TouHou Project Artist urls Fetch xml parser demo

htmlparser.py

#!/usr/bin/python
# -*- coding: utf-8 -*- 

# this shell  is uesed for fetching TouHouProject artists's  urls ,and prepares for fetch albumss and songs

import urllib2
import HTMLParser
from urlparse import urljoin

FILTERURLS = ["/cgi-bin/feedback", '?C=N;O=D', "?C=M;O=A", "?C=S;O=A", "?C=D;O=A", "/", "cp_images.sh", "fix_unicode.sh", "mv_images.sh", "ren13.py"]

BASEURL = "http://kuukunen.net:8080/toh/"

class ArtistLinksParser(HTMLParser.HTMLParser):
    def __init__(self):
		HTMLParser.HTMLParser.__init__(self)
		self.recording = 0
		self.url = None
		self.ArtistUrls = []
	def handle_starttag(self, tag, attrs):
		if tag != 'a':
			return
		if self.recording:
			self.recording += 1
			return
		for name, value in attrs:
			if name == 'href' and value not in FILTERURLS:
				print value
				
				self.url = urljoin(BASEURL, value)
				break
			else:
				return
		self.recording = 1
	def handle_endtag(self, tag):
		if tag == 'a' and self.recording:
			self.recording -= 1
	def handle_data(self, data):
		if self.recording:
				arist = data.strip("/[]") 
				self.ArtistUrls.append([arist, self.url])
	
	def write2file(self, filename):
		with open(filename, "w") as f:
			for arist,url in self.ArtistUrls:
				f.write(arist)
				f.write(" , ")
				f.write(url)
				f.write("\n")
				


	

if __name__ == "__main__":				
	p = ArtistLinksParser()
	f = urllib2.urlopen(BASEURL)
	html = f.read()
	p.feed(html)
	p.write2file("aristurls.csv")
	p.close()