gistfile1.py

import urllib
import urllib2
import os.path
from lxml import etree
import string

def output_node(node, message):
	link = e.attrib['v'].encode('utf-8')
	link = link.replace("pl:", "")
	print
	print message
	print ("http://www.openstreetmap.org/node/"+node.attrib['id']).encode('utf-8')
	print "https://pl.wikipedia.org/wiki/"+urllib2.quote(link)
	print node.attrib['lat'].encode('utf-8')
	print node.attrib['lon'].encode('utf-8')

data = etree.parse("..\cyclemap\interpreter.osm")
for node in data.getiterator("node"):
	for e in node:
		if e.attrib['k'] == "wikipedia":
			link = e.attrib['v'].encode('utf-8')
			if string.find(link, "pl:")== -1:
				output_node(node, "missing pl:")
			else:
				link = link.replace("pl:", "")
				filename = "cache\\"+link+".txt"
				if not os.path.isfile(filename):
					print "fetching "+link
					file = open(filename, 'w')
					f = urllib.urlopen("https://pl.wikipedia.org/wiki/"+urllib2.quote(link))
					file.write(f.read())
					file.close()
				file = open(filename, 'r')
				text = file.read()
				#<span class="latitude">50°04'02”N</span>&#160;<span class="longitude">19°55'03”E</span>
				if string.find(text, "<span class=\"latitude\">")== -1:
					if string.find(text, "W Wikipedii nie ma jeszcze artykułu pod taką nazwą. Możesz wykonać jedną z poniższych czynności:") != -1:
						output_node(node, "missing article at wiki:")
					else:
						output_node(node, "missing coordinates at wiki:")