|
#! /usr/bin/env python
"""Tkinter-based GUI for websucker.
Easy use: type or paste source URL and destination directory in
their respective text boxes, click GO or hit return, and presto.
"""
from Tkinter import *
import Tkinter
import websucker
import sys
import os
import threading
import Queue
import time
VERBOSE = 2
try:
class Canceled(Exception):
"Exception used to cancel run()."
except (NameError, TypeError):
Canceled = __name__ + ".Canceled"
class SuckerThread(websucker.Sucker):
stopit = 0
savedir = None
rootdir = None
def __init__(self, msgq):
self.msgq = msgq
websucker.Sucker.__init__(self)
self.setflags(verbose=VERBOSE)
self.urlopener.addheaders = [
('User-agent', 'websucker/%s' % websucker.__version__),
]
def message(self, format, *args):
if args:
format = format%args
##print format
self.msgq.put(format)
def run1(self, url):
try:
try:
self.reset()
self.addroot(url)
self.run()
except Canceled:
self.message("[canceled]")
else:
self.message("[done]")
finally:
self.msgq.put(None)
def savefile(self, text, path):
if self.stopit:
raise Canceled
websucker.Sucker.savefile(self, text, path)
def getpage(self, url):
if self.stopit:
raise Canceled
return websucker.Sucker.getpage(self, url)
def savefilename(self, url):
path = websucker.Sucker.savefilename(self, url)
if self.savedir:
n = len(self.rootdir)
if path[:n] == self.rootdir:
path = path[n:]
while path[:1] == os.sep:
path = path[1:]
path = os.path.join(self.savedir, path)
return path
def XXXaddrobot(self, *args):
pass
def XXXisallowed(self, *args):
return 1
class App:
sucker = None
msgq = None
def __init__(self, top):
self.top = top
top.columnconfigure(99, weight=1)
self.url_label = Label(top, text="URL:")
self.url_label.grid(row=0, column=0, sticky='e')
self.url_entry = Entry(top, width=60, exportselection=0)
self.url_entry.grid(row=0, column=1, sticky='we',
columnspan=99)
self.url_entry.focus_set()
self.url_entry.bind("<Key-Return>", self.go)
self.dir_label = Label(top, text="Directory:")
self.dir_label.grid(row=1, column=0, sticky='e')
self.dir_entry = Entry(top)
self.dir_entry.grid(row=1, column=1, sticky='we',
columnspan=99)
self.go_button = Button(top, text="Go", command=self.go)
self.go_button.grid(row=2, column=1, sticky='w')
self.cancel_button = Button(top, text="Cancel",
command=self.cancel,
state=DISABLED)
self.cancel_button.grid(row=2, column=2, sticky='w')
self.auto_button = Button(top, text="Paste+Go",
command=self.auto)
self.auto_button.grid(row=2, column=3, sticky='w')
self.status_label = Label(top, text="[idle]")
self.status_label.grid(row=2, column=4, sticky='w')
self.top.update_idletasks()
self.top.grid_propagate(0)
def message(self, text, *args):
if args:
text = text % args
self.status_label.config(text=text)
def check_msgq(self):
while not self.msgq.empty():
msg = self.msgq.get()
if msg is None:
self.go_button.configure(state=NORMAL)
self.auto_button.configure(state=NORMAL)
self.cancel_button.configure(state=DISABLED)
if self.sucker:
self.sucker.stopit = 0
self.top.bell()
else:
self.message(msg)
self.top.after(100, self.check_msgq)
def go(self, event=None):
if not self.msgq:
self.msgq = Queue.Queue(0)
self.check_msgq()
if not self.sucker:
self.sucker = SuckerThread(self.msgq)
if self.sucker.stopit:
return
self.url_entry.selection_range(0, END)
url = self.url_entry.get()
url = url.strip()
if not url:
self.top.bell()
self.message("[Error: No URL entered]")
return
self.rooturl = url
dir = self.dir_entry.get().strip()
if not dir:
self.sucker.savedir = None
else:
self.sucker.savedir = dir
self.sucker.rootdir = os.path.dirname(
websucker.Sucker.savefilename(self.sucker, url))
self.go_button.configure(state=DISABLED)
self.auto_button.configure(state=DISABLED)
self.cancel_button.configure(state=NORMAL)
self.message( '[running...]')
self.sucker.stopit = 0
t = threading.Thread(target=self.sucker.run1, args=(url,))
t.start()
def cancel(self):
if self.sucker:
self.sucker.stopit = 1
self.message("[canceling...]")
def auto(self):
tries = ['PRIMARY', 'CLIPBOARD']
text = ""
for t in tries:
try:
text = self.top.selection_get(selection=t)
except TclError:
continue
text = text.strip()
if text:
break
if not text:
self.top.bell()
self.message("[Error: clipboard is empty]")
return
self.url_entry.delete(0, END)
self.url_entry.insert(0, text)
self.go()
class AppArray:
def __init__(self, top=None):
if not top:
top = Tk()
top.title("websucker GUI")
top.iconname("wsgui")
top.wm_protocol('WM_DELETE_WINDOW', self.exit)
self.top = top
self.appframe = Frame(self.top)
self.appframe.pack(fill='both')
self.applist = []
self.exit_button = Button(top, text="Exit", command=self.exit)
self.exit_button.pack(side=RIGHT)
self.new_button = Button(top, text="New", command=self.addsucker)
self.new_button.pack(side=LEFT)
self.addsucker()
##self.applist[0].url_entry.insert(END, "http://www.python.org/doc/essays/")
def addsucker(self):
self.top.geometry("")
frame = Frame(self.appframe, borderwidth=2, relief=GROOVE)
frame.pack(fill='x')
app = App(frame)
self.applist.append(app)
done = 0
def mainloop(self):
while not self.done:
time.sleep(0.1)
self.top.update()
def exit(self):
for app in self.applist:
app.cancel()
app.message("[exiting...]")
self.done = 1
def main():
AppArray().mainloop()
if __name__ == '__main__':
main()
#! /usr/bin/env python
"""A variant on webchecker that creates a mirror copy of a remote site."""
__version__ = "$Revision: 1.10 $"
import os
import sys
import urllib
import getopt
import webchecker
# Extract real version number if necessary
if __version__[0] == '$':
_v = __version__.split()
if len(_v) == 3:
__version__ = _v[1]
def main():
verbose = webchecker.VERBOSE
try:
opts, args = getopt.getopt(sys.argv[1:], "qv")
except getopt.error, msg:
print msg
print "usage:", sys.argv[0], "[-qv] ... [rooturl] ..."
return 2
for o, a in opts:
if o == "-q":
verbose = 0
if o == "-v":
verbose = verbose + 1
c = Sucker()
c.setflags(verbose=verbose)
c.urlopener.addheaders = [
('User-agent', 'websucker/%s' % __version__),
]
for arg in args:
print "Adding root", arg
c.addroot(arg)
print "Run..."
c.run()
class Sucker(webchecker.Checker):
checkext = 0
nonames = 1
# 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_pair)
if f:
info = f.info()
nurl = f.geturl()
if nurl != url:
url = nurl
path = self.savefilename(url)
text = f.read()
f.close()
self.savefile(text, path)
if not self.checkforhtml(info, url):
text = None
else:
if self.checkforhtml({}, url):
text = f.read()
f.close()
return text, url
def savefile(self, text, path):
dir, base = os.path.split(path)
makedirs(dir)
try:
f = open(path, "wb")
f.write(text)
f.close()
self.message("saved %s", path)
except IOError, msg:
self.message("didn't save %s: %s", path, str(msg))
def savefilename(self, url):
type, rest = urllib.splittype(url)
host, path = urllib.splithost(rest)
path = path.lstrip("/")
user, host = urllib.splituser(host)
host, port = urllib.splitnport(host)
host = host.lower()
if not path or path[-1] == "/":
path = path + "index.html"
if os.sep != "/":
path = os.sep.join(path.split("/"))
if os.name == "mac":
path = os.sep + path
path = os.path.join(host, path)
return path
def makedirs(dir):
if not dir:
return
if os.path.exists(dir):
if not os.path.isdir(dir):
try:
os.rename(dir, dir + ".bak")
os.mkdir(dir)
os.rename(dir + ".bak", os.path.join(dir, "index.html"))
except os.error:
pass
return
head, tail = os.path.split(dir)
if not tail:
print "Huh? Don't know how to make dir", dir
return
makedirs(head)
os.mkdir(dir, 0777)
if __name__ == '__main__':
sys.exit(main() or 0)
###webchecker.py###################################################################################
#! /usr/bin/env python
# Original code by Guido van Rossum; extensive changes by Sam Bayer,
# including code to check URL fragments.
"""Web tree checker.
This utility is handy to check a subweb of the world-wide web for
errors. A subweb is specified by giving one or more ''root URLs''; a
page belongs to the subweb if one of the root URLs is an initial
prefix of it.
File URL extension:
In order to easy the checking of subwebs via the local file system,
the interpretation of ''file:'' URLs is extended to mimic the behavior
of your average HTTP daemon: if a directory pathname is given, the
file index.html in that directory is returned if it exists, otherwise
a directory listing is returned. Now, you can point webchecker to the
document tree in the local file system of your HTTP daemon, and have
most of it checked. In fact the default works this way if your local
web tree is located at /usr/local/etc/httpd/htdpcs (the default for
the NCSA HTTP daemon and probably others).
Report printed:
When done, it reports pages with bad links within the subweb. When
interrupted, it reports for the pages that it has checked already.
In verbose mode, additional messages are printed during the
information gathering phase. By default, it prints a summary of its
work status every 50 URLs (adjustable with the -r option), and it
reports errors as they are encountered. Use the -q option to disable
this output.
Checkpoint feature:
Whether interrupted or not, it dumps its state (a Python pickle) to a
checkpoint file and the -R option allows it to restart from the
checkpoint (assuming that the pages on the subweb that were already
processed haven't changed). Even when it has run till completion, -R
can still be useful -- it will print the reports again, and -Rq prints
the errors only. In this case, the checkpoint file is not written
again. The checkpoint file can be set with the -d option.
The checkpoint file is written as a Python pickle. Remember that
Python's pickle module is currently quite slow. Give it the time it
needs to load and save the checkpoint file. When interrupted while
writing the checkpoint file, the old checkpoint file is not
overwritten, but all work done in the current run is lost.
Miscellaneous:
- You may find the (Tk-based) GUI version easier to use. See wcgui.py.
- Webchecker honors the "robots.txt" convention. Thanks to Skip
Montanaro for his robotparser.py module (included in this directory)!
The agent name is hardwired to "webchecker". URLs that are disallowed
by the robots.txt file are reported as external URLs.
- Because the SGML parser is a bit slow, very large SGML files are
skipped. The size limit can be set with the -m option.
- When the server or protocol does not tell us a file's type, we guess
it based on the URL's suffix. The mimetypes.py module (also in this
directory) has a built-in table mapping most currently known suffixes,
and in addition attempts to read the mime.types configuration files in
the default locations of Netscape and the NCSA HTTP daemon.
- We follow links indicated by <A>, <FRAME> and <IMG> tags. We also
honor the <BASE> tag.
- We now check internal NAME anchor links, as well as toplevel links.
- Checking external links is now done by default; use -x to *disable*
this feature. External links are now checked during normal
processing. (XXX The status of a checked link could be categorized
better. Later...)
- If external links are not checked, you can use the -t flag to
provide specific overrides to -x.
Usage: webchecker.py [option] ... [rooturl] ...
Options:
-R -- restart from checkpoint file
-d file -- checkpoint filename (default %(DUMPFILE)s)
-m bytes -- skip HTML pages larger than this size (default %(MAXPAGE)d)
-n -- reports only, no checking (use with -R)
-q -- quiet operation (also suppresses external links report)
-r number -- number of links processed per round (default %(ROUNDSIZE)d)
-t root -- specify root dir which should be treated as internal (can repeat)
-v -- verbose operation; repeating -v will increase verbosity
-x -- don't check external links (these are often slow to check)
-a -- don't check name anchors
Arguments:
rooturl -- URL to start checking
(default %(DEFROOT)s)
"""
__version__ = "$Revision: 1.32 $"
import sys
import os
from types import *
import StringIO
import getopt
import pickle
import urllib
import urlparse
import sgmllib
import cgi
import mimetypes
import robotparser
# Extract real version number if necessary
if __version__[0] == '$':
_v = __version__.split()
if len(_v) == 3:
__version__ = _v[1]
# Tunable parameters
DEFROOT = "file:/usr/local/etc/httpd/htdocs/" # Default root URL
CHECKEXT = 1 # Check external references (1 deep)
VERBOSE = 1 # Verbosity level (0-3)
MAXPAGE = 150000 # Ignore files bigger than this
ROUNDSIZE = 50 # Number of links processed per round
DUMPFILE = "@webchecker.pickle" # Pickled checkpoint
AGENTNAME = "webchecker" # Agent name for robots.txt parser
NONAMES = 0 # Force name anchor checking
# Global variables
def main():
checkext = CHECKEXT
verbose = VERBOSE
maxpage = MAXPAGE
roundsize = ROUNDSIZE
dumpfile = DUMPFILE
restart = 0
norun = 0
try:
opts, args = getopt.getopt(sys.argv[1:], 'Rd:m:nqr:t:vxa')
except getopt.error, msg:
sys.stdout = sys.stderr
print msg
print __doc__%globals()
sys.exit(2)
# The extra_roots variable collects extra roots.
extra_roots = []
nonames = NONAMES
for o, a in opts:
if o == '-R':
restart = 1
if o == '-d':
dumpfile = a
if o == '-m':
maxpage = int(a)
if o == '-n':
norun = 1
if o == '-q':
verbose = 0
if o == '-r':
roundsize = int(a)
if o == '-t':
extra_roots.append(a)
if o == '-a':
nonames = not nonames
if o == '-v':
verbose = verbose + 1
if o == '-x':
checkext = not checkext
if verbose > 0:
print AGENTNAME, "version", __version__
if restart:
c = load_pickle(dumpfile=dumpfile, verbose=verbose)
else:
c = Checker()
c.setflags(checkext=checkext, verbose=verbose,
maxpage=maxpage, roundsize=roundsize,
nonames=nonames
)
if not restart and not args:
args.append(DEFROOT)
for arg in args:
c.addroot(arg)
# The -t flag is only needed if external links are not to be
# checked. So -t values are ignored unless -x was specified.
if not checkext:
for root in extra_roots:
# Make sure it's terminated by a slash,
# so that addroot doesn't discard the last
# directory component.
if root[-1] != "/":
root = root + "/"
c.addroot(root, add_to_do = 0)
try:
if not norun:
try:
c.run()
except KeyboardInterrupt:
if verbose > 0:
print "[run interrupted]"
try:
c.report()
except KeyboardInterrupt:
if verbose > 0:
print "[report interrupted]"
finally:
if c.save_pickle(dumpfile):
if dumpfile == DUMPFILE:
print "Use ''%s -R'' to restart." % sys.argv[0]
else:
print "Use ''%s -R -d %s'' to restart." % (sys.argv[0],
dumpfile)
def load_pickle(dumpfile=DUMPFILE, verbose=VERBOSE):
if verbose > 0:
print "Loading checkpoint from %s ..." % dumpfile
f = open(dumpfile, "rb")
c = pickle.load(f)
f.close()
if verbose > 0:
print "Done."
print "Root:", "\n ".join(c.roots)
return c
class Checker:
checkext = CHECKEXT
verbose = VERBOSE
maxpage = MAXPAGE
roundsize = ROUNDSIZE
nonames = NONAMES
validflags = tuple(dir())
def __init__(self):
self.reset()
def setflags(self, **kw):
for key in kw.keys():
if key not in self.validflags:
raise NameError, "invalid keyword argument: %s" % str(key)
for key, value in kw.items():
setattr(self, key, value)
def reset(self):
self.roots = []
self.todo = {}
self.done = {}
self.bad = {}
# Add a name table, so that the name URLs can be checked. Also
# serves as an implicit cache for which URLs are done.
self.name_table = {}
self.round = 0
# The following are not pickled:
self.robots = {}
self.errors = {}
self.urlopener = MyURLopener()
self.changed = 0
def note(self, level, format, *args):
if self.verbose > level:
if args:
format = format%args
self.message(format)
def message(self, format, *args):
if args:
format = format%args
print format
def __getstate__(self):
return (self.roots, self.todo, self.done, self.bad, self.round)
def __setstate__(self, state):
self.reset()
(self.roots, self.todo, self.done, self.bad, self.round) = state
for root in self.roots:
self.addrobot(root)
for url in self.bad.keys():
self.markerror(url)
def addroot(self, root, add_to_do = 1):
if root not in self.roots:
troot = root
scheme, netloc, path, params, query, fragment = \
|
