euscan: fix #435118 and #435120

Signed-off-by: Corentin Chary <corentin.chary@gmail.com>

4 files changed, 23 insertions, 20 deletions

diff --git a/bin/euscan b/bin/euscan
index 5d5e812..79053e5 100755
--- a/bin/euscan
+++ b/bin/euscan
@@ -287,9 +287,9 @@ def main():
 
             from os.path import basename  # To get the short name
 
-            output.error(
+            output.eerror(
                 "The short ebuild name '%s' is ambiguous. Please specify" %
-                    basename(pkgs[0]),
+                    basename(pkgs[0]) +
                 "one of the above fully-qualified ebuild names instead."
             )
             exit_helper(1)
diff --git a/pym/euscan/__init__.py b/pym/euscan/__init__.py
index 12c4a16..946c63c 100644
--- a/pym/euscan/__init__.py
+++ b/pym/euscan/__init__.py
@@ -77,11 +77,12 @@ ROBOTS_TXT_BLACKLIST_DOMAINS = [
     '(.*)sourceforge(.*)',
     '(.*)github.com',
     '(.*)berlios(.*)',
-    '(.*)qt.nokia.com(.*)',
-    '(.*)chromium.org(.*)',
-    '(.*)nodejs.org(.*)',
-    '(.*)download.mono-project.com(.*)',
-    '(.*)fedorahosted.org(.*)',
+    '(.*)qt\.nokia\.com(.*)',
+    '(.*)chromium\.org(.*)',
+    '(.*)nodejs\.org(.*)',
+    '(.*)download\.mono-project\.com(.*)',
+    '(.*)fedorahosted\.org(.*)',
+    '(.*)download\.tuxfamily\.org(.*)',
 ]
 
 from out import EuscanOutput
diff --git a/pym/euscan/handlers/generic.py b/pym/euscan/handlers/generic.py
index fd82c71..0795488 100644
--- a/pym/euscan/handlers/generic.py
+++ b/pym/euscan/handlers/generic.py
@@ -70,6 +70,7 @@ def scan_html(data, url, pattern):
                  match.group(0))
             )
 
+
     return results
 
 
diff --git a/pym/euscan/helpers.py b/pym/euscan/helpers.py
index 5e3e6ea..3271811 100644
--- a/pym/euscan/helpers.py
+++ b/pym/euscan/helpers.py
@@ -373,27 +373,28 @@ def tryurl(fileurl, template):
 
 def regex_from_template(template):
     # Escape
-    template = re.escape(template)
+    regexp = re.escape(template)
 
     # Unescape specific stuff
-    template = template.replace('\$\{', '${')
-    template = template.replace('\}', '}')
-    template = template.replace('}\.$', '}.$')
+    regexp = regexp.replace('\$\{', '${')
+    regexp = regexp.replace('\}', '}')
+    regexp = regexp.replace('}\.$', '}.$')
 
     # Replace ${\d+}
-    #template = template.replace('${0}', r'([\d]+?)')
-    template = re.sub(r'(\$\{\d+\}(\.?))+', r'([\w\.]+?)', template)
+    #regexp = regexp.replace('${0}', r'([\d]+?)')
+    regexp = re.sub(r'(\$\{\d+\}(\.?))+', r'([\w\.]+?)', regexp)
 
-    #template = re.sub(r'(\$\{\d+\}\.?)+', r'([\w]+?)', template)
-    #template = re.sub(r'(\$\{\d+\}\.+)+', '(.+?)\.', template)
-    #template = re.sub(r'(\$\{\d+\})+', '(.+?)', template)
+    #regexp = re.sub(r'(\$\{\d+\}\.?)+', r'([\w]+?)', regexp)
+    #regexp = re.sub(r'(\$\{\d+\}\.+)+', '(.+?)\.', regexp)
+    #regexp = re.sub(r'(\$\{\d+\})+', '(.+?)', regexp)
 
     # Full version
-    template = template.replace('${PV}', _v)
+    regexp = regexp.replace('${PV}', _v)
 
     # End
-    template = template + r'/?$'
-    return template
+    regexp = regexp + r'/?$'
+
+    return regexp
 
 
 def basedir_from_template(template):
@@ -417,7 +418,7 @@ def generate_scan_paths(url):
     path = prefix + ":/"
     for chunk in chunks:
         if '${' in chunk:
-            steps.append((path, regex_from_template(chunk)))
+            steps.append((path, '^(?:|.*/)'  + regex_from_template(chunk)))
             path = ""
         else:
             path += "/"