2016-04-27 15 views
0

Ich stieß auf den folgenden Code in dem Programm Programmierung kollektive Intelligenz namens newfeatures.py.News Clustering-Programm zeigt keine Links in Python

Hier ist der Code:

import feedparser 
import re 
feedlist=['http://today.reuters.com/rss/topNews', 
      'http://today.reuters.com/rss/domesticNews', 
      'http://today.reuters.com/rss/worldNews', 
      'http://hosted.ap.org/lineups/TOPHEADS-rss_2.0.xml', 
      'http://hosted.ap.org/lineups/USHEADS-rss_2.0.xml', 
      'http://hosted.ap.org/lineups/WORLDHEADS-rss_2.0.xml', 
      'http://hosted.ap.org/lineups/POLITICSHEADS-rss_2.0.xml', 
      'http://www.nytimes.com/services/xml/rss/nyt/HomePage.xml', 
      'http://www.nytimes.com/services/xml/rss/nyt/International.xml', 
      'http://news.google.com/?output=rss', 
      'http://feeds.salon.com/salon/news', 
      'http://www.foxnews.com/xmlfeed/rss/0,4313,0,00.rss', 
      'http://www.foxnews.com/xmlfeed/rss/0,4313,80,00.rss', 
      'http://www.foxnews.com/xmlfeed/rss/0,4313,81,00.rss', 
      'http://rss.cnn.com/rss/edition.rss', 
      'http://rss.cnn.com/rss/edition_world.rss', 
      'http://rss.cnn.com/rss/edition_us.rss'] 
def stripHTML(h): 
    p='' 
    s=0 
    for c in h: 
     if c=='<': s=1 
     elif c=='>': 
      s=0 
      p+=' ' 
     elif s==0: p+=c 
    return p 
def separatewords(text): 
    splitter=re.compile('\\W*') 
    return [s.lower() for s in splitter.split(text) if len(s)>3] 
def getarticlewords(): 
    allwords={} 
    articlewords=[] 
    articletitles=[] 
    ec=0 
    # Loop over every feed 
    for feed in feedlist: 
     f=feedparser.parse(feed) 
     # Loop over every article 
     for e in f.entries: 
      # Ignore identical articles 
      if e.title in articletitles: continue 
      # Extract the words 
      txt=e.title.encode('utf8')+stripHTML(e.description.encode('utf8')) 
      words=separatewords(txt) 
      articlewords.append({}) 
      articletitles.append(e.title) 
      # Increase the counts for this word in allwords and in articlewords 
      for word in words: 
       allwords.setdefault(word,0) 
       allwords[word]+=1 
       articlewords[ec].setdefault(word,0) 
       articlewords[ec][word]+=1 
      ec+=1 
    return allwords,articlewords,articletitles 
def makematrix(allw,articlew): 
    wordvec=[] 
    # Only take words that are common but not too common 
    for w,c in allw.items(): 
     if c>3 and c<len(articlew)*0.6: 
      wordvec.append(w) 
    # Create the word matrix 
    l1=[[(word in f and f[word] or 0) for word in wordvec] for f in articlew] 
    return l1,wordvec 
from numpy import * 
def showfeatures(w,h,titles,wordvec,out='features.txt'): 
    outfile=file(out,'w') 
    pc,wc=shape(h) 
    toppatterns=[[] for i in range(len(titles))] 
    patternnames=[] 
    # Loop over all the features 
    for i in range(pc): 
     slist=[] 
     # Create a list of words and their weights 
     for j in range(wc): 
      slist.append((h[i,j],wordvec[j])) 
     # Reverse sort the word list 
     slist.sort() 
     slist.reverse() 
     # Print the first six elements 
     n=[s[1] for s in slist[0:6]] 
     outfile.write(str(n)+'\n') 
     patternnames.append(n) 
     # Create a list of articles for this feature 
     flist=[] 
     for j in range(len(titles)): 
      # Add the article with its weight 
      flist.append((w[j,i],titles[j])) 
      toppatterns[j].append((w[j,i],i,titles[j])) 
     # Reverse sort the list 
     flist.sort() 
     flist.reverse() 
     # Show the top 3 articles 
     for f in flist[0:3]: 
      outfile.write(str(f)+'\n') 
     outfile.write('\n') 
    outfile.close() 
    # Return the pattern names for later use 
    return toppatterns,patternnames 

Die Nutzung ist wie folgt:

>>> import newsfeatures 
>>> allw,artw,artt= newsfeatures.getarticlewords() 
>>> artt[1] 
u'Fatah, Hamas men abducted freed: sources' 

Wie Sie sehen können, diese Linie, produziert die Schlagzeile.

>>> artt[1] 
u'Fatah, Hamas men abducted freed: sources' 

Was will ich weiß, ist, ist es, durch die someway das Programm nicht nur die Überschrift zeigt, sondern zeigt auch die Quelle der Überschrift vom feedlist.

Konnte jemand helfen?

Dank!

+0

Ändern Sie die 'getarticlewords' Funktion und lesen Sie die [' feedparser' Dokumentation] (http://pythonhosted.org/feedparser/) . Es gibt eine Reihe von Eigenschaften wie 'feed.publisher' und' feed.title' und 'entries [i] .link', die wahrscheinlich enthalten, was Sie wollen. – ChrisP

+0

OMG, dieser schlechte Code ist * wirklich * in einem Buch gewesen?!? –

Antwort

1

ersetzen

articletitles.append(e.title) 

in getarticlewords() mit so etwas wie

articletitles.append(' '.join([e.title, ', from', feed]))