Exclude domains contained in a whitelist

diff --git a/updateHostsFile.py b/updateHostsFile.py
index 484ccdb819e24de0d15bb65ab7f72dfe83e10333..fc460aa1fb16fc3739a3b171c7bd9ef8724b0441 100755 (executable)
--- a/updateHostsFile.py
+++ b/updateHostsFile.py
@@ -77,10 +77,18 @@ SOURCES = listdir_nohidden(DATA_PATH)
 README_TEMPLATE = os.path.join(BASEDIR_PATH, 'readme_template.md')
 README_FILE = os.path.join(BASEDIR_PATH, 'readme.md')
 TARGET_HOST = '0.0.0.0'
+WHITELIST_FILE = os.path.join(BASEDIR_PATH, 'whitelist')
 
 # Exclusions
 EXCLUSION_PATTERN = '([a-zA-Z\d-]+\.){0,}' #append domain the end
 
+# Exclutions from whitelist file
+EXCLUSIONS = []
+if os.path.isfile(WHITELIST_FILE):
+       with open(WHITELIST_FILE, "r") as ins:
+               for line in ins:
+                       EXCLUSIONS.append(line)
+
 # Common domains to exclude
 COMMON_EXCLUSIONS = ['hulu.com']
 
@@ -90,6 +98,7 @@ numberOfRules = 0
 
 def main():
        promptForUpdate()
+       excludeFromFile()
        promptForExclusions()
        mergeFile = createInitialFile()
        finalFile = removeDups(mergeFile)
@@ -99,6 +108,14 @@ def main():
 
        promptForMove(finalFile)
 
+# Exclusion from file
+def excludeFromFile():
+       for domain in EXCLUSIONS:
+               if (domain != '' and not domain.startswith("#")):
+                       domainRegex = re.compile("www\d{0,3}[.]|https?")
+                       if not (domainRegex.match(domain)):
+                               excludeDomain(domain)
+
 # Prompt the User
 def promptForUpdate():
        response = query_yes_no("Do you want to update all data sources?")