Open ndarville opened 10 years ago
from baseparser import BaseParser
from BeautifulSoup import BeautifulSoup
class InformationParser(BaseParser):
feeder_pat = '^http://www.dr.dk/Nyheder/(Politik|Indland|Udland)/'
feeder_pages = [
'http://www.dr.dk/nyheder/allenyheder/indland',
'http://www.dr.dk/nyheder/allenyheder/udland',
'http://www.dr.dk/nyheder/allenyheder/politik'
]
def _parse(self, html):
"""Retrieve and serve the required fields to create an entry."""
soup = BeautifulSoup(html,
convertEntities=BeautifulSoup.HTML_ENTITIES,
fromEncoding='utf-8')
self.meta = soup.findAll('meta')
self.title = soup.find('h1').getText()
self.date = soup.find('time', {'itemprop': 'datetime'}).getText()
self.byline = soup.find('span', 'author-name').next.getText()
# body_container = ('div', 'wcms-article-content')
# body_summary = body_container.find('p', 'summary').getText()
self.body = ""
The articles don’t have a container, so FML.