paulo@39: import os
paulo@39: import re
paulo@39: 
paulo@39: import html
paulo@39: import xml.etree.ElementTree 
paulo@39: 
paulo@39: 
paulo@39: MAX_ITEMS = 30
paulo@39: MAX_LINK_Z = 4
paulo@39: 
paulo@39: 
paulo@39: _PARSE_ROOT_TAG_RE = re.compile(r"(\{(.+)\})?(.+)")
paulo@39: 
paulo@39: def _parse_root_tag(root_tag):
paulo@39: 	re_match = _PARSE_ROOT_TAG_RE.match(root_tag)
paulo@39: 
paulo@39: 	if re_match is None:
paulo@39: 		return (None, None)
paulo@39: 	else:
paulo@39: 		return re_match.group(2, 3)
paulo@39: 	
paulo@39: 
paulo@39: def _go_rss(elementTree):
paulo@39: 	title = elementTree.find("channel/title").text.strip()
paulo@39: 	link = elementTree.find("channel/link").text
paulo@39: 
paulo@39: 	items = []
paulo@39: 
paulo@39: 	for i in elementTree.findall("channel/item")[:MAX_ITEMS]:
paulo@39: 		it_title = i.find("title").text.strip()
paulo@39: 		it_link = i.find("link").text
paulo@39: 
paulo@39: 		items.append((it_title, it_link))
paulo@39: 
paulo@39: 	return (title, link, items)
paulo@39: 
paulo@39: 
paulo@39: def _go_atom(elementTree):
paulo@39: 	ns = "http://www.w3.org/2005/Atom"
paulo@39: 
paulo@39: 	title = elementTree.find("{%s}title" % ns).text.strip()
paulo@39: 	link = ''
paulo@39: 
paulo@39: 	for i in elementTree.findall("{%s}link" % ns):
paulo@39: 		if i.get("type") == "text/html" and i.get("rel") == "alternate":
paulo@39: 			link = i.get("href")
paulo@39: 			break
paulo@39: 
paulo@39: 	items = []
paulo@39: 
paulo@39: 	for i in elementTree.findall("{%s}entry" % ns)[:MAX_ITEMS]:
paulo@39: 		it_title = i.find("{%s}title" % ns).text.strip()
paulo@39: 		it_link = ''
paulo@39: 		
paulo@39: 		for j in i.findall("{%s}link" % ns):
paulo@39: 			if j.get("type") == "text/html" and j.get("rel") == "alternate":
paulo@39: 				it_link = j.get("href")
paulo@39: 				break
paulo@39: 
paulo@39: 		items.append((it_title, it_link))
paulo@39: 
paulo@39: 	return (title, link, items)
paulo@39: 
paulo@39: 
paulo@39: def _to_html(docstruct):
paulo@39: 	root = html.HTML()
paulo@39: 
paulo@39: 	header = root.header
paulo@39: 	header.title("myrss")
paulo@39: 	header.link(rel="stylesheet", type="text/css", href="index.css")
paulo@39: 
paulo@39: 	link_z = 0
paulo@39: 
paulo@39: 	for feed in docstruct:
paulo@39: 		(title, link, items) = feed
paulo@39: 
paulo@39: 		root.h1.a(title, href=link, klass="z%d" % (link_z % MAX_LINK_Z))
paulo@39: 		link_z += 1
paulo@39: 		p = root.p
paulo@39: 
paulo@39: 		for (i, (it_title, it_link)) in enumerate(items):
paulo@39: 			if i > 0:
paulo@39: 				p += " - "
paulo@39: 
paulo@39: 			p.a(it_title, href=it_link, klass="z%d" % (link_z % MAX_LINK_Z))
paulo@39: 			link_z += 1
paulo@39: 
paulo@39: 	return unicode(root).encode("utf-8")
paulo@39: 
paulo@39: 
paulo@39: if __name__ == "__main__":
paulo@39: 
paulo@39: 	docstruct = []
paulo@39: 	XMLFILE = "%d.feedtmp"
paulo@39: 	
paulo@39: 	for i in range(31):
paulo@39: 		if os.path.exists(XMLFILE % i):
paulo@39: 			elementTree = xml.etree.ElementTree.parse(XMLFILE % i)
paulo@39: 			root = elementTree.getroot()
paulo@39: 
paulo@39: 			if _parse_root_tag(root.tag) == (None, "rss"):
paulo@39: 				version = float(root.get("version", 0.0))
paulo@39: 				if version >= 2.0:
paulo@39: 					docstruct.append(_go_rss(elementTree))
paulo@39: 				else:
paulo@39: 					raise NotImplementedError("Unsupported rss version")
paulo@39: 			elif _parse_root_tag(root.tag) == ("http://www.w3.org/2005/Atom", "feed"):
paulo@39: 				docstruct.append(_go_atom(elementTree))
paulo@39: 			else:
paulo@39: 				raise NotImplementedError("Unknown root tag")
paulo@39: 
paulo@39: 	if len(docstruct) > 0:
paulo@39: 		print _to_html(docstruct)
paulo@39: 	else:
paulo@39: 		raise RuntimeError("Could not produce docstruct")