Fix(Robot): Stop splitting and un-splitting URLs

[bookmarks_db.git] / Robots / bkmk_rurllib2.py

diff --git a/Robots/bkmk_rurllib2.py b/Robots/bkmk_rurllib2.py
index d9c91491be35f384d4d35d802111e3522e74e6a7..d1b679c11d68ebef2f14e815d3c2230cfd3c46d6 100644 (file)
--- a/Robots/bkmk_rurllib2.py
+++ b/Robots/bkmk_rurllib2.py
@@ -5,7 +5,7 @@ This file is a part of Bookmarks database and Internet robot.
 """
 
 __author__ = "Oleg Broytman <phd@phdru.name>"
-__copyright__ = "Copyright (C) 2014 PhiloSoft Design"
+__copyright__ = "Copyright (C) 2014-2024 PhiloSoft Design"
 __license__ = "GNU GPL"
 
 __all__ = ['robot_urllib2']
@@ -14,11 +14,12 @@ __all__ = ['robot_urllib2']
 import sys
 import httplib
 import urllib2
-from Robots.bkmk_robot_base import robot_base, get_error
+from Robots.bkmk_robot_base import robot_base, request_headers, get_error
 
 
 _fw = None
 
+
 class FTPHandler(urllib2.FTPHandler):
     def connect_ftp(self, user, passwd, host, port, dirs, timeout):
         global _fw
@@ -38,24 +39,13 @@ for klass in default_classes:
 urllib2.install_opener(opener)
 
 
-# Fake headers to pretend this is a real browser
-_user_agent = "Mozilla/5.0 (X11; Linux i686; rv:30.0) Gecko/20100101 Firefox/30.0"
-_x_user_agent = "bookmarks_db (Python %d.%d.%d; urllib2)" % (
-    sys.version_info[0], sys.version_info[1], sys.version_info[2])
-
-
 class robot_urllib2(robot_base):
     def get(self, bookmark, url, accept_charset=False):
         request = urllib2.Request(url)
-        request.add_header('Accept', '*/*')
+        for h, v in request_headers.items():
+            request.add_header(h, v)
         if accept_charset and bookmark.charset:
             request.add_header('Accept-Charset', bookmark.charset)
-        request.add_header('Accept-Language', 'ru,en')
-        request.add_header('Cache-Control', 'max-age=300')
-        request.add_header('Connection', 'close')
-        request.add_header('Referer', url)
-        request.add_header('User-agent', _user_agent)
-        request.add_header('X-User-Agent', _x_user_agent)
 
         global _fw
         _fw = None
@@ -63,23 +53,24 @@ class robot_urllib2(robot_base):
         try:
             response = urllib2.urlopen(request)
 
-        except urllib2.HTTPError, e:
-            if e.code in (301, 302, 303, 307):
+        except urllib2.HTTPError as e:
+            if e.code in (301, 302, 303, 307, 308):
                 return None, e.code, e.hdrs['Location'], None, None
             else:
                 self.log('   HTTP Error %s: %s' % (e.code, e.msg))
-                return "HTTP Error %s: %s" % (e.code, e.msg), None, None, None, None
+                return ("HTTP Error %s: %s" % (e.code, e.msg),
+                        None, None, None, None)
 
-        except urllib2.URLError, e:
+        except urllib2.URLError as e:
             self.log('   URL Error: %s' % e.reason)
             return "URL Error: %s" % e.reason, None, None, None, None
 
-        except httplib.HTTPException, e:
+        except httplib.HTTPException as e:
             error = get_error(e)
             self.log('   HTTP Exception: %s' % error)
             return "HTTP Exception: %s" % error, None, None, None, None
 
-        except IOError, e:
+        except IOError as e:
             error = get_error(e)
             self.log('   I/O Error: %s' % error)
             return "I/O Error: %s" % error, None, None, None, None