From 6c619b7c47fcfaca8cebd86c3b7393f70081647d Mon Sep 17 00:00:00 2001 From: calvin Date: Thu, 6 Apr 2000 19:17:15 +0000 Subject: [PATCH] See ChangeLog git-svn-id: https://linkchecker.svn.sourceforge.net/svnroot/linkchecker/trunk/linkchecker@63 e7d03fd6-7b0d-0410-9947-9c21f3af8025 --- ChangeLog | 3 +++ Makefile | 9 ++++++--- README | 2 +- TODO | 2 -- linkcheck/Logging.py | 21 +++++++++++++++++++++ linkchecker | 12 +++++++----- 6 files changed, 38 insertions(+), 11 deletions(-) diff --git a/ChangeLog b/ChangeLog index 5dd724bb..27d1d285 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,3 +1,6 @@ +6.4.2000 + * forgot to include linkchecker script in .deb package + 30.3.2000 * support for NNTP news: links * forgot to put lc.fcgi and lc.sz_fcgi in release diff --git a/Makefile b/Makefile index cefe5203..cda7d009 100644 --- a/Makefile +++ b/Makefile @@ -1,8 +1,8 @@ VERSION=$(shell ./setup.py -V) -#HOST=treasure.calvinsplayground.de +HOST=treasure.calvinsplayground.de PROXY= #PROXY=-P$(HOST):5050 -HOST=fsinfo.cs.uni-sb.de +#HOST=fsinfo.cs.uni-sb.de #PROXY=-Pwww-proxy.uni-sb.de:3128 PACKAGE = linkchecker DEBPACKAGE = $(PACKAGE)_$(VERSION)_i386.deb @@ -20,8 +20,11 @@ clean: install: ./setup.py install --prefix=/tmp/usr --exec-prefix=/tmp/usr + # do what I mean, Distutils! cp -a /tmp/usr/* $(DESTDIR)/usr - install -c -m 644 linkcheckerrc $(DESTDIR)/etc + # remove following line if Distutils have script support + install -c m 755 linkchecker $(DESTDIR)/usr/bin/ + install -c -m 644 linkcheckerrc $(DESTDIR)/etc/ install -c -m 644 DNS/README $(DESTDIR)/usr/share/doc/$(PACKAGE)/README.dns dist: diff --git a/README b/README index a385ed3f..4ea4b23c 100644 --- a/README +++ b/README @@ -6,7 +6,7 @@ Features: o recursive checking o multithreaded o output can be colored or normal text, HTML, SQL or a GML sitemap graph -o HTTP/1.1, HTTPS, FTP, mailto:, Gopher, Telnet and local file links +o HTTP/1.1, HTTPS, FTP, mailto:, news:, Gopher, Telnet and local file links are supported Javascript links are currently ignored o restrict link checking to your local domain diff --git a/TODO b/TODO index 8eaf53a2..688e2624 100644 --- a/TODO +++ b/TODO @@ -1,7 +1,5 @@ High priority -o Stable release? After 1.1.4 there will be 1.2. - o DNS (and some URLs) seem to hang sometimes. Why? o I want to be able to supply a "break" command even when multiple diff --git a/linkcheck/Logging.py b/linkcheck/Logging.py index fe8dcf15..4a59fa06 100644 --- a/linkcheck/Logging.py +++ b/linkcheck/Logging.py @@ -383,3 +383,24 @@ class SQLLogger(StandardLogger): def endOfOutput(self): self.fd = None + + +class BlacklistLogger: + """Updates a blacklist of wrong links""" + def __init__(self, filename): + self.blacklist = {} + self.filename = filename + + def init(self): + """initialize the blacklist""" + pass + + def newUrl(self, urlData): + if urlData.valid: + self.blacklist[urlData.getCacheKey()] = None + elif not urlData.cached: + self.blacklist[urlData.getCacheKey()] = urlData + + def endOfOutput(self): + """write the blacklist""" + pass diff --git a/linkchecker b/linkchecker index 7b78468f..121d392e 100755 --- a/linkchecker +++ b/linkchecker @@ -84,16 +84,18 @@ OPTIONS Notes = """NOTES o LinkChecker assumes an http:// resp. ftp:// link when a commandline URL - starts with "www." resp. "ftp.". - You can also give local files as arguments. + starts with "www." resp. "ftp." + You can also give local files as arguments o If you have your system configured to automatically establish a connection to the internet (e.g. with diald), it will connect when - checking links not pointing to your local host. - Use the -s and -i options to prevent this (see EXAMPLES). + checking links not pointing to your local host + Use the -s and -i options to prevent this (see EXAMPLES) o Javascript links are currently ignored o If your platform does not support threading, linkchecker assumes -t0 o You can supply multiple user/password pairs in a configuration file -o Cookies are not accepted by LinkChecker. +o Cookies are not accepted by LinkChecker +o When checking news: links the given news host doesn't need to be the + same as the host of the user browsing your pages! """ Examples = """EXAMPLES