Samuel L. Bayer:

- same trick with "import wcnew; webchecker = wcnew" as above
- updated readhtml() method to handle pair representation; used
  new name suppression infrastructure from wcnew.py to suppress
  processing name anchors

[And untabified --GvR]
This commit is contained in:
Guido van Rossum 1999-11-17 15:04:26 +00:00
parent a8946406df
commit 64acb5ce93
1 changed files with 12 additions and 4 deletions

View File

@ -10,7 +10,9 @@ import string
import urllib
import getopt
import webchecker
import wcnew
webchecker = wcnew
# Extract real version number if necessary
if __version__[0] == '$':
@ -45,14 +47,20 @@ def main():
class Sucker(webchecker.Checker):
checkext = 0
nonames = 1
def readhtml(self, url):
# SAM 11/13/99: in general, URLs are now URL pairs.
# Since we've suppressed name anchor checking,
# we can ignore the second dimension.
def readhtml(self, url_pair):
url = url_pair[0]
text = None
path = self.savefilename(url)
try:
f = open(path, "rb")
except IOError:
f = self.openpage(url)
f = self.openpage(url_pair)
if f:
info = f.info()
nurl = f.geturl()