#!/usr/bin/env python3 from news import News from db import db from pprint import pprint d = db() cat = 1 kw = d.get_keywords(cat) f = open("links") links = f.read().split('\n') f.close() not_matched=[] matched=[] for url in links: if url == "": continue n = News(url, "57351207d47db2159a918636", "9to5", cat, kw) out = n.get() if out is not None and "weight" in out and out["weight"] > 1: matched.append(url) continue not_matched.append(url) #print("[DID NOT MATCH] %s" % url) p = {} p["kw"] = out["kw"] p["matches"] = out["matches"] p["title"] = out["title"] p["url"] = out["url"] p["weight"] = out["weight"] p["text"] = out["text"] #pprint(out) # print("#######################################") # d.insert_article(n.get()) # forbesUtilCookie={'toURL':'http://www.forbes.com/sites/lizryan/2016/05/21/want-to-hire-great-people-stop-asking-stupid-interview-questions/','refURL':'','referrer':''}; # Path=/; Domain=.forbes.com; Expires=Session for n in matched: print("[KEYWORD MATCH] %s" % n) for n in not_matched: print("[DID NOT MATCH] %s" % n)