feedparser 학습 요약

>>> import feedparser
>>> d = feedparser.parse('http://willzh.iteye.com/rss')
>>> d['feed']['title']
u"Will's Blog"

>>> import feedparser
>>> d = feedparser.parse("http://feedparser.org/docs/examples/atom10.xml")
>>> d['feed']['title']             # feed data is a dictionary
u'Sample Feed'
>>> d.feed.title                   # get values attr-style or dict-style
u'Sample Feed'
>>> d.channel.title                # use RSS or Atom terminology anywhere
u'Sample Feed'
>>> d.feed.link                    # resolves relative links
u'http://example.org/'
>>> d.feed.subtitle                 # parses escaped HTML
u'For documentation <em>only</em>'
>>> d.channel.description          # RSS terminology works here too
u'For documentation <em>only</em>'
>>> len(d['entries'])              # entries are a list
1
>>> d['entries'][0]['title']       # each entry is a dictionary
u'First entry title'
>>> d.entries[0].title             # attr-style works here too
u'First entry title'
>>> d['items'][0].title            # RSS terminology works here too
u'First entry title'
>>> e = d.entries[0]
>>> e.link                         # easy access to alternate link
u'http://example.org/entry/3'
>>> e.links[1].rel                 # full access to all Atom links
u'related'
>>> e.links[0].href                # resolves relative links here too
u'http://example.org/entry/3'
>>> e.author_detail.name           # author data is a dictionary
u'Mark Pilgrim'
>>> e.updated_parsed              # parses all date formats
(2005, 11, 9, 11, 56, 34, 2, 313, 0)
>>> e.content[0].value             # sanitizes dangerous HTML
u'<div>Watch out for <em>nasty tricks</em></div>'
>>> d.version                      # reports feed type and version
u'atom10'
>>> d.encoding                     # auto-detects character encoding
u'utf-8'
>>> d.headers.get('Content-type')  # full access to all HTTP headers
u'application/xml'