X-Git-Url: https://git.phdru.name/?a=blobdiff_plain;f=Robots%2Fbkmk_rurllib.py;h=6f15ad5cf193aecd5832dd5ed7837ca2f936e232;hb=97202bf84e9c78d8fac912a82a85fb1cbb233a4b;hp=839e37316197d10a51b8812e5bca874e7f00738f;hpb=917353d7c874075d3709f9295dc231d8894e61a4;p=bookmarks_db.git

diff --git a/Robots/bkmk_rurllib.py b/Robots/bkmk_rurllib.py
index 839e373..6f15ad5 100644
--- a/Robots/bkmk_rurllib.py
+++ b/Robots/bkmk_rurllib.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) 2000-2014 PhiloSoft Design"
+__copyright__ = "Copyright (C) 2000-2017 PhiloSoft Design"
 __license__ = "GNU GPL"
 
 __all__ = ['robot_urllib']
@@ -13,9 +13,15 @@ __all__ = ['robot_urllib']
 
 import sys, os
 import time, urllib
-from Robots.bkmk_robot_base import robot_base, RedirectException, get_error
+from Robots.bkmk_robot_base import robot_base, get_error
 
 
+class RedirectException(Exception):
+   def __init__(self, errcode, newurl):
+      Exception.__init__(self)
+      self.errcode = errcode
+      self.newurl = newurl
+
 class MyURLopener(urllib.URLopener):
    # Error 301 -- relocated (permanently)
    def http_error_301(self, url, fp, errcode, errmsg, headers, data=None): 
@@ -36,29 +42,29 @@ class MyURLopener(urllib.URLopener):
 
    # Error 401 -- authentication required
    def http_error_401(self, url, fp, errcode, errmsg, headers, data=None): 
-      raise IOError, ('http error', errcode, "Authentication required ", headers)
+      raise IOError(('http error', errcode, "Authentication required ", headers))
 
    def http_error_default(self, url, fp, errcode, errmsg, headers):
       if fp:
          void = fp.read()
          fp.close()
-      raise IOError, ('http error', errcode, errmsg, headers)
+      raise IOError(('http error', errcode, errmsg, headers))
 
 
 urllib._urlopener = MyURLopener()
 
 # Fake headers to pretend this is a real browser
-_version = "Mozilla/5.0 (X11; U; Linux 2.6 i686; en) Gecko/20001221 Firefox/2.0.0"
-urllib._urlopener.addheaders[0] = ('User-Agent', _version)
-_version = "bookmarks_db (Python %d.%d.%d; urllib/%s)" % (
+_user_agent = "Mozilla/5.0 (X11; U; Linux 2.6 i686; en) Gecko/20001221 Firefox/2.0.0"
+urllib._urlopener.addheaders[0] = ('User-Agent', _user_agent)
+_x_user_agent = "bookmarks_db (Python %d.%d.%d; urllib/%s)" % (
    sys.version_info[0], sys.version_info[1], sys.version_info[2], urllib.__version__)
-urllib._urlopener.addheader('X-User-Agent', _version)
+urllib._urlopener.addheader('X-User-Agent', _x_user_agent)
 urllib._urlopener.addheader('Referer', '')
 
-urllib._urlopener.addheader('Connection', 'close')
 urllib._urlopener.addheader('Accept', '*/*')
 urllib._urlopener.addheader('Accept-Language', 'ru,en')
 urllib._urlopener.addheader('Cache-Control', 'max-age=300')
+urllib._urlopener.addheader('Connection', 'close')
 
 
 urllib_ftpwrapper = urllib.ftpwrapper
@@ -91,18 +97,21 @@ class robot_urllib(robot_base):
          content = infile.read()
          infile.close()
 
-         return headers, content, None
+         return None, None, None, headers, content
+
+      except RedirectException as e:
+         return None, e.errcode, e.newurl, None, None
 
-      except IOError, msg:
-         if (msg[0] == "http error") and (msg[1] == -1):
+      except IOError as e:
+         if (e[0] == "http error") and (e[1] == -1):
             error = None
             bookmark.no_error = "The server did not return any header - it is not an error, actually"
             self.log('   no headers: %s' % bookmark.no_error)
          else:
-            error = get_error(msg)
+            error = get_error(e)
             self.log('   Error: %s' % error)
 
-         return None, None, error
+         return error, None, None, None, None
 
    def get_ftp_welcome(self):
       global ftpcache_key
@@ -111,5 +120,6 @@ class robot_urllib(robot_base):
                           # If there are - ftpcache_key in prev line is invalid.
       return _welcome
 
-   def cleanup(self):
+   def finish_check_url(self, bookmark):
+      robot_base.finish_check_url(self, bookmark)
       urllib.urlcleanup()