Update cli client commands, add debugging to test server

src/readability_lxml/client.py

@@ -16,11 +16,6 @@ def parse_args():
         default=False,
         help="Increase logging verbosity to DEBUG.")
 
-    parser.add_argument('-u', '--url',
-        action='store',
-        default=None,
-        help="Indicate that this is a url path.")
-
     parser.add_argument('path', metavar='P', type=str, nargs=1,
         help="The url or file path to process in readable form.")
 
@@ -31,19 +26,27 @@ def parse_args():
 def main():
     args = parse_args()
 
-    target = None
-    if args.url:
+    target = args.path[0]
+
+    if target.startswith('http') or target.startswith('www'):
+        is_url = True
+        url = target
+    else:
+        is_url = False
+        url = None
+
+    if is_url:
         import urllib
-        target = urllib.urlopen(args.path[0])
+        target = urllib.urlopen(target)
     else:
-        target = open(args.path[0], 'rt')
+        target = open(target, 'rt')
 
     enc = sys.__stdout__.encoding or 'utf-8'
 
     try:
         doc = Document(target.read(),
             debug=args.verbose,
-            url=args.url)
+            url=url)
         print doc.summary().encode(enc, 'replace')
 
     finally:

src/readability_lxml/encoding.py

@@ -1,8 +1,14 @@
+import logging
 import re
 import chardet
 
 
+LOG = logging.getLogger()
+
+
 def get_encoding(page):
+    LOG.info('GET ENCODING')
+    LOG.info(type(page))
     text = re.sub('</?[^>]*>\s*', ' ', page)
     enc = 'utf-8'
     if not text.strip() or len(text) < 10:

src/readability_lxml/htmls.py

@@ -13,7 +13,12 @@ logging.getLogger().setLevel(logging.DEBUG)
 utf8_parser = HTMLParser(encoding='utf-8')
 
 
+LOG = logging.getLogger()
+
+
 def build_doc(page):
+    LOG.info('BUILD DOC')
+    LOG.info(type(page))
     if isinstance(page, unicode):
         page_unicode = page
     else: