X-Git-Url: http://www.chiark.greenend.org.uk/ucgi/~yarrgweb/git?p=ypp-sc-tools.db-test.git;a=blobdiff_plain;f=yarrg%2Fyppedia-ocean-scraper;h=d55f7acab83d7d0a03ae21655059e4277e1e9068;hp=30d0c4a8de8d895292879a074a6bf654ecdec4c5;hb=b14effcf3ea7900eb4198f6e50112da751f29add;hpb=efeac1885cd0211754b34e173a5efb74b6cbedb2

diff --git a/yarrg/yppedia-ocean-scraper b/yarrg/yppedia-ocean-scraper
index 30d0c4a..d55f7ac 100755
--- a/yarrg/yppedia-ocean-scraper
+++ b/yarrg/yppedia-ocean-scraper
@@ -2,22 +2,22 @@
 
 # helper program for getting information from yppedia
 
-# This is part of ypp-sc-tools, a set of third-party tools for assisting
-# players of Yohoho Puzzle Pirates.
+# This is part of the YARRG website.  YARRG is a tool and website
+# for assisting players of Yohoho Puzzle Pirates.
 #
 # Copyright (C) 2009 Ian Jackson <ijackson@chiark.greenend.org.uk>
 #
 # This program is free software: you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation, either version 3 of the License, or
-# (at your option) any later version.
+# it under the terms of the GNU Affero General Public License as
+# published by the Free Software Foundation, either version 3 of the
+# License, or (at your option) any later version.
 #
 # This program is distributed in the hope that it will be useful,
 # but WITHOUT ANY WARRANTY; without even the implied warranty of
 # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# GNU General Public License for more details.
+# GNU Affero General Public License for more details.
 #
-# You should have received a copy of the GNU General Public License
+# You should have received a copy of the GNU Affero General Public License
 # along with this program.  If not, see <http://www.gnu.org/licenses/>.
 #
 # Yohoho and Puzzle Pirates are probably trademarks of Three Rings and
@@ -37,11 +37,42 @@ signal.signal(signal.SIGINT, signal.SIG_DFL)
 import sys
 import os
 import urllib
-import urllib2
 import re as regexp
+import subprocess
 from optparse import OptionParser
 from BeautifulSoup import BeautifulSoup
 
+
+# For fuck's sake!
+import codecs
+import locale
+def fix_stdout():
+    sys.stdout = codecs.EncodedFile(sys.stdout, locale.getpreferredencoding())
+    def null_decode(input, errors='strict'):
+        return input, len(input)
+    sys.stdout.decode = null_decode
+# From
+#  http://ewx.livejournal.com/457086.html?thread=3016574
+#  http://ewx.livejournal.com/457086.html?thread=3016574
+# lightly modified.
+# See also Debian #415968.
+fix_stdout()
+
+
+# User agent:
+class YarrgURLopener(urllib.FancyURLopener):
+	base_version= urllib.URLopener().version
+	proc= subprocess.Popen(
+		["./database-info-fetch", "useragentstringmap",
+		 base_version, "manual islands/topology fetch"],
+		shell=False,
+		stderr=None,
+		stdout=subprocess.PIPE,
+		)
+	version = proc.communicate()[0].rstrip('\n');
+	assert(proc.returncode is not None and proc.returncode == 0)
+urllib._urlopener = YarrgURLopener()
+
 ocean = None
 soup = None
 opts = None
@@ -60,7 +91,7 @@ def fetch():
 	url = ('http://yppedia.puzzlepirates.com/' +
 			(url_base % urllib.quote(ocean,'')))
 	debug('fetching',url)
-	dataf = urllib2.urlopen(url)
+	dataf = urllib.urlopen(url)
 	debug('fetched',dataf)
 	soup = BeautifulSoup(dataf)
 
@@ -89,13 +120,13 @@ def parse_chart():
 	debug('s',s)
 	s = regexp.sub(r'\&lt\;', '<', s)
 	s = regexp.sub(r'\&gt\;', '>', s)
+	s = regexp.sub(r'\&quot\;', '"', s)
 	s = regexp.sub(r'\&amp\;', '&', s)
 	debug('s',s)
 	return s
 
 def parse_ocean():
-	firstarch = soup.find('a', attrs = {'title': title_arch_ok})
-	debug('fa',firstarch)
+	content = soup.find('div', attrs = {'id': 'content'})
 
 	def findall_title_arch_ok(t):
 		return t.findAll('a', attrs = {'title': title_arch_ok})
@@ -104,7 +135,7 @@ def parse_ocean():
 		if u.name != 'table': return False
 		return len(findall_title_arch_ok(u)) > 1
 
-	archestable = firstarch.findParent('table', attrs={'border':'1'})
+	archestable = content.findChild('table', attrs={'border':'1'})
 	debug('at',archestable)
 
 	archsoups = []