X-Git-Url: http://www.chiark.greenend.org.uk/ucgi/~yarrgweb/git?p=ypp-sc-tools.db-live.git;a=blobdiff_plain;f=yarrg%2Fyppedia-ocean-scraper;h=ba145eafcc247b6bae90d13244b159d62570928d;hp=5f9c5f007b46fda4265ccc7492dc2b3d58e079f0;hb=0505b9e0fd61bfaa4c84968dfba65404b408cbf6;hpb=ff016739a385102c8e11e80757d5404745bd9a39

diff --git a/yarrg/yppedia-ocean-scraper b/yarrg/yppedia-ocean-scraper
index 5f9c5f0..ba145ea 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
@@ -57,14 +88,15 @@ def fetch():
 		url_base = 'index.php?title=Template:Map:%s_Ocean&action=edit'
 	else:
 		url_base = '%s_Ocean'
-	url = ('http://yppedia.puzzlepirates.com/' +
-			(url_base % urllib.quote(ocean,'')))
-	debug('fetching',url)
-	dataf = urllib2.urlopen(url)
-	debug('fetched',dataf)
-	soup = BeautifulSoup(dataf,
-		convertEntities=BeautifulSoup.HTML_ENTITIES)
-
+	url_base = url_base % urllib.quote(ocean,'')
+	if opts.localhtml is None:
+		url = ('http://yppedia.puzzlepirates.com/' + url_base)
+		debug('fetching',url)
+		dataf = urllib.urlopen(url)
+		debug('fetched',dataf)
+	else:
+		dataf = file(opts.localhtml + '/' + url_base, 'r')
+	soup = BeautifulSoup(dataf)
 
 title_arch_re = regexp.compile('(\\S.*\\S) Archipelago \\((\\S+)\\)$')
 title_any_re = regexp.compile('(\\S.*\\S) \((\\S+)\\)$')
@@ -86,13 +118,17 @@ def title_arch_ok(t):
 def parse_chart():
 	ta = soup.find('textarea')
 	debug('ta',ta)
-	rc = ta.renderContents()
-	debug('rc',rc)
-	return rc
+	s = ta.string
+	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})
@@ -101,7 +137,7 @@ 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 = []
@@ -155,6 +191,9 @@ def main():
 		help='print chart source rather than arch/island info')
 	ao('--debug', action='count', dest='debug', default=0,
 		help='enable debugging output')
+	ao('--local-html-dir', action='store', dest='localhtml',
+		help='get yppedia pages from local directory LOCALHTML'+
+			' instead of via HTTP')
 
 	(opts,args) = pa.parse_args()
 	if len(args) != 1: