|
|
@@ -37,17 +37,11 @@ class Source():
|
|
|
|
|
|
class LinkList():
|
|
|
def __init__(self,url,selector=None,rss=False):
|
|
|
+ self.links=[]
|
|
|
if rss:
|
|
|
feed = feedparser.parse(url)
|
|
|
- print(feed["bozo"])
|
|
|
- #print(feed["channel"])
|
|
|
- for i in feed["items"]:
|
|
|
- print(i["date"])
|
|
|
- print(i["date_parsed"])
|
|
|
- print(i["title"])
|
|
|
- print(i["summary"])
|
|
|
- print(i["link"])
|
|
|
- self.links=[]
|
|
|
+ #print(feed["bozo"]) FIXME: If bozo==1 => error
|
|
|
+ self.links=[i["link"] for i in feed["items"]]
|
|
|
return
|
|
|
if selector is None:
|
|
|
#s=newspaper.build(url,language="en",memoize_articles=False) #memoize puede salvarme la vida
|
|
|
@@ -59,26 +53,11 @@ class LinkList():
|
|
|
s.parse_categories()
|
|
|
s.generate_articles()
|
|
|
|
|
|
- for a in s.articles:
|
|
|
- self.articlePrinter(a)
|
|
|
- print(s.size())
|
|
|
+ self.links=[a.url for a in s.articles]
|
|
|
else:
|
|
|
f=FrontPage(url,selector)
|
|
|
- for l in f.links:
|
|
|
- print(l)
|
|
|
self.links=f.links
|
|
|
|
|
|
- def articlePrinter(self,a):
|
|
|
- print(a.url)
|
|
|
-# def getList(self):
|
|
|
-# ret=[]
|
|
|
-# for art in self.source.articles:
|
|
|
-# print(art)
|
|
|
-# print(art.url)
|
|
|
-# ret.append(art.url)
|
|
|
-# return ret
|
|
|
-
|
|
|
-
|
|
|
class News():
|
|
|
r=re.compile(r"hours? ago|yesterday|today|last week|month",flags=re.IGNORECASE)
|
|
|
def __init__(self,url,lang="en"):
|
|
|
@@ -126,6 +105,10 @@ l=LinkList("http://officialandroid.blogspot.com/atom.xml",rss=True)
|
|
|
#n=News("http://www.alibabagroup.com/en/news/article?news=p150908b")
|
|
|
#n=News("http://phx.corporate-ir.net/phoenix.zhtml?c=176060&p=irol-newsArticle&ID=1250170")
|
|
|
#n=News("http://about.americanexpress.com/news/pr/2016/amex-dividend-payable-august-10-2016.aspx")
|
|
|
+
|
|
|
+for a in l.links:
|
|
|
+ print(a)
|
|
|
+print(len(l.links))
|
|
|
sys.exit(1)
|
|
|
def sanitizeSelector(s):
|
|
|
s=s.replace(">a","> a")
|
