+class FlagInfo(SomethingSoupInfo):
+ def __init__(self, flagid, max_age=600):
+ SomethingSoupInfo.__init__(self,
+ 'flag/info.wm?flagid=', flagid, max_age)
+ self._find_flag()
+
+ def _find_flag(self):
+ font2 = self._soup.find('font',{'size':'+2'})
+ self.flag = font2.find('b').contents[0]
+ magnate = self._soup.find('img',{'src':
+ '/yoweb/images/repute-MAGNATE.png'})
+ warinfo = (magnate.findParent('table').findParent('tr').
+ findNextSibling('tr').findNext('td',{'align':'left'}))
+ for waritem in warinfo.contents:
+ print 'ITEM ',`waritem`
+
+#---------- scraper for ocean info incl. embargoes etc. ----------
+
+class IslandInfo():
+ def __init__(self, ocean, islename):
+ self.ocean = ocean
+ self.name = islename
+ def collect(self):
+ pass
+ def yppedia_dataf(self):
+ def q(x): return urllib.quote(x.replace(' ','_'))
+ url_rhs = q(self.name) + '_(' + q(self.ocean) + ')'
+ if opts.localhtml is None:
+ url = 'http://yppedia.puzzlepirates.com/' + url_rhs
+ debug('IslandInfo retrieving YPP '+url);
+ return urllib.urlopen(url)
+ else:
+ return file(opts.localhtml + '/' + url_rhs, 'r')
+ def yoweb_url(self):
+ soup = BeautifulSoup(self.yppedia_dataf())
+ content = soup.find('div', attrs = {'id': 'content'})
+ yoweb_re = regexp.compile('^http://\w+\.puzzlepirates\.com/'+
+ 'yoweb/island/info\.wm\?islandid=\d+$')
+ a = soup.find('a', attrs = { 'href': yoweb_re })
+ if a is None: return None
+ return a['href']
+ def ruling_flag_id(self):
+ yo = self.yoweb_url()
+ if yo is None: return None
+ dataf = fetcher.fetch(yo, 600)
+ soup = BeautifulSoup(dataf)
+ ruler_re = regexp.compile('http://\w+\.puzzlepirates\.com/'+
+ 'yoweb/flag/info\.wm\?flagid=(\d+)$')
+ ruler = soup.find('a', attrs = { 'href': ruler_re })
+ if not ruler: return None
+ m = ruler_re.find(ruler['href'])
+ return m.group(1)
+
+class OceanInfo():
+ # Public data attributes (valid after collect()):
+ # oi.islands[islename] = IslandInfo(...)
+ # oi.arches[archname][islename] = IslandInfo(...)
+ def __init__(self):
+ self.isleclass = IslandInfo
+ self.ocean = fetcher.ocean.lower().capitalize()
+ def collect(self):
+ cmdl = ['./yppedia-ocean-scraper']
+ if opts.localhtml is not None:
+ cmdl += ['--local-html-dir',opts.localhtml]
+ cmdl += [self.ocean]
+ debug('OceanInfo collect running ' + `cmdl`)
+ oscraper = subprocess.Popen(
+ cmdl,
+ stdout = subprocess.PIPE,
+ cwd = yppsc_dir()+'/yarrg',
+ shell=False, stderr=None,
+ )
+ h = oscraper.stdout.readline()
+ debug('OceanInfo collect h '+`h`)
+ assert(regexp.match('^ocean ', h))
+ arch_re = regexp.compile('^ (\S.*)')
+ island_re = regexp.compile('^ (\S.*)')
+
+ self.islands = { }
+ self.arches = { }
+ archname = None
+
+ for l in oscraper.stdout:
+ debug('OceanInfo collect l '+`l`)
+ l = l.rstrip('\n')
+ m = island_re.match(l)
+ if m:
+ assert(archname is not None)
+ islename = m.group(1)
+ isle = self.isleclass(self.ocean, islename)
+ isle.arch = archname
+ self.islands[islename] = isle
+ self.arches[archname][islename] = isle
+ continue
+ m = arch_re.match(l)
+ if m:
+ archname = m.group(1)
+ assert(archname not in self.arches)
+ self.arches[archname] = { }
+ continue
+ assert(False)
+ oscraper.wait()
+ assert(oscraper.returncode == 0)
+