|
|
|
@ -13,3 +13,10 @@ Based on:
|
|
|
|
|
- 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/ )
|
|
|
|
|
|
|
|
|
|
Usage:
|
|
|
|
|
|
|
|
|
|
import urllib
|
|
|
|
|
html = urllib.urlopen(url).read()
|
|
|
|
|
readable_article = Document(html).summary()
|
|
|
|
|
readable_title = Document(html).short_title()
|
|
|
|
|