diff --git a/README b/README deleted file mode 100644 index e3d40b3..0000000 --- a/README +++ /dev/null @@ -1,62 +0,0 @@ -This code is under the Apache License 2.0. http://www.apache.org/licenses/LICENSE-2.0 - -This is a python port of a ruby port of arc90's readability project - -http://lab.arc90.com/experiments/readability/ - -In few words, -Given a html document, it pulls out the main body text and cleans it up. -It also can clean up title based on latest readability.js code. - -Based on: - - Latest readability.js ( https://github.com/MHordecki/readability-redux/blob/master/readability/readability.js ) - - Ruby port by starrhorne and iterationlabs - - Python port by gfxmonk ( https://github.com/gfxmonk/python-readability , based on BeautifulSoup ) - - Decruft effort to move to lxml ( http://www.minvolai.com/blog/decruft-arc90s-readability-in-python/ ) - - "BR to P" fix from readability.js which improves quality for smaller texts. - - Github users contributions. - -Installation:: - - easy_install readability-lxml - or - pip install readability-lxml - -Usage:: - - from readability.readability import Document - import urllib - html = urllib.urlopen(url).read() - readable_article = Document(html).summary() - readable_title = Document(html).short_title() - -Command-line usage:: - - python -m readability.readability -u http://pypi.python.org/pypi/readability-lxml - -To open resulting page in browser:: - - python -m readability.readability -b -u http://pypi.python.org/pypi/readability-lxml - -Using positive/negative keywords example:: - - python -m readability.readability -p intro -n newsindex,homepage-box,news-section -u http://python.org - - -Document() kwarg options: - - - attributes: - - debug: output debug messages - - min_text_length: - - retry_length: - - url: will allow adjusting links to be absolute - - positive_keywords: the list of positive search patterns in classes and ids, for example: ["news-item", "block"] - - negative_keywords: the list of negative search patterns in classes and ids, for example: ["mysidebar", "related", "ads"] - - -Updates - - - 0.3 Added Document.encoding, positive_keywords and negative_keywords - - 0.4 Added Videos loading and allowed more images per paragraph - - 0.5 Preparing a release to support Python versions 2.6, 2.7, 3.3 and 3.4 - - 0.6 Finally a release which supports Python versions 2.6, 2.7, 3.3 and 3.4 diff --git a/README.rst b/README.rst new file mode 100644 index 0000000..a2a1c8c --- /dev/null +++ b/README.rst @@ -0,0 +1,61 @@ +python-readability +================== + +Given a html document, it pulls out the main body text and cleans it up. + +This is a python port of a ruby port of `arc90's readability +project `__. + +Installation +------------ + +It's easy using ``pip``, just run: + +:: + + $ pip install readability-lxml + +Usage +----- + +:: + + >> import requests + >> from readability import Document + >> + >> response = requests.get('http://example.com') + >> doc = Document(response.text) + >> doc.title() + >> 'Example Domain' + +Change Log +---------- + +- 0.3 Added Document.encoding, positive\_keywords and + negative\_keywords +- 0.4 Added Videos loading and allowed more images per paragraph +- 0.5 Preparing a release to support Python versions 2.6, 2.7, 3.3 and + 3.4 +- 0.6 Finally a release which supports Python versions 2.6, 2.7, 3.3 + and 3.4 + +Licensing +========= + +This code is under `the Apache License +2.0 `__ license. + +Thanks to +--------- + +- Latest + `readability.js `__ +- Ruby port by starrhorne and iterationlabs +- `Python port `__ by + gfxmonk +- `Decruft + effort `__ + to move to lxml +- "BR to P" fix from readability.js which improves quality for smaller + texts +- Github users contributions. diff --git a/setup.py b/setup.py index 371dac9..18a4fae 100755 --- a/setup.py +++ b/setup.py @@ -19,7 +19,7 @@ setup( author_email="burchik@gmail.com", description="fast html to text parser (article readability tool) with python3 support", test_suite = "tests.test_article_only", - long_description=open("README").read(), + long_description=open("README.rst").read(), license="Apache License 2.0", url="http://github.com/buriy/python-readability", packages=['readability', 'readability.compat'],