extractors.py

Revision 159, 0.6 kB (checked in by dsandler, 2 years ago)
The refactoring monster was here. Now Digg's link-extraction code is factored out, so other sites can be added.

Line
1	import sys ; sys.path.append('lib')
2	from BeautifulSoup import BeautifulSoup
3	from utils import *
4
5	class DefaultExtractor:
6	def __init__(self): pass
7	def get_link(self,link):
8	return link
9
10	class DiggExtractor(DefaultExtractor):
11	def get_link(self,link):
12	page = urlfetch(link)
13	soup = BeautifulSoup(page)
14	# <div class="news-full" id="main0" style="z-index:1000"><div class="news-body"><h3 id="title1"><a href="http://www.chron.com/disp/story.mpl/ap/politics/3654155.html" >
15	title = soup.first('h3')
16	coral_url = title.a['href']
17	return coral_url

Note: See TracBrowser for help on using the browser.