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=d55f7acab83d7d0a03ae21655059e4277e1e9068;hp=401de9bd6925fe60b904aa5f09b2791f99fc76a7;hb=59316f0dcddd4e5d15e47dfde36f513e1685c4ae;hpb=cf9d0277c5d6bfe900a0881a00984f8268a90514 diff --git a/yarrg/yppedia-ocean-scraper b/yarrg/yppedia-ocean-scraper index 401de9b..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 # # 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 . # # 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 @@ -53,15 +84,19 @@ def debug(k,v): def fetch(): global soup - url = ('http://yppedia.puzzlepirates.com/%s_Ocean' % - urllib.quote(ocean,'')) + if opts.chart: + 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) + dataf = urllib.urlopen(url) debug('fetched',dataf) soup = BeautifulSoup(dataf) -title_arch_re = regexp.compile('(\\S+) Archipelago \\((\\S+)\\)$') +title_arch_re = regexp.compile('(\\S.*\\S) Archipelago \\((\\S+)\\)$') title_any_re = regexp.compile('(\\S.*\\S) \((\\S+)\\)$') href_img_re = regexp.compile('\\.png$') @@ -78,9 +113,20 @@ def title_arch_ok(t): if o is None: return False return o == ocean -def parse(): - firstarch = soup.find('a', attrs = {'title': title_arch_ok}) - debug('fa',firstarch) +def parse_chart(): + ta = soup.find('textarea') + debug('ta',ta) + s = ta.string + debug('s',s) + s = regexp.sub(r'\<\;', '<', s) + s = regexp.sub(r'\>\;', '>', s) + s = regexp.sub(r'\"\;', '"', s) + s = regexp.sub(r'\&\;', '&', s) + debug('s',s) + return s + +def parse_ocean(): + content = soup.find('div', attrs = {'id': 'content'}) def findall_title_arch_ok(t): return t.findAll('a', attrs = {'title': title_arch_ok}) @@ -89,7 +135,7 @@ def parse(): 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 = [] @@ -107,8 +153,8 @@ def parse(): debug('links',links) if not links: continue (a,o) = title_arch_info(links[0]['title']) + debug('arch-ocean', (a,o)) assert(o == ocean) - debug('arch', a) assert(a not in arches) isles = [] for link in links[1:]: @@ -136,8 +182,11 @@ def main(): global opts pa = OptionParser( - '''usage: .../yppedia-ocean-scraper [--debug] OCEAN''') +'''usage: .../yppedia-ocean-scraper [--debug] [--chart] OCEAN''') ao = pa.add_option + + ao('--chart', action='store_true', dest='chart', + help='print chart source rather than arch/island info') ao('--debug', action='count', dest='debug', default=0, help='enable debugging output') @@ -148,7 +197,10 @@ def main(): ocean = args[0] fetch() - parse() - output() + if opts.chart: + print parse_chart() + else: + parse_ocean() + output() main()