark'] = '*'
module_args['strong_mark'] = '__'
cmdline_args.append('-e')
if base_fn.find('escape_snob') >= 0:
module_args['escape_snob'] = True
cmdline_args.append('--escape-all')
if base_fn.find('table_bypass') >= 0:
module_args['bypass_tables'] = True
cmdline_args.append('--bypass-tables')
if base_fn.startswith('bodywidth'):
# module_args['unicode_snob'] = True
module_args['body_width'] = 0
cmdline_args.append('--body-width=0')
func_args['bodywidth'] = 0
if base_fn.startswith('protect_links'):
module_args['protect_links'] = True
cmdline_args.append('--protect-links')
if base_fn.startswith('images_to_alt'):
module_args['images_to_alt'] = True
cmdline_args.append('--images-to-alt')
if base_fn.startswith('images_with_size'):
module_args['images_with_size'] = True
cmdline_args.append('--images-with-size')
if base_fn.startswith('single_line_break'):
module_args['body_width'] = 0
cmdline_args.append('--body-width=0')
module_args['single_line_break'] = True
cmdline_args.append('--single-line-break')
if base_fn.startswith('no_inline_links'):
module_args['inline_links'] = False
cmdline_args.append('--reference-links')
if base_fn.startswith('no_wrap_links'):
module_args['wrap_links'] = False
cmdline_args.append('--no-wrap-links')
if base_fn.startswith('mark_code'):
module_args['mark_code'] = True
cmdline_args.append('--mark-code')
if base_fn not in ['bodywidth_newline.html', 'abbr_tag.html']:
test_func = None
return test_mod, test_cmd, test_func
# Originally from http://stackoverflow.com/questions/32899/\
# how-to-generate-dynamic-parametrized-unit-tests-in-python
test_dir_name = os.path.dirname(os.path.realpath(__file__))
for fn in glob.glob("%s/*.html" % test_dir_name):
test_name = 'test_%s' % os.path.splitext(os.path.basename(fn))[0].lower()
test_m, test_c, test_func = generate_test(fn)
setattr(TestHTML2Text, test_name + "_mod", test_m)
if test_c:
setattr(TestHTML2Text, test_name + "_cmd", test_c)
if test_func:
setattr(TestHTML2Text, test_name + "_func", test_func)
if __name__ == "__main__":
unittest.main()
html2text-2016.1.8/test/url-escaping.html 0000664 0001750 0001750 00000002511 12471110237 021027 0 ustar ubuntu ubuntu 0000000 0000000 Markdown-sensible characters processing
This test checks special characters processing inside URLs: parenthesis and brackets should be escaped to keep markdown image and anchor syntax safe and sound.
And here are images with tricky attribute values:
html2text-2016.1.8/test/GoogleDocSaved_two.md 0000644 0001750 0001750 00000000000 12616413406 021602 0 ustar ubuntu ubuntu 0000000 0000000 html2text-2016.1.8/test/GoogleDocMassDownload.md 0000664 0001750 0001750 00000000643 12471110237 022254 0 ustar ubuntu ubuntu 0000000 0000000 # test doc
first issue
- bit
- _**bold italic**_
- orange
- apple
- final
text to separate lists
1. now with numbers
2. the prisoner
1. not an _italic number_
2. a **bold human** being
3. end
**bold**
_italic_
` def func(x):`
` if x < 1:`
` return 'a'`
` return 'b'`
Some ` fixed width text` here
_` italic fixed width text`_
html2text-2016.1.8/test/css_import_no_semicolon.md 0000664 0001750 0001750 00000000267 12471110237 023026 0 ustar ubuntu ubuntu 0000000 0000000 # CSS @import statement without semicolon handling test
Lorem ipsum dolor sit amet, consectetur adipisicing elit, sed do eiusmod
tempor incididunt ut labore et dolore magna aliqua.
html2text-2016.1.8/test/no_wrap_links.html 0000644 0001750 0001750 00000000227 12616413406 021310 0 ustar ubuntu ubuntu 0000000 0000000 And here is a long link I had at hand.
html2text-2016.1.8/test/mark_code.md 0000644 0001750 0001750 00000000207 12616413406 020021 0 ustar ubuntu ubuntu 0000000 0000000 Normal text with 'pre' code block.
[code]
import os
def function():
a = 1
[/code]
Normal text continues.
html2text-2016.1.8/test/no_inline_links_images_to_alt.md 0000644 0001750 0001750 00000000215 12616413406 024135 0 ustar ubuntu ubuntu 0000000 0000000 [ ![ALT TEXT][1] ][2]
[![ALT TEXT][1]][2]
[![http://example.com][1]][2]
[1]: http://example.com/img.png
[2]: http://example.com
html2text-2016.1.8/test/abbr_tag.html 0000644 0001750 0001750 00000000077 12616413406 020207 0 ustar ubuntu ubuntu 0000000 0000000 TLA
xyz
html2text-2016.1.8/test/GoogleDocSaved.md 0000664 0001750 0001750 00000000643 12471110237 020723 0 ustar ubuntu ubuntu 0000000 0000000 # test doc
first issue
- bit
- _**bold italic**_
- orange
- apple
- final
text to separate lists
1. now with numbers
2. the prisoner
1. not an _italic number_
2. a **bold human** being
3. end
**bold**
_italic_
` def func(x):`
` if x < 1:`
` return 'a'`
` return 'b'`
Some ` fixed width text` here
_` italic fixed width text`_
html2text-2016.1.8/test/GoogleDocSaved_two.html 0000644 0001750 0001750 00000007465 12616413406 022174 0 ustar ubuntu ubuntu 0000000 0000000
Sandbox
test doc
first issue
-
bit
-
bold italic
-
orange
-
apple
-
final
text to separate lists
-
now with numbers
-
the prisoner
-
not an
italic number
-
a
bold human
being
-
end
bold
italic
def func(x):
if x < 1:
return 'a'
return 'b'
Some
fixed width text
here
italic fixed width text
html2text-2016.1.8/test/no_inline_links_example.md 0000644 0001750 0001750 00000000306 12616413406 022762 0 ustar ubuntu ubuntu 0000000 0000000 [Googler][1] No href No href but title available [ Example][2] [ [ [ link text
][3]][3]][3]
[1]: http://google.com
[2]: http://example.com (Example title)
[3]: http://example.com (abc)
html2text-2016.1.8/test/images_with_size.md 0000644 0001750 0001750 00000000670 12616413406 021433 0 ustar ubuntu ubuntu 0000000 0000000 
html2text-2016.1.8/test/link_titles.md 0000644 0001750 0001750 00000000131 12616413406 020412 0 ustar ubuntu ubuntu 0000000 0000000 [ first example](http://example.com "MyTitle" )
[ second example](http://example.com)
html2text-2016.1.8/test/horizontal_rule.html 0000644 0001750 0001750 00000000057 12616413406 021664 0 ustar ubuntu ubuntu 0000000 0000000
html2text-2016.1.8/test/horizontal_rule.md 0000644 0001750 0001750 00000000007 12616413406 021313 0 ustar ubuntu ubuntu 0000000 0000000 * * *
html2text-2016.1.8/test/decript_tage.html 0000644 0001750 0001750 00000000101 12616413406 021064 0 ustar ubuntu ubuntu 0000000 0000000 something
something
something
html2text-2016.1.8/test/no_inline_links_images_to_alt.html 0000644 0001750 0001750 00000000441 12616413406 024502 0 ustar ubuntu ubuntu 0000000 0000000
html2text-2016.1.8/setup.cfg 0000664 0001750 0001750 00000000144 12643763140 016422 0 ustar ubuntu ubuntu 0000000 0000000 [metadata]
description-file = README.md
[egg_info]
tag_build =
tag_date = 0
tag_svn_revision = 0
html2text-2016.1.8/PKG-INFO 0000644 0001750 0001750 00000002115 12643763140 015674 0 ustar ubuntu ubuntu 0000000 0000000 Metadata-Version: 1.1
Name: html2text
Version: 2016.1.8
Summary: Turn HTML into equivalent Markdown-structured text.
Home-page: https://github.com/Alir3z4/html2text/
Author: Alireza Savand
Author-email: alireza.savand@gmail.com
License: GNU GPL 3
Description: UNKNOWN
Platform: OS Independent
Classifier: Development Status :: 5 - Production/Stable
Classifier: Intended Audience :: Developers
Classifier: License :: OSI Approved :: GNU General Public License (GPL)
Classifier: Operating System :: OS Independent
Classifier: Programming Language :: Python
Classifier: Programming Language :: Python :: 2
Classifier: Programming Language :: Python :: 2.4
Classifier: Programming Language :: Python :: 2.5
Classifier: Programming Language :: Python :: 2.6
Classifier: Programming Language :: Python :: 2.7
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.0
Classifier: Programming Language :: Python :: 3.1
Classifier: Programming Language :: Python :: 3.2
Classifier: Programming Language :: Python :: 3.3
Classifier: Programming Language :: Python :: 3.4
html2text-2016.1.8/MANIFEST.in 0000664 0001750 0001750 00000000164 12471110237 016331 0 ustar ubuntu ubuntu 0000000 0000000 include COPYING
include README.md
include ChangeLog.rst
include AUTHORS.rst
recursive-include test *.html *.md *.py
html2text-2016.1.8/html2text/ 0000755 0001750 0001750 00000000000 12643763140 016533 5 ustar ubuntu ubuntu 0000000 0000000 html2text-2016.1.8/html2text/__init__.py 0000644 0001750 0001750 00000071227 12643763075 020664 0 ustar ubuntu ubuntu 0000000 0000000 #!/usr/bin/env python
# coding: utf-8
"""html2text: Turn HTML into equivalent Markdown-structured text."""
from __future__ import division
import re
import cgi
try:
from textwrap import wrap
except ImportError: # pragma: no cover
pass
from html2text.compat import urlparse, HTMLParser
from html2text import config
from html2text.utils import (
name2cp,
unifiable_n,
google_text_emphasis,
google_fixed_width_font,
element_style,
hn,
google_has_height,
escape_md,
google_list_style,
list_numbering_start,
dumb_css_parser,
escape_md_section,
skipwrap
)
__version__ = (2016, 1, 8)
# TODO:
# Support decoded entities with UNIFIABLE.
class HTML2Text(HTMLParser.HTMLParser):
def __init__(self, out=None, baseurl='', bodywidth=config.BODY_WIDTH):
"""
Input parameters:
out: possible custom replacement for self.outtextf (which
appends lines of text).
baseurl: base URL of the document we process
"""
HTMLParser.HTMLParser.__init__(self)
# Config options
self.split_next_td = False
self.td_count = 0
self.table_start = False
self.unicode_snob = config.UNICODE_SNOB # covered in cli
self.escape_snob = config.ESCAPE_SNOB # covered in cli
self.links_each_paragraph = config.LINKS_EACH_PARAGRAPH
self.body_width = bodywidth # covered in cli
self.skip_internal_links = config.SKIP_INTERNAL_LINKS # covered in cli
self.inline_links = config.INLINE_LINKS # covered in cli
self.protect_links = config.PROTECT_LINKS # covered in cli
self.google_list_indent = config.GOOGLE_LIST_INDENT # covered in cli
self.ignore_links = config.IGNORE_ANCHORS # covered in cli
self.ignore_images = config.IGNORE_IMAGES # covered in cli
self.images_to_alt = config.IMAGES_TO_ALT # covered in cli
self.images_with_size = config.IMAGES_WITH_SIZE # covered in cli
self.ignore_emphasis = config.IGNORE_EMPHASIS # covered in cli
self.bypass_tables = config.BYPASS_TABLES # covered in cli
self.google_doc = False # covered in cli
self.ul_item_mark = '*' # covered in cli
self.emphasis_mark = '_' # covered in cli
self.strong_mark = '**'
self.single_line_break = config.SINGLE_LINE_BREAK # covered in cli
self.use_automatic_links = config.USE_AUTOMATIC_LINKS # covered in cli
self.hide_strikethrough = False # covered in cli
self.mark_code = config.MARK_CODE
self.wrap_links = config.WRAP_LINKS # covered in cli
self.tag_callback = None
if out is None: # pragma: no cover
self.out = self.outtextf
else: # pragma: no cover
self.out = out
# empty list to store output characters before they are "joined"
self.outtextlist = []
self.quiet = 0
self.p_p = 0 # number of newline character to print before next output
self.outcount = 0
self.start = 1
self.space = 0
self.a = []
self.astack = []
self.maybe_automatic_link = None
self.empty_link = False
self.absolute_url_matcher = re.compile(r'^[a-zA-Z+]+://')
self.acount = 0
self.list = []
self.blockquote = 0
self.pre = 0
self.startpre = 0
self.code = False
self.br_toggle = ''
self.lastWasNL = 0
self.lastWasList = False
self.style = 0
self.style_def = {}
self.tag_stack = []
self.emphasis = 0
self.drop_white_space = 0
self.inheader = False
self.abbr_title = None # current abbreviation definition
self.abbr_data = None # last inner HTML (for abbr being defined)
self.abbr_list = {} # stack of abbreviations to write later
self.baseurl = baseurl
try:
del unifiable_n[name2cp('nbsp')]
except KeyError:
pass
config.UNIFIABLE['nbsp'] = ' _place_holder;'
def feed(self, data):
data = data.replace("", "")
HTMLParser.HTMLParser.feed(self, data)
def handle(self, data):
self.feed(data)
self.feed("")
return self.optwrap(self.close())
def outtextf(self, s):
self.outtextlist.append(s)
if s:
self.lastWasNL = s[-1] == '\n'
def close(self):
HTMLParser.HTMLParser.close(self)
try:
nochr = unicode('')
except NameError:
nochr = str('')
self.pbr()
self.o('', 0, 'end')
outtext = nochr.join(self.outtextlist)
if self.unicode_snob:
try:
nbsp = unichr(name2cp('nbsp'))
except NameError:
nbsp = chr(name2cp('nbsp'))
else:
try:
nbsp = unichr(32)
except NameError:
nbsp = chr(32)
try:
outtext = outtext.replace(unicode(' _place_holder;'), nbsp)
except NameError:
outtext = outtext.replace(' _place_holder;', nbsp)
# Clear self.outtextlist to avoid memory leak of its content to
# the next handling.
self.outtextlist = []
return outtext
def handle_charref(self, c):
charref = self.charref(c)
if not self.code and not self.pre:
charref = cgi.escape(charref)
self.handle_data(charref, True)
def handle_entityref(self, c):
entityref = self.entityref(c)
if (not self.code and not self.pre
and entityref != ' _place_holder;'):
entityref = cgi.escape(entityref)
self.handle_data(entityref, True)
def handle_starttag(self, tag, attrs):
self.handle_tag(tag, attrs, 1)
def handle_endtag(self, tag):
self.handle_tag(tag, None, 0)
def previousIndex(self, attrs):
"""
:type attrs: dict
:returns: The index of certain set of attributes (of a link) in the
self.a list. If the set of attributes is not found, returns None
:rtype: int
"""
if 'href' not in attrs: # pragma: no cover
return None
i = -1
for a in self.a:
i += 1
match = 0
if ('href' in a) and a['href'] == attrs['href']:
if ('title' in a) or ('title' in attrs):
if (('title' in a) and ('title' in attrs) and
a['title'] == attrs['title']):
match = True
else:
match = True
if match:
return i
def handle_emphasis(self, start, tag_style, parent_style):
"""
Handles various text emphases
"""
tag_emphasis = google_text_emphasis(tag_style)
parent_emphasis = google_text_emphasis(parent_style)
# handle Google's text emphasis
strikethrough = 'line-through' in \
tag_emphasis and self.hide_strikethrough
bold = 'bold' in tag_emphasis and not 'bold' in parent_emphasis
italic = 'italic' in tag_emphasis and not 'italic' in parent_emphasis
fixed = google_fixed_width_font(tag_style) and not \
google_fixed_width_font(parent_style) and not self.pre
if start:
# crossed-out text must be handled before other attributes
# in order not to output qualifiers unnecessarily
if bold or italic or fixed:
self.emphasis += 1
if strikethrough:
self.quiet += 1
if italic:
self.o(self.emphasis_mark)
self.drop_white_space += 1
if bold:
self.o(self.strong_mark)
self.drop_white_space += 1
if fixed:
self.o('`')
self.drop_white_space += 1
self.code = True
else:
if bold or italic or fixed:
# there must not be whitespace before closing emphasis mark
self.emphasis -= 1
self.space = 0
if fixed:
if self.drop_white_space:
# empty emphasis, drop it
self.drop_white_space -= 1
else:
self.o('`')
self.code = False
if bold:
if self.drop_white_space:
# empty emphasis, drop it
self.drop_white_space -= 1
else:
self.o(self.strong_mark)
if italic:
if self.drop_white_space:
# empty emphasis, drop it
self.drop_white_space -= 1
else:
self.o(self.emphasis_mark)
# space is only allowed after *all* emphasis marks
if (bold or italic) and not self.emphasis:
self.o(" ")
if strikethrough:
self.quiet -= 1
def handle_tag(self, tag, attrs, start):
# attrs is None for endtags
if attrs is None:
attrs = {}
else:
attrs = dict(attrs)
if self.tag_callback is not None:
if self.tag_callback(self, tag, attrs, start) is True:
return
# first thing inside the anchor tag is another tag that produces some output
if (start and not self.maybe_automatic_link is None
and tag not in ['p', 'div', 'style', 'dl', 'dt']
and (tag != "img" or self.ignore_images)):
self.o("[")
self.maybe_automatic_link = None
self.empty_link = False
if self.google_doc:
# the attrs parameter is empty for a closing tag. in addition, we
# need the attributes of the parent nodes in order to get a
# complete style description for the current element. we assume
# that google docs export well formed html.
parent_style = {}
if start:
if self.tag_stack:
parent_style = self.tag_stack[-1][2]
tag_style = element_style(attrs, self.style_def, parent_style)
self.tag_stack.append((tag, attrs, tag_style))
else:
dummy, attrs, tag_style = self.tag_stack.pop() if self.tag_stack else (None, {}, {})
if self.tag_stack:
parent_style = self.tag_stack[-1][2]
if hn(tag):
self.p()
if start:
self.inheader = True
self.o(hn(tag) * "#" + ' ')
else:
self.inheader = False
return # prevent redundant emphasis marks on headers
if tag in ['p', 'div']:
if self.google_doc:
if start and google_has_height(tag_style):
self.p()
else:
self.soft_br()
else:
self.p()
if tag == "br" and start:
self.o(" \n")
if tag == "hr" and start:
self.p()
self.o("* * *")
self.p()
if tag in ["head", "style", 'script']:
if start:
self.quiet += 1
else:
self.quiet -= 1
if tag == "style":
if start:
self.style += 1
else:
self.style -= 1
if tag in ["body"]:
self.quiet = 0 # sites like 9rules.com never close
if tag == "blockquote":
if start:
self.p()
self.o('> ', 0, 1)
self.start = 1
self.blockquote += 1
else:
self.blockquote -= 1
self.p()
if tag in ['em', 'i', 'u'] and not self.ignore_emphasis:
self.o(self.emphasis_mark)
if tag in ['strong', 'b'] and not self.ignore_emphasis:
self.o(self.strong_mark)
if tag in ['del', 'strike', 's']:
if start:
self.o('~~')
else:
self.o('~~')
if self.google_doc:
if not self.inheader:
# handle some font attributes, but leave headers clean
self.handle_emphasis(start, tag_style, parent_style)
if tag in ["code", "tt"] and not self.pre:
self.o('`') # TODO: `` `this` ``
self.code = not self.code
if tag == "abbr":
if start:
self.abbr_title = None
self.abbr_data = ''
if ('title' in attrs):
self.abbr_title = attrs['title']
else:
if self.abbr_title is not None:
self.abbr_list[self.abbr_data] = self.abbr_title
self.abbr_title = None
self.abbr_data = ''
if tag == "a" and not self.ignore_links:
if start:
if ('href' in attrs) and \
(attrs['href'] is not None) and \
not (self.skip_internal_links and
attrs['href'].startswith('#')):
self.astack.append(attrs)
self.maybe_automatic_link = attrs['href']
self.empty_link = True
if self.protect_links:
attrs['href'] = '<'+attrs['href']+'>'
else:
self.astack.append(None)
else:
if self.astack:
a = self.astack.pop()
if self.maybe_automatic_link and not self.empty_link:
self.maybe_automatic_link = None
elif a:
if self.empty_link:
self.o("[")
self.empty_link = False
self.maybe_automatic_link = None
if self.inline_links:
try:
title = escape_md(a['title'])
except KeyError:
self.o("](" + escape_md(a['href']) + ")")
else:
self.o("](" + escape_md(a['href'])
+ ' "' + title + '" )')
else:
i = self.previousIndex(a)
if i is not None:
a = self.a[i]
else:
self.acount += 1
a['count'] = self.acount
a['outcount'] = self.outcount
self.a.append(a)
self.o("][" + str(a['count']) + "]")
if tag == "img" and start and not self.ignore_images:
if 'src' in attrs:
if not self.images_to_alt:
attrs['href'] = attrs['src']
alt = attrs.get('alt') or ''
# If we have images_with_size, write raw html including width,
# height, and alt attributes
if self.images_with_size and \
("width" in attrs or "height" in attrs):
self.o("![](" + attrs["src"] + ")
")
return
# If we have a link to create, output the start
if not self.maybe_automatic_link is None:
href = self.maybe_automatic_link
if self.images_to_alt and escape_md(alt) == href and \
self.absolute_url_matcher.match(href):
self.o("<" + escape_md(alt) + ">")
self.empty_link = False
return
else:
self.o("[")
self.maybe_automatic_link = None
self.empty_link = False
# If we have images_to_alt, we discard the image itself,
# considering only the alt text.
if self.images_to_alt:
self.o(escape_md(alt))
else:
self.o("![" + escape_md(alt) + "]")
if self.inline_links:
href = attrs.get('href') or ''
self.o("(" + escape_md(href) + ")")
else:
i = self.previousIndex(attrs)
if i is not None:
attrs = self.a[i]
else:
self.acount += 1
attrs['count'] = self.acount
attrs['outcount'] = self.outcount
self.a.append(attrs)
self.o("[" + str(attrs['count']) + "]")
if tag == 'dl' and start:
self.p()
if tag == 'dt' and not start:
self.pbr()
if tag == 'dd' and start:
self.o(' ')
if tag == 'dd' and not start:
self.pbr()
if tag in ["ol", "ul"]:
# Google Docs create sub lists as top level lists
if (not self.list) and (not self.lastWasList):
self.p()
if start:
if self.google_doc:
list_style = google_list_style(tag_style)
else:
list_style = tag
numbering_start = list_numbering_start(attrs)
self.list.append({
'name': list_style,
'num': numbering_start
})
else:
if self.list:
self.list.pop()
self.lastWasList = True
else:
self.lastWasList = False
if tag == 'li':
self.pbr()
if start:
if self.list:
li = self.list[-1]
else:
li = {'name': 'ul', 'num': 0}
if self.google_doc:
nest_count = self.google_nest_count(tag_style)
else:
nest_count = len(self.list)
# TODO: line up - s > 9 correctly.
self.o(" " * nest_count)
if li['name'] == "ul":
self.o(self.ul_item_mark + " ")
elif li['name'] == "ol":
li['num'] += 1
self.o(str(li['num']) + ". ")
self.start = 1
if tag in ["table", "tr", "td", "th"]:
if self.bypass_tables:
if start:
self.soft_br()
if tag in ["td", "th"]:
if start:
self.o('<{0}>\n\n'.format(tag))
else:
self.o('\n'.format(tag))
else:
if start:
self.o('<{0}>'.format(tag))
else:
self.o(''.format(tag))
else:
if tag == "table" and start:
self.table_start = True
if tag in ["td", "th"] and start:
if self.split_next_td:
self.o("| ")
self.split_next_td = True
if tag == "tr" and start:
self.td_count = 0
if tag == "tr" and not start:
self.split_next_td = False
self.soft_br()
if tag == "tr" and not start and self.table_start:
# Underline table header
self.o("|".join(["---"] * self.td_count))
self.soft_br()
self.table_start = False
if tag in ["td", "th"] and start:
self.td_count += 1
if tag == "pre":
if start:
self.startpre = 1
self.pre = 1
else:
self.pre = 0
if self.mark_code:
self.out("\n[/code]")
self.p()
# TODO: Add docstring for these one letter functions
def pbr(self):
"Pretty print has a line break"
if self.p_p == 0:
self.p_p = 1
def p(self):
"Set pretty print to 1 or 2 lines"
self.p_p = 1 if self.single_line_break else 2
def soft_br(self):
"Soft breaks"
self.pbr()
self.br_toggle = ' '
def o(self, data, puredata=0, force=0):
"""
Deal with indentation and whitespace
"""
if self.abbr_data is not None:
self.abbr_data += data
if not self.quiet:
if self.google_doc:
# prevent white space immediately after 'begin emphasis'
# marks ('**' and '_')
lstripped_data = data.lstrip()
if self.drop_white_space and not (self.pre or self.code):
data = lstripped_data
if lstripped_data != '':
self.drop_white_space = 0
if puredata and not self.pre:
# This is a very dangerous call ... it could mess up
# all handling of when not handled properly
# (see entityref)
data = re.sub(r'\s+', r' ', data)
if data and data[0] == ' ':
self.space = 1
data = data[1:]
if not data and not force:
return
if self.startpre:
#self.out(" :") #TODO: not output when already one there
if not data.startswith("\n"): #
stuff...
data = "\n" + data
if self.mark_code:
self.out("\n[code]")
self.p_p = 0
bq = (">" * self.blockquote)
if not (force and data and data[0] == ">") and self.blockquote:
bq += " "
if self.pre:
if not self.list:
bq += " "
#else: list content is already partially indented
for i in range(len(self.list)):
bq += " "
data = data.replace("\n", "\n" + bq)
if self.startpre:
self.startpre = 0
if self.list:
# use existing initial indentation
data = data.lstrip("\n")
if self.start:
self.space = 0
self.p_p = 0
self.start = 0
if force == 'end':
# It's the end.
self.p_p = 0
self.out("\n")
self.space = 0
if self.p_p:
self.out((self.br_toggle + '\n' + bq) * self.p_p)
self.space = 0
self.br_toggle = ''
if self.space:
if not self.lastWasNL:
self.out(' ')
self.space = 0
if self.a and ((self.p_p == 2 and self.links_each_paragraph)
or force == "end"):
if force == "end":
self.out("\n")
newa = []
for link in self.a:
if self.outcount > link['outcount']:
self.out(" [" + str(link['count']) + "]: " +
urlparse.urljoin(self.baseurl, link['href']))
if 'title' in link:
self.out(" (" + link['title'] + ")")
self.out("\n")
else:
newa.append(link)
# Don't need an extra line when nothing was done.
if self.a != newa:
self.out("\n")
self.a = newa
if self.abbr_list and force == "end":
for abbr, definition in self.abbr_list.items():
self.out(" *[" + abbr + "]: " + definition + "\n")
self.p_p = 0
self.out(data)
self.outcount += 1
def handle_data(self, data, entity_char=False):
if r'\/script>' in data:
self.quiet -= 1
if self.style:
self.style_def.update(dumb_css_parser(data))
if not self.maybe_automatic_link is None:
href = self.maybe_automatic_link
if (href == data and self.absolute_url_matcher.match(href)
and self.use_automatic_links):
self.o("<" + data + ">")
self.empty_link = False
return
else:
self.o("[")
self.maybe_automatic_link = None
self.empty_link = False
if not self.code and not self.pre and not entity_char:
data = escape_md_section(data, snob=self.escape_snob)
self.o(data, 1)
def unknown_decl(self, data): # pragma: no cover
# TODO: what is this doing here?
pass
def charref(self, name):
if name[0] in ['x', 'X']:
c = int(name[1:], 16)
else:
c = int(name)
if not self.unicode_snob and c in unifiable_n.keys():
return unifiable_n[c]
else:
try:
try:
return unichr(c)
except NameError: # Python3
return chr(c)
except ValueError: # invalid unicode
return ''
def entityref(self, c):
if not self.unicode_snob and c in config.UNIFIABLE.keys():
return config.UNIFIABLE[c]
else:
try:
name2cp(c)
except KeyError:
return "&" + c + ';'
else:
if c == 'nbsp':
return config.UNIFIABLE[c]
else:
try:
return unichr(name2cp(c))
except NameError: # Python3
return chr(name2cp(c))
def replaceEntities(self, s):
s = s.group(1)
if s[0] == "#":
return self.charref(s[1:])
else:
return self.entityref(s)
def unescape(self, s):
return config.RE_UNESCAPE.sub(self.replaceEntities, s)
def google_nest_count(self, style):
"""
Calculate the nesting count of google doc lists
:type style: dict
:rtype: int
"""
nest_count = 0
if 'margin-left' in style:
nest_count = int(style['margin-left'][:-2]) \
// self.google_list_indent
return nest_count
def optwrap(self, text):
"""
Wrap all paragraphs in the provided text.
:type text: str
:rtype: str
"""
if not self.body_width:
return text
assert wrap, "Requires Python 2.3."
result = ''
newlines = 0
# I cannot think of a better solution for now.
# To avoid the non-wrap behaviour for entire paras
# because of the presence of a link in it
if not self.wrap_links:
self.inline_links = False
for para in text.split("\n"):
if len(para) > 0:
if not skipwrap(para, self.wrap_links):
result += "\n".join(wrap(para, self.body_width))
if para.endswith(' '):
result += " \n"
newlines = 1
else:
result += "\n\n"
newlines = 2
else:
# Warning for the tempted!!!
# Be aware that obvious replacement of this with
# line.isspace()
# DOES NOT work! Explanations are welcome.
if not config.RE_SPACE.match(para):
result += para + "\n"
newlines = 1
else:
if newlines < 2:
result += "\n"
newlines += 1
return result
def html2text(html, baseurl='', bodywidth=None):
if bodywidth is None:
bodywidth = config.BODY_WIDTH
h = HTML2Text(baseurl=baseurl, bodywidth=bodywidth)
return h.handle(html)
def unescape(s, unicode_snob=False):
h = HTML2Text()
h.unicode_snob = unicode_snob
return h.unescape(s)
if __name__ == "__main__":
from html2text.cli import main
main()
html2text-2016.1.8/html2text/compat.py 0000644 0001750 0001750 00000000436 12616413406 020370 0 ustar ubuntu ubuntu 0000000 0000000 import sys
if sys.version_info[0] == 2:
import htmlentitydefs
import urlparse
import HTMLParser
import urllib
else:
import urllib.parse as urlparse
import html.entities as htmlentitydefs
import html.parser as HTMLParser
import urllib.request as urllib
html2text-2016.1.8/html2text/config.py 0000644 0001750 0001750 00000006327 12616413406 020357 0 ustar ubuntu ubuntu 0000000 0000000 import re
# Use Unicode characters instead of their ascii psuedo-replacements
UNICODE_SNOB = 0
# Escape all special characters. Output is less readable, but avoids
# corner case formatting issues.
ESCAPE_SNOB = 0
# Put the links after each paragraph instead of at the end.
LINKS_EACH_PARAGRAPH = 0
# Wrap long lines at position. 0 for no wrapping. (Requires Python 2.3.)
BODY_WIDTH = 78
# Don't show internal links (href="#local-anchor") -- corresponding link
# targets won't be visible in the plain text file anyway.
SKIP_INTERNAL_LINKS = True
# Use inline, rather than reference, formatting for images and links
INLINE_LINKS = True
# Protect links from line breaks surrounding them with angle brackets (in
# addition to their square brackets)
PROTECT_LINKS = False
# WRAP_LINKS = True
WRAP_LINKS = True
# Number of pixels Google indents nested lists
GOOGLE_LIST_INDENT = 36
IGNORE_ANCHORS = False
IGNORE_IMAGES = False
IMAGES_TO_ALT = False
IMAGES_WITH_SIZE = False
IGNORE_EMPHASIS = False
MARK_CODE = False
DECODE_ERRORS = 'strict'
# Convert links with same href and text to format if they are absolute links
USE_AUTOMATIC_LINKS = True
# For checking space-only lines on line 771
RE_SPACE = re.compile(r'\s\+')
RE_UNESCAPE = re.compile(r"&(#?[xX]?(?:[0-9a-fA-F]+|\w{1,8}));")
RE_ORDERED_LIST_MATCHER = re.compile(r'\d+\.\s')
RE_UNORDERED_LIST_MATCHER = re.compile(r'[-\*\+]\s')
RE_MD_CHARS_MATCHER = re.compile(r"([\\\[\]\(\)])")
RE_MD_CHARS_MATCHER_ALL = re.compile(r"([`\*_{}\[\]\(\)#!])")
RE_LINK = re.compile(r"(\[.*?\] ?\(.*?\))|(\[.*?\]:.*?)") # to find links in the text
RE_MD_DOT_MATCHER = re.compile(r"""
^ # start of line
(\s*\d+) # optional whitespace and a number
(\.) # dot
(?=\s) # lookahead assert whitespace
""", re.MULTILINE | re.VERBOSE)
RE_MD_PLUS_MATCHER = re.compile(r"""
^
(\s*)
(\+)
(?=\s)
""", flags=re.MULTILINE | re.VERBOSE)
RE_MD_DASH_MATCHER = re.compile(r"""
^
(\s*)
(-)
(?=\s|\-) # followed by whitespace (bullet list, or spaced out hr)
# or another dash (header or hr)
""", flags=re.MULTILINE | re.VERBOSE)
RE_SLASH_CHARS = r'\`*_{}[]()#+-.!'
RE_MD_BACKSLASH_MATCHER = re.compile(r'''
(\\) # match one slash
(?=[%s]) # followed by a char that requires escaping
''' % re.escape(RE_SLASH_CHARS),
flags=re.VERBOSE)
UNIFIABLE = {
'rsquo': "'",
'lsquo': "'",
'rdquo': '"',
'ldquo': '"',
'copy': '(C)',
'mdash': '--',
'nbsp': ' ',
'rarr': '->',
'larr': '<-',
'middot': '*',
'ndash': '-',
'oelig': 'oe',
'aelig': 'ae',
'agrave': 'a',
'aacute': 'a',
'acirc': 'a',
'atilde': 'a',
'auml': 'a',
'aring': 'a',
'egrave': 'e',
'eacute': 'e',
'ecirc': 'e',
'euml': 'e',
'igrave': 'i',
'iacute': 'i',
'icirc': 'i',
'iuml': 'i',
'ograve': 'o',
'oacute': 'o',
'ocirc': 'o',
'otilde': 'o',
'ouml': 'o',
'ugrave': 'u',
'uacute': 'u',
'ucirc': 'u',
'uuml': 'u',
'lrm': '',
'rlm': ''
}
BYPASS_TABLES = False
# Use a single line break after a block element rather an two line breaks.
# NOTE: Requires body width setting to be 0.
SINGLE_LINE_BREAK = False
html2text-2016.1.8/html2text/utils.py 0000644 0001750 0001750 00000013661 12643762105 020254 0 ustar ubuntu ubuntu 0000000 0000000 import sys
from html2text import config
from html2text.compat import htmlentitydefs
def name2cp(k):
"""Return sname to codepoint"""
if k == 'apos':
return ord("'")
return htmlentitydefs.name2codepoint[k]
unifiable_n = {}
for k in config.UNIFIABLE.keys():
unifiable_n[name2cp(k)] = config.UNIFIABLE[k]
def hn(tag):
if tag[0] == 'h' and len(tag) == 2:
try:
n = int(tag[1])
if n in range(1, 10): # pragma: no branch
return n
except ValueError:
return 0
def dumb_property_dict(style):
"""
:returns: A hash of css attributes
"""
out = dict([(x.strip(), y.strip()) for x, y in
[z.split(':', 1) for z in
style.split(';') if ':' in z
]
]
)
return out
def dumb_css_parser(data):
"""
:type data: str
:returns: A hash of css selectors, each of which contains a hash of
css attributes.
:rtype: dict
"""
# remove @import sentences
data += ';'
importIndex = data.find('@import')
while importIndex != -1:
data = data[0:importIndex] + data[data.find(';', importIndex) + 1:]
importIndex = data.find('@import')
# parse the css. reverted from dictionary comprehension in order to
# support older pythons
elements = [x.split('{') for x in data.split('}') if '{' in x.strip()]
try:
elements = dict([(a.strip(), dumb_property_dict(b))
for a, b in elements])
except ValueError: # pragma: no cover
elements = {} # not that important
return elements
def element_style(attrs, style_def, parent_style):
"""
:type attrs: dict
:type style_def: dict
:type style_def: dict
:returns: A hash of the 'final' style attributes of the element
:rtype: dict
"""
style = parent_style.copy()
if 'class' in attrs:
for css_class in attrs['class'].split():
css_style = style_def.get('.' + css_class, {})
style.update(css_style)
if 'style' in attrs:
immediate_style = dumb_property_dict(attrs['style'])
style.update(immediate_style)
return style
def google_list_style(style):
"""
Finds out whether this is an ordered or unordered list
:type style: dict
:rtype: str
"""
if 'list-style-type' in style:
list_style = style['list-style-type']
if list_style in ['disc', 'circle', 'square', 'none']:
return 'ul'
return 'ol'
def google_has_height(style):
"""
Check if the style of the element has the 'height' attribute
explicitly defined
:type style: dict
:rtype: bool
"""
if 'height' in style:
return True
return False
def google_text_emphasis(style):
"""
:type style: dict
:returns: A list of all emphasis modifiers of the element
:rtype: list
"""
emphasis = []
if 'text-decoration' in style:
emphasis.append(style['text-decoration'])
if 'font-style' in style:
emphasis.append(style['font-style'])
if 'font-weight' in style:
emphasis.append(style['font-weight'])
return emphasis
def google_fixed_width_font(style):
"""
Check if the css of the current element defines a fixed width font
:type style: dict
:rtype: bool
"""
font_family = ''
if 'font-family' in style:
font_family = style['font-family']
if 'Courier New' == font_family or 'Consolas' == font_family:
return True
return False
def list_numbering_start(attrs):
"""
Extract numbering from list element attributes
:type attrs: dict
:rtype: int or None
"""
if 'start' in attrs:
try:
return int(attrs['start']) - 1
except ValueError:
pass
return 0
def skipwrap(para, wrap_links):
# If it appears to contain a link
# don't wrap
if (len(config.RE_LINK.findall(para)) > 0) and not wrap_links:
return True
# If the text begins with four spaces or one tab, it's a code block;
# don't wrap
if para[0:4] == ' ' or para[0] == '\t':
return True
# If the text begins with only two "--", possibly preceded by
# whitespace, that's an emdash; so wrap.
stripped = para.lstrip()
if stripped[0:2] == "--" and len(stripped) > 2 and stripped[2] != "-":
return False
# I'm not sure what this is for; I thought it was to detect lists,
# but there's a
-inside- case in one of the tests that
# also depends upon it.
if stripped[0:1] == '-' or stripped[0:1] == '*':
return True
# If the text begins with a single -, *, or +, followed by a space,
# or an integer, followed by a ., followed by a space (in either
# case optionally proceeded by whitespace), it's a list; don't wrap.
if config.RE_ORDERED_LIST_MATCHER.match(stripped) or \
config.RE_UNORDERED_LIST_MATCHER.match(stripped):
return True
return False
def wrapwrite(text):
text = text.encode('utf-8')
try: # Python3
sys.stdout.buffer.write(text)
except AttributeError:
sys.stdout.write(text)
def wrap_read(): # pragma: no cover
"""
:rtype: str
"""
try:
return sys.stdin.read()
except AttributeError:
return sys.stdin.buffer.read()
def escape_md(text):
"""
Escapes markdown-sensitive characters within other markdown
constructs.
"""
return config.RE_MD_CHARS_MATCHER.sub(r"\\\1", text)
def escape_md_section(text, snob=False):
"""
Escapes markdown-sensitive characters across whole document sections.
"""
text = config.RE_MD_BACKSLASH_MATCHER.sub(r"\\\1", text)
if snob:
text = config.RE_MD_CHARS_MATCHER_ALL.sub(r"\\\1", text)
text = config.RE_MD_DOT_MATCHER.sub(r"\1\\\2", text)
text = config.RE_MD_PLUS_MATCHER.sub(r"\1\\\2", text)
text = config.RE_MD_DASH_MATCHER.sub(r"\1\\\2", text)
return text
html2text-2016.1.8/html2text/cli.py 0000644 0001750 0001750 00000020705 12616413406 017655 0 ustar ubuntu ubuntu 0000000 0000000 import optparse
from html2text.compat import urllib
from html2text import HTML2Text, config, __version__
from html2text.utils import wrapwrite, wrap_read
def main():
baseurl = ''
class bcolors: # pragma: no cover
HEADER = '\033[95m'
OKBLUE = '\033[94m'
OKGREEN = '\033[92m'
WARNING = '\033[93m'
FAIL = '\033[91m'
ENDC = '\033[0m'
BOLD = '\033[1m'
UNDERLINE = '\033[4m'
p = optparse.OptionParser(
'%prog [(filename|url) [encoding]]',
version='%prog ' + ".".join(map(str, __version__))
)
p.add_option(
"--no-wrap-links",
dest="wrap_links",
action="store_false",
default=config.WRAP_LINKS,
help="wrap links during conversion"
)
p.add_option(
"--ignore-emphasis",
dest="ignore_emphasis",
action="store_true",
default=config.IGNORE_EMPHASIS,
help="don't include any formatting for emphasis"
)
p.add_option(
"--reference-links",
dest="inline_links",
action="store_false",
default=config.INLINE_LINKS,
help="use reference style links instead of inline links"
)
p.add_option(
"--ignore-links",
dest="ignore_links",
action="store_true",
default=config.IGNORE_ANCHORS,
help="don't include any formatting for links")
p.add_option(
"--protect-links",
dest="protect_links",
action="store_true",
default=config.PROTECT_LINKS,
help=("protect links from line breaks surrounding them " +
"with angle brackets"))
p.add_option(
"--ignore-images",
dest="ignore_images",
action="store_true",
default=config.IGNORE_IMAGES,
help="don't include any formatting for images"
)
p.add_option(
"--images-to-alt",
dest="images_to_alt",
action="store_true",
default=config.IMAGES_TO_ALT,
help="Discard image data, only keep alt text"
)
p.add_option(
"--images-with-size",
dest="images_with_size",
action="store_true",
default=config.IMAGES_WITH_SIZE,
help="Write image tags with height and width attrs as raw html to "
"retain dimensions"
)
p.add_option(
"-g", "--google-doc",
action="store_true",
dest="google_doc",
default=False,
help="convert an html-exported Google Document"
)
p.add_option(
"-d", "--dash-unordered-list",
action="store_true",
dest="ul_style_dash",
default=False,
help="use a dash rather than a star for unordered list items"
)
p.add_option(
"-e", "--asterisk-emphasis",
action="store_true",
dest="em_style_asterisk",
default=False,
help="use an asterisk rather than an underscore for emphasized text"
)
p.add_option(
"-b", "--body-width",
dest="body_width",
action="store",
type="int",
default=config.BODY_WIDTH,
help="number of characters per output line, 0 for no wrap"
)
p.add_option(
"-i", "--google-list-indent",
dest="list_indent",
action="store",
type="int",
default=config.GOOGLE_LIST_INDENT,
help="number of pixels Google indents nested lists"
)
p.add_option(
"-s", "--hide-strikethrough",
action="store_true",
dest="hide_strikethrough",
default=False,
help="hide strike-through text. only relevant when -g is "
"specified as well"
)
p.add_option(
"--escape-all",
action="store_true",
dest="escape_snob",
default=False,
help="Escape all special characters. Output is less readable, but "
"avoids corner case formatting issues."
)
p.add_option(
"--bypass-tables",
action="store_true",
dest="bypass_tables",
default=config.BYPASS_TABLES,
help="Format tables in HTML rather than Markdown syntax."
)
p.add_option(
"--single-line-break",
action="store_true",
dest="single_line_break",
default=config.SINGLE_LINE_BREAK,
help=(
"Use a single line break after a block element rather than two "
"line breaks. NOTE: Requires --body-width=0"
)
)
p.add_option(
"--unicode-snob",
action="store_true",
dest="unicode_snob",
default=config.UNICODE_SNOB,
help="Use unicode throughout document"
)
p.add_option(
"--no-automatic-links",
action="store_false",
dest="use_automatic_links",
default=config.USE_AUTOMATIC_LINKS,
help="Do not use automatic links wherever applicable"
)
p.add_option(
"--no-skip-internal-links",
action="store_false",
dest="skip_internal_links",
default=config.SKIP_INTERNAL_LINKS,
help="Do not skip internal links"
)
p.add_option(
"--links-after-para",
action="store_true",
dest="links_each_paragraph",
default=config.LINKS_EACH_PARAGRAPH,
help="Put links after each paragraph instead of document"
)
p.add_option(
"--mark-code",
action="store_true",
dest="mark_code",
default=config.MARK_CODE,
help="Mark program code blocks with [code]...[/code]"
)
p.add_option(
"--decode-errors",
dest="decode_errors",
action="store",
type="string",
default=config.DECODE_ERRORS,
help="What to do in case of decode errors.'ignore', 'strict' and 'replace' are acceptable values"
)
(options, args) = p.parse_args()
# process input
encoding = "utf-8"
if len(args) > 0 and args[0] != '-': # pragma: no cover
file_ = args[0]
if len(args) == 2:
encoding = args[1]
if len(args) > 2:
p.error('Too many arguments')
if file_.startswith('http://') or file_.startswith('https://'):
baseurl = file_
j = urllib.urlopen(baseurl)
data = j.read()
if encoding is None:
try:
from feedparser import _getCharacterEncoding as enc
except ImportError:
enc = lambda x, y: ('utf-8', 1)
encoding = enc(j.headers, data)[0]
if encoding == 'us-ascii':
encoding = 'utf-8'
else:
data = open(file_, 'rb').read()
if encoding is None:
try:
from chardet import detect
except ImportError:
detect = lambda x: {'encoding': 'utf-8'}
encoding = detect(data)['encoding']
else:
data = wrap_read()
if hasattr(data, 'decode'):
try:
try:
data = data.decode(encoding, errors=options.decode_errors)
except TypeError:
# python 2.6.x does not have the errors option
data = data.decode(encoding)
except UnicodeDecodeError as err:
warning = bcolors.WARNING + "Warning:" + bcolors.ENDC
warning += ' Use the ' + bcolors.OKGREEN
warning += '--decode-errors=ignore' + bcolors.ENDC + 'flag.'
print(warning)
raise err
h = HTML2Text(baseurl=baseurl)
# handle options
if options.ul_style_dash:
h.ul_item_mark = '-'
if options.em_style_asterisk:
h.emphasis_mark = '*'
h.strong_mark = '__'
h.body_width = options.body_width
h.google_list_indent = options.list_indent
h.ignore_emphasis = options.ignore_emphasis
h.ignore_links = options.ignore_links
h.protect_links = options.protect_links
h.ignore_images = options.ignore_images
h.images_to_alt = options.images_to_alt
h.images_with_size = options.images_with_size
h.google_doc = options.google_doc
h.hide_strikethrough = options.hide_strikethrough
h.escape_snob = options.escape_snob
h.bypass_tables = options.bypass_tables
h.single_line_break = options.single_line_break
h.inline_links = options.inline_links
h.unicode_snob = options.unicode_snob
h.use_automatic_links = options.use_automatic_links
h.skip_internal_links = options.skip_internal_links
h.links_each_paragraph = options.links_each_paragraph
h.mark_code = options.mark_code
h.wrap_links = options.wrap_links
wrapwrite(h.handle(data))
html2text-2016.1.8/setup.py 0000644 0001750 0001750 00000004245 12616416405 016316 0 ustar ubuntu ubuntu 0000000 0000000 # coding: utf-8
import sys
from setuptools import setup, Command, find_packages
requires_list = []
try:
import unittest2 as unittest
except ImportError:
import unittest
else:
if sys.version_info <= (2, 6):
requires_list.append("unittest2")
class RunTests(Command):
"""New setup.py command to run all tests for the package.
"""
description = "run all tests for the package"
user_options = []
def initialize_options(self):
pass
def finalize_options(self):
pass
def run(self):
tests = unittest.TestLoader().discover('.')
runner = unittest.TextTestRunner()
results = runner.run(tests)
sys.exit(not results.wasSuccessful())
setup(
name="html2text",
version=".".join(map(str, __import__('html2text').__version__)),
description="Turn HTML into equivalent Markdown-structured text.",
author="Aaron Swartz",
author_email="me@aaronsw.com",
maintainer='Alireza Savand',
maintainer_email='alireza.savand@gmail.com',
url='https://github.com/Alir3z4/html2text/',
cmdclass={'test': RunTests},
platforms='OS Independent',
classifiers=[
'Development Status :: 5 - Production/Stable',
'Intended Audience :: Developers',
'License :: OSI Approved :: GNU General Public License (GPL)',
'Operating System :: OS Independent',
'Programming Language :: Python',
'Programming Language :: Python :: 2',
'Programming Language :: Python :: 2.4',
'Programming Language :: Python :: 2.5',
'Programming Language :: Python :: 2.6',
'Programming Language :: Python :: 2.7',
'Programming Language :: Python :: 3',
'Programming Language :: Python :: 3.0',
'Programming Language :: Python :: 3.1',
'Programming Language :: Python :: 3.2',
'Programming Language :: Python :: 3.3',
'Programming Language :: Python :: 3.4',
],
entry_points="""
[console_scripts]
html2text=html2text.cli:main
""",
license='GNU GPL 3',
requires=requires_list,
packages=find_packages(exclude=['test']),
include_package_data=True,
zip_safe=False,
)
html2text-2016.1.8/COPYING 0000664 0001750 0001750 00000104513 12471110237 015631 0 ustar ubuntu ubuntu 0000000 0000000 GNU GENERAL PUBLIC LICENSE
Version 3, 29 June 2007
Copyright (C) 2007 Free Software Foundation, Inc.
Everyone is permitted to copy and distribute verbatim copies
of this license document, but changing it is not allowed.
Preamble
The GNU General Public License is a free, copyleft license for
software and other kinds of works.
The licenses for most software and other practical works are designed
to take away your freedom to share and change the works. By contrast,
the GNU General Public License is intended to guarantee your freedom to
share and change all versions of a program--to make sure it remains free
software for all its users. We, the Free Software Foundation, use the
GNU General Public License for most of our software; it applies also to
any other work released this way by its authors. You can apply it to
your programs, too.
When we speak of free software, we are referring to freedom, not
price. Our General Public Licenses are designed to make sure that you
have the freedom to distribute copies of free software (and charge for
them if you wish), that you receive source code or can get it if you
want it, that you can change the software or use pieces of it in new
free programs, and that you know you can do these things.
To protect your rights, we need to prevent others from denying you
these rights or asking you to surrender the rights. Therefore, you have
certain responsibilities if you distribute copies of the software, or if
you modify it: responsibilities to respect the freedom of others.
For example, if you distribute copies of such a program, whether
gratis or for a fee, you must pass on to the recipients the same
freedoms that you received. You must make sure that they, too, receive
or can get the source code. And you must show them these terms so they
know their rights.
Developers that use the GNU GPL protect your rights with two steps:
(1) assert copyright on the software, and (2) offer you this License
giving you legal permission to copy, distribute and/or modify it.
For the developers' and authors' protection, the GPL clearly explains
that there is no warranty for this free software. For both users' and
authors' sake, the GPL requires that modified versions be marked as
changed, so that their problems will not be attributed erroneously to
authors of previous versions.
Some devices are designed to deny users access to install or run
modified versions of the software inside them, although the manufacturer
can do so. This is fundamentally incompatible with the aim of
protecting users' freedom to change the software. The systematic
pattern of such abuse occurs in the area of products for individuals to
use, which is precisely where it is most unacceptable. Therefore, we
have designed this version of the GPL to prohibit the practice for those
products. If such problems arise substantially in other domains, we
stand ready to extend this provision to those domains in future versions
of the GPL, as needed to protect the freedom of users.
Finally, every program is threatened constantly by software patents.
States should not allow patents to restrict development and use of
software on general-purpose computers, but in those that do, we wish to
avoid the special danger that patents applied to a free program could
make it effectively proprietary. To prevent this, the GPL assures that
patents cannot be used to render the program non-free.
The precise terms and conditions for copying, distribution and
modification follow.
TERMS AND CONDITIONS
0. Definitions.
"This License" refers to version 3 of the GNU General Public License.
"Copyright" also means copyright-like laws that apply to other kinds of
works, such as semiconductor masks.
"The Program" refers to any copyrightable work licensed under this
License. Each licensee is addressed as "you". "Licensees" and
"recipients" may be individuals or organizations.
To "modify" a work means to copy from or adapt all or part of the work
in a fashion requiring copyright permission, other than the making of an
exact copy. The resulting work is called a "modified version" of the
earlier work or a work "based on" the earlier work.
A "covered work" means either the unmodified Program or a work based
on the Program.
To "propagate" a work means to do anything with it that, without
permission, would make you directly or secondarily liable for
infringement under applicable copyright law, except executing it on a
computer or modifying a private copy. Propagation includes copying,
distribution (with or without modification), making available to the
public, and in some countries other activities as well.
To "convey" a work means any kind of propagation that enables other
parties to make or receive copies. Mere interaction with a user through
a computer network, with no transfer of a copy, is not conveying.
An interactive user interface displays "Appropriate Legal Notices"
to the extent that it includes a convenient and prominently visible
feature that (1) displays an appropriate copyright notice, and (2)
tells the user that there is no warranty for the work (except to the
extent that warranties are provided), that licensees may convey the
work under this License, and how to view a copy of this License. If
the interface presents a list of user commands or options, such as a
menu, a prominent item in the list meets this criterion.
1. Source Code.
The "source code" for a work means the preferred form of the work
for making modifications to it. "Object code" means any non-source
form of a work.
A "Standard Interface" means an interface that either is an official
standard defined by a recognized standards body, or, in the case of
interfaces specified for a particular programming language, one that
is widely used among developers working in that language.
The "System Libraries" of an executable work include anything, other
than the work as a whole, that (a) is included in the normal form of
packaging a Major Component, but which is not part of that Major
Component, and (b) serves only to enable use of the work with that
Major Component, or to implement a Standard Interface for which an
implementation is available to the public in source code form. A
"Major Component", in this context, means a major essential component
(kernel, window system, and so on) of the specific operating system
(if any) on which the executable work runs, or a compiler used to
produce the work, or an object code interpreter used to run it.
The "Corresponding Source" for a work in object code form means all
the source code needed to generate, install, and (for an executable
work) run the object code and to modify the work, including scripts to
control those activities. However, it does not include the work's
System Libraries, or general-purpose tools or generally available free
programs which are used unmodified in performing those activities but
which are not part of the work. For example, Corresponding Source
includes interface definition files associated with source files for
the work, and the source code for shared libraries and dynamically
linked subprograms that the work is specifically designed to require,
such as by intimate data communication or control flow between those
subprograms and other parts of the work.
The Corresponding Source need not include anything that users
can regenerate automatically from other parts of the Corresponding
Source.
The Corresponding Source for a work in source code form is that
same work.
2. Basic Permissions.
All rights granted under this License are granted for the term of
copyright on the Program, and are irrevocable provided the stated
conditions are met. This License explicitly affirms your unlimited
permission to run the unmodified Program. The output from running a
covered work is covered by this License only if the output, given its
content, constitutes a covered work. This License acknowledges your
rights of fair use or other equivalent, as provided by copyright law.
You may make, run and propagate covered works that you do not
convey, without conditions so long as your license otherwise remains
in force. You may convey covered works to others for the sole purpose
of having them make modifications exclusively for you, or provide you
with facilities for running those works, provided that you comply with
the terms of this License in conveying all material for which you do
not control copyright. Those thus making or running the covered works
for you must do so exclusively on your behalf, under your direction
and control, on terms that prohibit them from making any copies of
your copyrighted material outside their relationship with you.
Conveying under any other circumstances is permitted solely under
the conditions stated below. Sublicensing is not allowed; section 10
makes it unnecessary.
3. Protecting Users' Legal Rights From Anti-Circumvention Law.
No covered work shall be deemed part of an effective technological
measure under any applicable law fulfilling obligations under article
11 of the WIPO copyright treaty adopted on 20 December 1996, or
similar laws prohibiting or restricting circumvention of such
measures.
When you convey a covered work, you waive any legal power to forbid
circumvention of technological measures to the extent such circumvention
is effected by exercising rights under this License with respect to
the covered work, and you disclaim any intention to limit operation or
modification of the work as a means of enforcing, against the work's
users, your or third parties' legal rights to forbid circumvention of
technological measures.
4. Conveying Verbatim Copies.
You may convey verbatim copies of the Program's source code as you
receive it, in any medium, provided that you conspicuously and
appropriately publish on each copy an appropriate copyright notice;
keep intact all notices stating that this License and any
non-permissive terms added in accord with section 7 apply to the code;
keep intact all notices of the absence of any warranty; and give all
recipients a copy of this License along with the Program.
You may charge any price or no price for each copy that you convey,
and you may offer support or warranty protection for a fee.
5. Conveying Modified Source Versions.
You may convey a work based on the Program, or the modifications to
produce it from the Program, in the form of source code under the
terms of section 4, provided that you also meet all of these conditions:
a) The work must carry prominent notices stating that you modified
it, and giving a relevant date.
b) The work must carry prominent notices stating that it is
released under this License and any conditions added under section
7. This requirement modifies the requirement in section 4 to
"keep intact all notices".
c) You must license the entire work, as a whole, under this
License to anyone who comes into possession of a copy. This
License will therefore apply, along with any applicable section 7
additional terms, to the whole of the work, and all its parts,
regardless of how they are packaged. This License gives no
permission to license the work in any other way, but it does not
invalidate such permission if you have separately received it.
d) If the work has interactive user interfaces, each must display
Appropriate Legal Notices; however, if the Program has interactive
interfaces that do not display Appropriate Legal Notices, your
work need not make them do so.
A compilation of a covered work with other separate and independent
works, which are not by their nature extensions of the covered work,
and which are not combined with it such as to form a larger program,
in or on a volume of a storage or distribution medium, is called an
"aggregate" if the compilation and its resulting copyright are not
used to limit the access or legal rights of the compilation's users
beyond what the individual works permit. Inclusion of a covered work
in an aggregate does not cause this License to apply to the other
parts of the aggregate.
6. Conveying Non-Source Forms.
You may convey a covered work in object code form under the terms
of sections 4 and 5, provided that you also convey the
machine-readable Corresponding Source under the terms of this License,
in one of these ways:
a) Convey the object code in, or embodied in, a physical product
(including a physical distribution medium), accompanied by the
Corresponding Source fixed on a durable physical medium
customarily used for software interchange.
b) Convey the object code in, or embodied in, a physical product
(including a physical distribution medium), accompanied by a
written offer, valid for at least three years and valid for as
long as you offer spare parts or customer support for that product
model, to give anyone who possesses the object code either (1) a
copy of the Corresponding Source for all the software in the
product that is covered by this License, on a durable physical
medium customarily used for software interchange, for a price no
more than your reasonable cost of physically performing this
conveying of source, or (2) access to copy the
Corresponding Source from a network server at no charge.
c) Convey individual copies of the object code with a copy of the
written offer to provide the Corresponding Source. This
alternative is allowed only occasionally and noncommercially, and
only if you received the object code with such an offer, in accord
with subsection 6b.
d) Convey the object code by offering access from a designated
place (gratis or for a charge), and offer equivalent access to the
Corresponding Source in the same way through the same place at no
further charge. You need not require recipients to copy the
Corresponding Source along with the object code. If the place to
copy the object code is a network server, the Corresponding Source
may be on a different server (operated by you or a third party)
that supports equivalent copying facilities, provided you maintain
clear directions next to the object code saying where to find the
Corresponding Source. Regardless of what server hosts the
Corresponding Source, you remain obligated to ensure that it is
available for as long as needed to satisfy these requirements.
e) Convey the object code using peer-to-peer transmission, provided
you inform other peers where the object code and Corresponding
Source of the work are being offered to the general public at no
charge under subsection 6d.
A separable portion of the object code, whose source code is excluded
from the Corresponding Source as a System Library, need not be
included in conveying the object code work.
A "User Product" is either (1) a "consumer product", which means any
tangible personal property which is normally used for personal, family,
or household purposes, or (2) anything designed or sold for incorporation
into a dwelling. In determining whether a product is a consumer product,
doubtful cases shall be resolved in favor of coverage. For a particular
product received by a particular user, "normally used" refers to a
typical or common use of that class of product, regardless of the status
of the particular user or of the way in which the particular user
actually uses, or expects or is expected to use, the product. A product
is a consumer product regardless of whether the product has substantial
commercial, industrial or non-consumer uses, unless such uses represent
the only significant mode of use of the product.
"Installation Information" for a User Product means any methods,
procedures, authorization keys, or other information required to install
and execute modified versions of a covered work in that User Product from
a modified version of its Corresponding Source. The information must
suffice to ensure that the continued functioning of the modified object
code is in no case prevented or interfered with solely because
modification has been made.
If you convey an object code work under this section in, or with, or
specifically for use in, a User Product, and the conveying occurs as
part of a transaction in which the right of possession and use of the
User Product is transferred to the recipient in perpetuity or for a
fixed term (regardless of how the transaction is characterized), the
Corresponding Source conveyed under this section must be accompanied
by the Installation Information. But this requirement does not apply
if neither you nor any third party retains the ability to install
modified object code on the User Product (for example, the work has
been installed in ROM).
The requirement to provide Installation Information does not include a
requirement to continue to provide support service, warranty, or updates
for a work that has been modified or installed by the recipient, or for
the User Product in which it has been modified or installed. Access to a
network may be denied when the modification itself materially and
adversely affects the operation of the network or violates the rules and
protocols for communication across the network.
Corresponding Source conveyed, and Installation Information provided,
in accord with this section must be in a format that is publicly
documented (and with an implementation available to the public in
source code form), and must require no special password or key for
unpacking, reading or copying.
7. Additional Terms.
"Additional permissions" are terms that supplement the terms of this
License by making exceptions from one or more of its conditions.
Additional permissions that are applicable to the entire Program shall
be treated as though they were included in this License, to the extent
that they are valid under applicable law. If additional permissions
apply only to part of the Program, that part may be used separately
under those permissions, but the entire Program remains governed by
this License without regard to the additional permissions.
When you convey a copy of a covered work, you may at your option
remove any additional permissions from that copy, or from any part of
it. (Additional permissions may be written to require their own
removal in certain cases when you modify the work.) You may place
additional permissions on material, added by you to a covered work,
for which you have or can give appropriate copyright permission.
Notwithstanding any other provision of this License, for material you
add to a covered work, you may (if authorized by the copyright holders of
that material) supplement the terms of this License with terms:
a) Disclaiming warranty or limiting liability differently from the
terms of sections 15 and 16 of this License; or
b) Requiring preservation of specified reasonable legal notices or
author attributions in that material or in the Appropriate Legal
Notices displayed by works containing it; or
c) Prohibiting misrepresentation of the origin of that material, or
requiring that modified versions of such material be marked in
reasonable ways as different from the original version; or
d) Limiting the use for publicity purposes of names of licensors or
authors of the material; or
e) Declining to grant rights under trademark law for use of some
trade names, trademarks, or service marks; or
f) Requiring indemnification of licensors and authors of that
material by anyone who conveys the material (or modified versions of
it) with contractual assumptions of liability to the recipient, for
any liability that these contractual assumptions directly impose on
those licensors and authors.
All other non-permissive additional terms are considered "further
restrictions" within the meaning of section 10. If the Program as you
received it, or any part of it, contains a notice stating that it is
governed by this License along with a term that is a further
restriction, you may remove that term. If a license document contains
a further restriction but permits relicensing or conveying under this
License, you may add to a covered work material governed by the terms
of that license document, provided that the further restriction does
not survive such relicensing or conveying.
If you add terms to a covered work in accord with this section, you
must place, in the relevant source files, a statement of the
additional terms that apply to those files, or a notice indicating
where to find the applicable terms.
Additional terms, permissive or non-permissive, may be stated in the
form of a separately written license, or stated as exceptions;
the above requirements apply either way.
8. Termination.
You may not propagate or modify a covered work except as expressly
provided under this License. Any attempt otherwise to propagate or
modify it is void, and will automatically terminate your rights under
this License (including any patent licenses granted under the third
paragraph of section 11).
However, if you cease all violation of this License, then your
license from a particular copyright holder is reinstated (a)
provisionally, unless and until the copyright holder explicitly and
finally terminates your license, and (b) permanently, if the copyright
holder fails to notify you of the violation by some reasonable means
prior to 60 days after the cessation.
Moreover, your license from a particular copyright holder is
reinstated permanently if the copyright holder notifies you of the
violation by some reasonable means, this is the first time you have
received notice of violation of this License (for any work) from that
copyright holder, and you cure the violation prior to 30 days after
your receipt of the notice.
Termination of your rights under this section does not terminate the
licenses of parties who have received copies or rights from you under
this License. If your rights have been terminated and not permanently
reinstated, you do not qualify to receive new licenses for the same
material under section 10.
9. Acceptance Not Required for Having Copies.
You are not required to accept this License in order to receive or
run a copy of the Program. Ancillary propagation of a covered work
occurring solely as a consequence of using peer-to-peer transmission
to receive a copy likewise does not require acceptance. However,
nothing other than this License grants you permission to propagate or
modify any covered work. These actions infringe copyright if you do
not accept this License. Therefore, by modifying or propagating a
covered work, you indicate your acceptance of this License to do so.
10. Automatic Licensing of Downstream Recipients.
Each time you convey a covered work, the recipient automatically
receives a license from the original licensors, to run, modify and
propagate that work, subject to this License. You are not responsible
for enforcing compliance by third parties with this License.
An "entity transaction" is a transaction transferring control of an
organization, or substantially all assets of one, or subdividing an
organization, or merging organizations. If propagation of a covered
work results from an entity transaction, each party to that
transaction who receives a copy of the work also receives whatever
licenses to the work the party's predecessor in interest had or could
give under the previous paragraph, plus a right to possession of the
Corresponding Source of the work from the predecessor in interest, if
the predecessor has it or can get it with reasonable efforts.
You may not impose any further restrictions on the exercise of the
rights granted or affirmed under this License. For example, you may
not impose a license fee, royalty, or other charge for exercise of
rights granted under this License, and you may not initiate litigation
(including a cross-claim or counterclaim in a lawsuit) alleging that
any patent claim is infringed by making, using, selling, offering for
sale, or importing the Program or any portion of it.
11. Patents.
A "contributor" is a copyright holder who authorizes use under this
License of the Program or a work on which the Program is based. The
work thus licensed is called the contributor's "contributor version".
A contributor's "essential patent claims" are all patent claims
owned or controlled by the contributor, whether already acquired or
hereafter acquired, that would be infringed by some manner, permitted
by this License, of making, using, or selling its contributor version,
but do not include claims that would be infringed only as a
consequence of further modification of the contributor version. For
purposes of this definition, "control" includes the right to grant
patent sublicenses in a manner consistent with the requirements of
this License.
Each contributor grants you a non-exclusive, worldwide, royalty-free
patent license under the contributor's essential patent claims, to
make, use, sell, offer for sale, import and otherwise run, modify and
propagate the contents of its contributor version.
In the following three paragraphs, a "patent license" is any express
agreement or commitment, however denominated, not to enforce a patent
(such as an express permission to practice a patent or covenant not to
sue for patent infringement). To "grant" such a patent license to a
party means to make such an agreement or commitment not to enforce a
patent against the party.
If you convey a covered work, knowingly relying on a patent license,
and the Corresponding Source of the work is not available for anyone
to copy, free of charge and under the terms of this License, through a
publicly available network server or other readily accessible means,
then you must either (1) cause the Corresponding Source to be so
available, or (2) arrange to deprive yourself of the benefit of the
patent license for this particular work, or (3) arrange, in a manner
consistent with the requirements of this License, to extend the patent
license to downstream recipients. "Knowingly relying" means you have
actual knowledge that, but for the patent license, your conveying the
covered work in a country, or your recipient's use of the covered work
in a country, would infringe one or more identifiable patents in that
country that you have reason to believe are valid.
If, pursuant to or in connection with a single transaction or
arrangement, you convey, or propagate by procuring conveyance of, a
covered work, and grant a patent license to some of the parties
receiving the covered work authorizing them to use, propagate, modify
or convey a specific copy of the covered work, then the patent license
you grant is automatically extended to all recipients of the covered
work and works based on it.
A patent license is "discriminatory" if it does not include within
the scope of its coverage, prohibits the exercise of, or is
conditioned on the non-exercise of one or more of the rights that are
specifically granted under this License. You may not convey a covered
work if you are a party to an arrangement with a third party that is
in the business of distributing software, under which you make payment
to the third party based on the extent of your activity of conveying
the work, and under which the third party grants, to any of the
parties who would receive the covered work from you, a discriminatory
patent license (a) in connection with copies of the covered work
conveyed by you (or copies made from those copies), or (b) primarily
for and in connection with specific products or compilations that
contain the covered work, unless you entered into that arrangement,
or that patent license was granted, prior to 28 March 2007.
Nothing in this License shall be construed as excluding or limiting
any implied license or other defenses to infringement that may
otherwise be available to you under applicable patent law.
12. No Surrender of Others' Freedom.
If conditions are imposed on you (whether by court order, agreement or
otherwise) that contradict the conditions of this License, they do not
excuse you from the conditions of this License. If you cannot convey a
covered work so as to satisfy simultaneously your obligations under this
License and any other pertinent obligations, then as a consequence you may
not convey it at all. For example, if you agree to terms that obligate you
to collect a royalty for further conveying from those to whom you convey
the Program, the only way you could satisfy both those terms and this
License would be to refrain entirely from conveying the Program.
13. Use with the GNU Affero General Public License.
Notwithstanding any other provision of this License, you have
permission to link or combine any covered work with a work licensed
under version 3 of the GNU Affero General Public License into a single
combined work, and to convey the resulting work. The terms of this
License will continue to apply to the part which is the covered work,
but the special requirements of the GNU Affero General Public License,
section 13, concerning interaction through a network will apply to the
combination as such.
14. Revised Versions of this License.
The Free Software Foundation may publish revised and/or new versions of
the GNU General Public License from time to time. Such new versions will
be similar in spirit to the present version, but may differ in detail to
address new problems or concerns.
Each version is given a distinguishing version number. If the
Program specifies that a certain numbered version of the GNU General
Public License "or any later version" applies to it, you have the
option of following the terms and conditions either of that numbered
version or of any later version published by the Free Software
Foundation. If the Program does not specify a version number of the
GNU General Public License, you may choose any version ever published
by the Free Software Foundation.
If the Program specifies that a proxy can decide which future
versions of the GNU General Public License can be used, that proxy's
public statement of acceptance of a version permanently authorizes you
to choose that version for the Program.
Later license versions may give you additional or different
permissions. However, no additional obligations are imposed on any
author or copyright holder as a result of your choosing to follow a
later version.
15. Disclaimer of Warranty.
THERE IS NO WARRANTY FOR THE PROGRAM, TO THE EXTENT PERMITTED BY
APPLICABLE LAW. EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT
HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY
OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO,
THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
PURPOSE. THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE PROGRAM
IS WITH YOU. SHOULD THE PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF
ALL NECESSARY SERVICING, REPAIR OR CORRECTION.
16. Limitation of Liability.
IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING
WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MODIFIES AND/OR CONVEYS
THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES, INCLUDING ANY
GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING OUT OF THE
USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED TO LOSS OF
DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD
PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER PROGRAMS),
EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF
SUCH DAMAGES.
17. Interpretation of Sections 15 and 16.
If the disclaimer of warranty and limitation of liability provided
above cannot be given local legal effect according to their terms,
reviewing courts shall apply local law that most closely approximates
an absolute waiver of all civil liability in connection with the
Program, unless a warranty or assumption of liability accompanies a
copy of the Program in return for a fee.
END OF TERMS AND CONDITIONS
How to Apply These Terms to Your New Programs
If you develop a new program, and you want it to be of the greatest
possible use to the public, the best way to achieve this is to make it
free software which everyone can redistribute and change under these terms.
To do so, attach the following notices to the program. It is safest
to attach them to the start of each source file to most effectively
state the exclusion of warranty; and each file should have at least
the "copyright" line and a pointer to where the full notice is found.
Copyright (C)
This program is free software: you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation, either version 3 of the License, or
(at your option) any later version.
This program is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU General Public License for more details.
You should have received a copy of the GNU General Public License
along with this program. If not, see .
Also add information on how to contact you by electronic and paper mail.
If the program does terminal interaction, make it output a short
notice like this when it starts in an interactive mode:
Copyright (C)
This program comes with ABSOLUTELY NO WARRANTY; for details type `show w'.
This is free software, and you are welcome to redistribute it
under certain conditions; type `show c' for details.
The hypothetical commands `show w' and `show c' should show the appropriate
parts of the General Public License. Of course, your program's commands
might be different; for a GUI interface, you would use an "about box".
You should also get your employer (if you work as a programmer) or school,
if any, to sign a "copyright disclaimer" for the program, if necessary.
For more information on this, and how to apply and follow the GNU GPL, see
.
The GNU General Public License does not permit incorporating your program
into proprietary programs. If your program is a subroutine library, you
may consider it more useful to permit linking proprietary applications with
the library. If this is what you want to do, use the GNU Lesser General
Public License instead of this License. But first, please read
.
html2text-2016.1.8/AUTHORS.rst 0000644 0001750 0001750 00000001232 12616413406 016452 0 ustar ubuntu ubuntu 0000000 0000000 ``html2text`` was originally written by Aaron Swartz.
The AUTHORS/Contributors are (and/or have been):
* Aaron Swartz
* Yariv Barkan
* Alex Musayev
* Matěj Cepl
* Stefano Rivera
* Alireza Savand
* Ivan Gromov
* Jocelyn Delalande
* Matt Dorn
* Miguel Tavares
* Scott Blackburn
* Peter Wu
* Arjoonn Sharma
* Ali Mohammad
* Albert Berger
* Etienne Millon
* John C F
Maintainer:
* Alireza Savand