add uploader to html2wiki

[otptools/otptools.git] / html2wiki / gettitles.py

diff --git a/html2wiki/gettitles.py b/html2wiki/gettitles.py
deleted file mode 100755 (executable)
index 452d604..0000000
--- a/html2wiki/gettitles.py
+++ /dev/null
@@ -1,64 +0,0 @@
-#!/usr/bin/env python
-# -*- coding: utf-8 -*-
-
-import os.path
-import sys
-import re
-import os
-import urllib
-import HTMLParser
-
-usage = "%s <urllist>" % sys.argv[0]
-
-try:
-    fname = sys.argv[1]
-except IndexError:
-    sys.exit(usage)
-
-class TitleParser(HTMLParser.HTMLParser):
-
-    def __init__(self):
-        HTMLParser.HTMLParser.__init__(self)
-        self._capt = False
-        self._title = ""
-
-    def parse(self, html_string):
-        """Parse html_string with url, and return anchors"""
-        self.feed(html_string)
-        return self._title
-
-    def handle_starttag(self, tag, attrs):
-        """starttag handler."""
-        if tag == "title":
-            self._capt = True
-
-    def handle_endtag(self, tag):
-        """starttag handler."""
-        if tag == "title":
-            self._capt = False
-
-    def handle_data(self, data):
-        if self._capt:
-            self._title = self._title + data.strip()
-
-f = open(fname, "r")
-
-rex = re.compile(r"<\s*script[^>]*?>.*?</script>", re.S)
-rex2 = re.compile(r"<\s*noscript[^>]*?>.*?</noscript>", re.S)
-for url in f:
-    url = url.strip()
-    u = urllib.urlopen(url)
-    data = u.read()
-
-    t = rex.sub("", data)
-    t = rex2.sub("", t)
-
-    p = TitleParser()
-    title = p.parse(t)
-    title = re.sub(r"\s*- SourceForge.JP Magazine\s*$", "", title)
-    title = title.replace(" ", "_").replace("/", "_").replace("+", "_")
-    sys.stdout.write(url + "\t" + title + "_p1\n")
-
-f.close()
-
-