Ocean scraper seems to work properly now

diff --git a/yarrg/yppedia-ocean-scraper b/yarrg/yppedia-ocean-scraper
index d53e2365da98491bf1b6204a131295cf4fef3d5c..401de9bd6925fe60b904aa5f09b2791f99fc76a7 100755 (executable)
--- a/yarrg/yppedia-ocean-scraper
+++ b/yarrg/yppedia-ocean-scraper
@@ -1,28 +1,63 @@
 #!/usr/bin/python
 
 #!/usr/bin/python
 

+# 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.
+#
+# 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.
+#
+# 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.
+#
+# You should have received a copy of the GNU 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
+# are used without permission.  This program is not endorsed or
+# sponsored by Three Rings.
+
+copyright_info = '''
+yppedia-ocean-scraper is part of ypp-sc-tools Copyright (C) 2009 Ian Jackson
+This program comes with ABSOLUTELY NO WARRANTY; this is free software,
+and you are welcome to redistribute it under certain conditions.  For
+details, read the top of the yppedia-ocean-scraper file.
+'''
+

 import signal
 signal.signal(signal.SIGINT, signal.SIG_DFL)
 
 import signal
 signal.signal(signal.SIGINT, signal.SIG_DFL)
 

+import sys

 import os
 import urllib
 import urllib2
 import re as regexp
 import os
 import urllib
 import urllib2
 import re as regexp

-#from optparse import OptionParser
-
+from optparse import OptionParser

 from BeautifulSoup import BeautifulSoup
 
 from BeautifulSoup import BeautifulSoup
 

-ocean = 'Opal'
+ocean = None

 soup = None
 soup = None

+opts = None
+arches = {}

 
 def debug(k,v):
 
 def debug(k,v):

-#      print k,`v`
-       pass
+       if opts.debug:
+               print >>sys.stderr, k,`v`

 
 def fetch():
        global soup
        url = ('http://yppedia.puzzlepirates.com/%s_Ocean' %
                urllib.quote(ocean,''))
 
 def fetch():
        global soup
        url = ('http://yppedia.puzzlepirates.com/%s_Ocean' %
                urllib.quote(ocean,''))

+       debug('fetching',url)

        dataf = urllib2.urlopen(url)
        dataf = urllib2.urlopen(url)

+       debug('fetched',dataf)

        soup = BeautifulSoup(dataf)
 
 
        soup = BeautifulSoup(dataf)
 
 


@@ -57,32 +92,63 @@ def parse():
        archestable = firstarch.findParent('table', attrs={'border':'1'})
        debug('at',archestable)
 
        archestable = firstarch.findParent('table', attrs={'border':'1'})
        debug('at',archestable)
 

-       arches = []
+       archsoups = []

        for row in archestable.findAll('tr',recursive=False):
        for row in archestable.findAll('tr',recursive=False):

-               arches += row.findAll('td',recursive=False)
-       debug('ac',arches)
+               archsoups += row.findAll('td',recursive=False)
+       debug('ac',archsoups)

 
        def is_island(v):
                return len(v.findAll(text = regexp.compile('.*Large'))) > 0
        def arch_up_map(u):
                return u.findParent(is_island)
 
 
        def is_island(v):
                return len(v.findAll(text = regexp.compile('.*Large'))) > 0
        def arch_up_map(u):
                return u.findParent(is_island)
 

-       for arch in arches:
+       for arch in archsoups:

                links = arch.findAll('a', href=True)
                debug('links',links)
                if not links: continue
                (a,o) = title_arch_info(links[0]['title'])
                assert(o == ocean)
                links = arch.findAll('a', href=True)
                debug('links',links)
                if not links: continue
                (a,o) = title_arch_info(links[0]['title'])
                assert(o == ocean)

-               print 'arch', a
+               debug('arch', a)
+               assert(a not in arches)
+               isles = []

                for link in links[1:]:
                        debug('link',link)
                        if href_img_re.search(link['href']): continue
                        m = title_any_re.match(link['title'])
                        assert(m.group(2) == ocean)
                for link in links[1:]:
                        debug('link',link)
                        if href_img_re.search(link['href']): continue
                        m = title_any_re.match(link['title'])
                        assert(m.group(2) == ocean)

-                       print 'island', m.group(1)
+                       island = m.group(1)
+                       debug('island', island)
+                       isles.append(island)
+               isles.sort()
+               arches[a] = isles
+
+def output():
+       print 'ocean',ocean
+       al = arches.keys()
+       al.sort()
+       for a in al:
+               print '',a
+               for island in arches[a]:
+                       print ' ',island

 
 def main():
 
 def main():

+       global ocean
+       global opts
+
+       pa = OptionParser(
+               '''usage: .../yppedia-ocean-scraper [--debug] OCEAN''')
+       ao = pa.add_option
+       ao('--debug', action='count', dest='debug', default=0,
+               help='enable debugging output')
+
+       (opts,args) = pa.parse_args()
+       if len(args) != 1:
+               print >>sys.stderr, copyright_info
+               pa.error('need an ocean argument')
+       ocean = args[0]
+

        fetch()
        parse()
        fetch()
        parse()

+       output()

 
 main()
 
 main()