forked from Lainports/freebsd-ports
9befe5ba60
When de-installing, try removing any .pyc or .pyo files generated by Python compiler next to the .py files we install. Not bumping up PORTREVISION, since it still does not work with the new Python and worked without the fixes with the earlier one. Submitted by: maintainer
123 lines
3.4 KiB
Text
123 lines
3.4 KiB
Text
--- myUrlLib.py Sun Mar 14 14:24:20 1999
|
|
+++ myUrlLib.py Wed Apr 3 10:52:19 2002
|
|
@@ -37,6 +38,7 @@
|
|
import htmlparse
|
|
import debugio
|
|
import sys
|
|
+import socket
|
|
|
|
|
|
def get_robots(location):
|
|
@@ -77,7 +79,7 @@
|
|
self.init()
|
|
|
|
debugio.write('\tparent = ' + str(parent),2)
|
|
- from urlparse import *
|
|
+ from urlparse import urlparse
|
|
|
|
parsed = urlparse(url)
|
|
self.scheme = parsed[0]
|
|
@@ -105,7 +107,10 @@
|
|
|
|
if (parent is None):
|
|
Link.baseurl=self.URL
|
|
- Link.base=self.URL[:string.rfind(self.URL,'/')+1]
|
|
+ if hasattr(self.URL, 'rfind'):
|
|
+ Link.base=self.URL[:self.URL.rfind('/')+1]
|
|
+ else:
|
|
+ Link.base=self.URL[:string.rfind(self.URL,'/')+1]
|
|
if Link.base[-2:] == '//': Link.base = self.URL
|
|
debugio.write('\tbase: %s' % Link.base)
|
|
if self.scheme == 'http':
|
|
@@ -257,7 +262,7 @@
|
|
|
|
def is_external(url):
|
|
""" returns true if url is an external link """
|
|
- from urlparse import *
|
|
+ from urlparse import urlparse
|
|
parsed = urlparse(url)
|
|
scheme = parsed[0]
|
|
location = parsed[1]
|
|
--- robotparser.py Sat Jan 9 19:01:45 1999
|
|
+++ robotparser.py Wed Jul 18 20:29:13 2001
|
|
@@ -37,7 +37,7 @@
|
|
self.parse(urlopener.open(self.url).readlines())
|
|
|
|
def parse(self, lines):
|
|
- import regsub, string, regex
|
|
+ import re, string
|
|
active = []
|
|
for line in lines:
|
|
if self.debug: print '>', line,
|
|
@@ -49,7 +49,7 @@
|
|
line = string.strip(line[:string.find(line, '#')])
|
|
if not line:
|
|
continue
|
|
- line = regsub.split(line, ' *: *')
|
|
+ line = re.split(' *: *', line)
|
|
if len(line) == 2:
|
|
line[0] = string.lower(line[0])
|
|
if line[0] == 'user-agent':
|
|
@@ -62,7 +62,7 @@
|
|
if line[1]:
|
|
if self.debug: print '>> disallow:', line[1]
|
|
for agent in active:
|
|
- self.rules[agent].append(regex.compile(line[1]))
|
|
+ self.rules[agent].append(re.compile(line[1]))
|
|
else:
|
|
pass
|
|
for agent in active:
|
|
@@ -83,7 +83,7 @@
|
|
return 1
|
|
path = urlparse.urlparse(url)[2]
|
|
for rule in self.rules[ag]:
|
|
- if rule.match(path) != -1:
|
|
+ if rule.match(path):
|
|
if self.debug: print '>> disallowing', url, 'fetch by', agent
|
|
return 0
|
|
if self.debug: print '>> allowing', url, 'fetch by', agent
|
|
--- schemes/filelink.py Thu Mar 11 22:56:07 1999
|
|
+++ schemes/filelink.py Wed Jul 18 20:19:26 2001
|
|
@@ -42,7 +42,7 @@
|
|
import time
|
|
import mimetypes
|
|
import myUrlLib
|
|
-import regsub
|
|
+import re
|
|
|
|
mimetypes.types_map['.shtml']='text/html'
|
|
|
|
@@ -51,7 +51,7 @@
|
|
parsed = urlparse.urlparse(self.URL,'file',0)
|
|
filename = parsed[2]
|
|
if os.name != 'posix':
|
|
- filename = regsub.sub("^/\(//\)?\([a-zA-Z]\)[|:]","\\2:",filename)
|
|
+ filename = re.sub("^/\(//\)?\([a-zA-Z]\)[|:]","\\2:",filename)
|
|
try:
|
|
stats = os.stat(filename)
|
|
except os.error:
|
|
@@ -70,7 +70,7 @@
|
|
parsed = urlparse.urlparse(url,'file',0)
|
|
filename = parsed[2]
|
|
if os.name != 'posix':
|
|
- filename = regsub.sub("^/\(//\)?\([a-zA-Z]\)[|:]","\\2:",filename)
|
|
+ filename = re.sub("^/\(//\)?\([a-zA-Z]\)[|:]","\\2:",filename)
|
|
|
|
return open(filename,'r').read()
|
|
|
|
--- htmlparse.py Wed Mar 10 23:51:25 1999
|
|
+++ htmlparse.py Wed Apr 3 11:10:55 2002
|
|
@@ -48,5 +48,5 @@
|
|
based on parent"""
|
|
|
|
- from urlparse import *
|
|
+ from urlparse import urlparse
|
|
|
|
method=urlparse(url)[0]
|
|
@@ -125,5 +125,5 @@
|
|
the <BASE HREF=> tag."""
|
|
import htmllib
|
|
- from urlparse import *
|
|
+ from urlparse import urlparse
|
|
from formatter import NullFormatter
|
|
|