home | new paste

import calendar
import sys
import time
import xml.dom.minidom as mini


class C:
   TIMEFMT   = "%Y-%m-%dT%H:%M:%S+00:00"
   EMPTYFEED = """\
<?xml version="1.0" encoding="UTF-8"?>
<feed xmlns:yt="http://www.youtube.com/xml/schemas/2015" xmlns:media="http://search.yahoo.com/mrss/" xmlns="http://www.w3.org/2005/Atom">
 <title>merged feed</title>
 <author>
  <name>comrade</name>
 </author>
</feed>"""


def nodetext (node):
   out = []

   for n in node.childNodes:
      if n.nodeType == n.TEXT_NODE:
         out.append (n.data)

   return ''.join (out)

def parsetime (s):
   t = time.strptime (s, C.TIMEFMT)
   return calendar.timegm (t)

def entrytime (entry):
   nodes = entry.getElementsByTagName ("updated")
   if nodes:
      return parsetime (nodetext (nodes [0]).strip ())

   nodes = entry.getElementsByTagName ("published")
   if nodes:
      return parsetime (nodetext (nodes [0]).strip ())

   return 0

def merge_docs (docs):
   merged = mini.parseString (C.EMPTYFEED)
   mfeed  = merged.documentElement
   all    = []

   for d in docs:
      entries = d.documentElement.getElementsByTagName ("entry")
      all.extend (entries)

   _et  = entrytime
   keys = [(_et (e), k) for k, e in enumerate (all)]

   keys.sort (reverse = True)

   for sec, k in keys:
      mfeed.appendChild (all [k])

   return merged

def main_merge (paths):
   docs   = [mini.parse (p) for p in paths]
   merged = merge_docs (docs)
   out    = "merged.xml"

   with open (out, "w") as f:
      merged.writexml (f,
         indent    = "",
         addindent = "",
         newl      = "",
         encoding  = "UTF-8")

   merged.unlink ()
   for d in docs:
      d.unlink ()


def main ():
   main_merge (sys.argv [1:])

if __name__ == "__main__": main ()