Improve detection of corporates

Because they are always creating new variations of their domain name

daemon_get.py

@@ -89,6 +89,7 @@ from httpcodes import http_304
 from httpcodes import http_400
 from httpcodes import http_503
 from httpcodes import write2
+from flags import is_corporate
 from flags import is_image_file
 from flags import is_artist
 from flags import is_blog_post
@@ -112,7 +113,6 @@ from utils import convert_domains
 from utils import get_nickname_from_actor
 from utils import get_json_content_from_accept
 from utils import check_bad_path
-from utils import corp_servers
 from utils import decoded_host
 from utils import detect_mitm
 from person import get_person_notes_endpoint
@@ -257,8 +257,9 @@ def daemon_http_get(self) -> None:
                            self.server.headers_catalog,
                            self.headers)
 
+    # bounce corporate servers
     if self.headers.get('Server'):
-        if self.headers['Server'] in corp_servers():
+        if is_corporate(self.headers['Server']):
             print('GET HTTP Corporate leech bounced: ' +
                   self.headers['Server'])
             http_402(self)

daemon_post.py

@@ -11,8 +11,8 @@ import time
 import errno
 import json
 from socket import error as SocketError
+from flags import is_corporate
 from utils import replace_strings
-from utils import corp_servers
 from utils import string_ends_with
 from utils import get_config_param
 from utils import decoded_host
@@ -156,7 +156,7 @@ def daemon_http_post(self) -> None:
     self.server.last_postreq = curr_time_postreq
 
     if self.headers.get('Server'):
-        if self.headers['Server'] in corp_servers():
+        if is_corporate(self.headers['Server']):
             print('POST HTTP Corporate leech bounced: ' +
                   self.headers['Server'])
             http_402(self)

flags.py

@@ -623,3 +623,16 @@ def url_permitted(url: str, federation_list: []) -> bool:
         if domain in url:
             return True
     return False
+
+
+def is_corporate(server_name: str) -> bool:
+    """Is the given server name a corporate leech?
+    """
+    server_lower = server_name.lower()
+    if 'google' in server_lower or \
+       'cloudflare' in server_lower or \
+       'facebook' in server_lower or \
+       'microsoft' in server_lower or \
+       'github' in server_lower:
+        return True
+    return False

utils.py

@@ -5018,13 +5018,6 @@ def lines_in_file(filename: str) -> int:
     return 0
 
 
-def corp_servers() -> ():
-    """Returns a list of despised corporate thieves
-    """
-    return ('GitHub.com', 'github.com', 'cloudflare', 'microsoft.com',
-            'google.com', 'google.co.')
-
-
 def get_media_url_from_video(post_json_object: {}) -> (str, str, str, str):
     """Within a Video post (eg peertube) return the media details
     """