Created
October 23, 2010 18:30
-
-
Save psychemedia/642527 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| import re, urllib, simplejson,csv | |
| import xml.sax.saxutils as saxutils | |
| from urlparse import urlparse | |
| fname="homepageurls2.csv" | |
| def opmlFromCSV(fname): | |
| fout="test" | |
| fo=open(fout+'.xml','w') | |
| writeOPMLHeadopenBody(fo) | |
| f = csv.reader(open(fname, "rb")) | |
| #url="http://ukwebfocus.wordpress.com" | |
| first=True | |
| curr='' | |
| for line in f: | |
| url,tag=line | |
| if curr!=tag: | |
| if first is True: | |
| first=False | |
| else: | |
| closeOPMLoutline(fo) | |
| curr=tag | |
| openOPMLoutline(fo,tag) | |
| handleOPMLitem(fo,url) | |
| closeOPMLoutline(fo) | |
| closeOPMLbody(fo) | |
| fo.close() | |
| def handleOPMLitem(fo,url): | |
| if url !='': | |
| try: | |
| urls = re.findall('http[s]?://(?:[a-zA-Z]|[0-9]|[$-_@.&+]|[!*\(\),]|(?:%[0-9a-fA-F][0-9a-fA-F]))+', url) | |
| for url in urls: | |
| print "testing",url | |
| o=url | |
| url='http://query.yahooapis.com/v1/public/yql/psychemedia/feedautodetect?url='+urllib.quote(url)+'&format=json' | |
| try: | |
| data = simplejson.load(urllib.urlopen(url)) | |
| if data['query']['count']>'0': | |
| print data['query'] | |
| if data['query']['count']=='1': | |
| l=data['query']['results']['link'] | |
| furl=checkPathOnFeedURL(l['href'],o) | |
| print "*****",furl,l['title'] | |
| handleFeedDetails(fo,furl) | |
| else: | |
| for r in data['query']['results']['link']: | |
| furl=checkPathOnFeedURL(r['href'],o) | |
| print furl,r['title'] | |
| handleFeedDetails(fo,furl) | |
| except: | |
| pass | |
| except: | |
| pass | |
| def checkPathOnFeedURL(furl,o): | |
| if furl.startswith('/'): | |
| x = urlparse(o) | |
| furl= 'http://'+x.netloc+furl | |
| return furl | |
| def writeOPMLHeadopenBody(fo): | |
| fo.write('<?xml version="1.0" encoding="UTF-8"?>\n') | |
| fo.write('<opml version="1.0">\n<head>\n\t<title>Generated OPML file</title>\n</head>\n\t<body>\n') | |
| def closeOPMLbody(fo): | |
| fo.write("</body>\n</opml>") | |
| def openOPMLoutline(f,t): | |
| f.write('\t\t<outline title="'+t+'" text="'+t+'">\n') | |
| def closeOPMLoutline(f): | |
| f.write('\t\t</outline>\n') | |
| def writeOPMLitem(f,htmlurl,xmlurl,title): | |
| title=saxutils.escape(title) | |
| f.write('\t\t\t<outline text="'+title+'" title="'+title+'" type="rss" xmlUrl="'+xmlurl+'" htmlUrl="'+htmlurl+'"/>\n') | |
| def handleFeedDetails(fo,furl): | |
| nocomments=True | |
| url='http://query.yahooapis.com/v1/public/yql/psychemedia/feeddetails?url='+urllib.quote(furl)+'&format=json' | |
| print "Trying feed url",furl | |
| try: | |
| details=simplejson.load(urllib.urlopen(url)) | |
| detail=details['query']['results']['feed'] | |
| #print "Acquired",detail | |
| for i in detail: | |
| if i['link']['rel']=='alternate': | |
| title=i['title'].encode('utf-8') | |
| hlink=i['link']['href'] | |
| print 'Using',hlink, furl,title | |
| if nocomments is True: | |
| if not (furl.find('/comments')>-1 or title.startswith('Comments for')): | |
| writeOPMLitem(fo,hlink,furl,title) | |
| else: | |
| writeOPMLitem(fo,hlink,furl,title) | |
| return | |
| except: | |
| pass | |
| #------- | |
| opmlFromCSV(fname) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment