youtube.py and xml.etree.ElementTree -> lxml.etree

plugins/twitter.py

@@ -4,19 +4,19 @@ retrieves most recent tweets
 """
 
 import urllib
-from xml.etree import ElementTree
+from lxml import etree
 
 import hook
 
 @hook.command
 def twitter(bot, input):
-    '''.twitter <user> - gets most recent tweet from <user>'''
+    ".twitter <user> - gets most recent tweet from <user>"
     if not input.inp.strip():
         return twitter.__doc__
 
     url = "http://twitter.com/statuses/user_timeline/%s.xml?count=1" \
             % urllib.quote(input.inp)
-    tweet = ElementTree.parse(urllib.urlopen(url))
+    tweet = etree.parse(url)
 
     if tweet.find('error') is not None:
         return "can't find that username"

plugins/weather.py

@@ -2,7 +2,7 @@
 "weather, thanks to google"
 
 import urllib
-from xml.etree import ElementTree
+from lxml import etree
 
 import hook
 
@@ -15,7 +15,7 @@ def weather(bot, input):
 
     data = urllib.urlencode({'weather':input.inp.encode('utf-8')})
     url = 'http://www.google.com/ig/api?' + data
-    w = ElementTree.parse(urllib.urlopen(url)).find('weather')
+    w = etree.parse(url).find('weather')
 
     if w.find('problem_cause') is not None:
         return "Couldn't fetch weather data for '%s', try using a zip or " \

plugins/youtube.py

@@ -1,17 +1,45 @@
-import urllib
+import re
-from xml.etree import ElementTree
+from lxml import etree
+import locale
+
+import hook
+
+locale.setlocale(locale.LC_ALL, "")
 
 def ytdata(id):
-    url = 'http://gdata.youtube.com/feeds/api/videos/' + idt
+    url = 'http://gdata.youtube.com/feeds/api/videos/' + id
-    print url
+    x = etree.parse(url)
-    data = urllib.urlopen(url).read()
-    if len(data) < 50: # it's some error message; ignore
-        print data
-        return
-    global x
-    def 
-    x = ElementTree.XML(data)
 
+    # I can't figure out how to deal with schemas/namespaces properly :(
+    yt = '{http://gdata.youtube.com/schemas/2007}'
+    media = '{http://search.yahoo.com/mrss/}'
+
+    rating = x.find('{http://schemas.google.com/g/2005}rating')
+    data = dict(rating.items())
+    data['title'] = x.find('{http://www.w3.org/2005/Atom}title').text
+    data['views'] = locale.format('%d', int(x.find(yt + 'statistics').get(
+                        'viewCount')), 1)
+    length = int(x.find(media + 'group/' + yt + 'duration').get('seconds'))
+    data['length'] = ''
+    if length / 3600: # > 1 hour
+        data['length'] += str(length/3600) + 'h '
+    if length / 60: # > 1 minute
+        data['length'] += str(length/60 % 60) + 'm '
+    data['length'] += "%ds" % (length % 60)
+
+    return data
+
+youtube_re = re.compile(r'.*youtube.*v=([-_a-z0-9]+)', flags=re.IGNORECASE)
+
+@hook.command(hook=r'(.*)', prefix=False)
+def youtube(inp):
+    m = youtube_re.match(inp)
+    if m:
+        data = ytdata(m.group(1))
+        return '\x02%(title)s\x02 - rated \x02%(average)s/%(max)s\x02 ' \
+                '(%(numRaters)s) - views \x02%(views)s\x02 - length \x02' \
+                '%(length)s\x02' % data
 
 if __name__ == '__main__':
-    ytdata('the0KZLEacs')
+    print ytdata('the0KZLEacs')
+    print ytdata('Ct8nZ6eTTiY')