def get_details_page_prefix(self):
return "wsj-details-%s" % (self.page_title)
+ def find_image(self, item):
+ image = item.findtext('image')
+ if image is not None:
+ url = image.get('url')
+ return url
+ return None
+
def should_use_https(self):
return True
def item_is_interesting_for_headlines(self, title, description, item):
+ if self.is_item_older_than_n_days(item, 7):
+ return False
return ("WSJ.com" not in title and
"WSJ.com" not in description)
def item_is_interesting_for_article(self, title, description, item):
+ if self.is_item_older_than_n_days(item, 7):
+ return False
return ("WSJ.com" not in title and
"WSJ.com" not in description)