More oceans

[ypp-sc-tools.db-live.git] / yarrg / yppedia-ocean-scraper

diff --git a/yarrg/yppedia-ocean-scraper b/yarrg/yppedia-ocean-scraper
index 5f9c5f007b46fda4265ccc7492dc2b3d58e079f0..a85403504aae52764a1a6d96f7202f6444c005ed 100755 (executable)
--- a/yarrg/yppedia-ocean-scraper
+++ b/yarrg/yppedia-ocean-scraper
@@ -62,8 +62,7 @@ def fetch():
        debug('fetching',url)
        dataf = urllib2.urlopen(url)
        debug('fetched',dataf)
-       soup = BeautifulSoup(dataf,
-               convertEntities=BeautifulSoup.HTML_ENTITIES)
+       soup = BeautifulSoup(dataf)
 
 
 title_arch_re = regexp.compile('(\\S.*\\S) Archipelago \\((\\S+)\\)$')
@@ -86,13 +85,17 @@ 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 +104,7 @@ 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 = []