dosage/dosage
2012-11-28 18:15:12 +01:00

221 lines
7.8 KiB
Python
Executable file

#!/usr/bin/env python
# -*- coding: iso-8859-1 -*-
# Dosage, the webcomic downloader
# Copyright (C) 2004-2005 Tristan Seligmann and Jonathan Jacobs
# Copyright (C) 2012 Bastian Kleineidam
#
# This program is free software; you can redistribute it and/or modify
# it under the terms of version 2 of the GNU General Public License as
# published by the Free Software Foundation.
#
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
# GNU General Public License for more details.
#
# You should have received a copy of the GNU General Public License
# along with this program; if not, write to the Free Software
# Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
from __future__ import print_function
import sys
import os
import optparse
from dosagelib import events, scraper
from dosagelib.output import out
from dosagelib.util import get_columns, internal_error
from dosagelib.configuration import App, Freeware, Copyright, SupportUrl
def setupOptions():
"""Construct option parser.
@return: new option parser
@rtype optparse.OptionParser
"""
usage = 'usage: %prog [options] comicModule [comicModule ...]'
parser = optparse.OptionParser(usage=usage)
parser.add_option('-v', '--verbose', action='count', dest='verbose', default=0, help='provides verbose output, use multiple times for more verbosity')
parser.add_option('-a', '--all', action='count', dest='all', default=None, help='traverse and retrieve all available comics')
parser.add_option('-b', '--basepath', action='store', dest='basepath', default='Comics', help='set the path to create invidivual comic directories in, default is Comics', metavar='PATH')
parser.add_option('--baseurl', action='store', dest='baseurl', default=None, help='the base URL of your comics directory (for RSS, HTML, etc.); this should correspond to --base-path', metavar='PATH')
parser.add_option('-l', '--list', action='store_const', const=1, dest='list', help='list available comic modules')
parser.add_option('--singlelist', action='store_const', const=2, dest='list', help='list available comic modules in a single list')
parser.add_option('-V', '--version', action='store_true', dest='version', help='display the version number')
parser.add_option('-m', '--modulehelp', action='store_true', dest='modhelp', help='display help for comic modules')
parser.add_option('-t', '--timestamps', action='store_true', dest='timestamps', default=False, help='print timestamps for all output at any info level')
parser.add_option('-o', '--output', action='store', dest='output', choices=events.getHandlers(), help='output formatting for downloaded comics')
return parser
def displayVersion():
"""Display application name, version, copyright and license."""
print(App)
print(Copyright)
print(Freeware)
print("For support see", SupportUrl)
return 0
def setOutputInfo(options):
"""Set global output level and timestamp option."""
out.level = 0
out.level += options.verbose
out.timestamps = options.timestamps
def saveComicStrip(strip, basepath):
"""Save a comic strip which can consist of multiple images."""
errors = 0
allskipped = True
for image in strip.getImages():
try:
filename, saved = image.save(basepath)
if saved:
allskipped = False
except IOError as msg:
out.write('Error saving %s: %s' % (image.filename, msg))
errors += 1
return errors, allskipped
def displayHelp(comics, basepath):
"""Print help for comic strips."""
for scraperobj in getScrapers(comics, basepath):
for line in scraperobj.getHelp().splitlines():
out.write("Help: "+line)
return 0
def getComics(options, comics):
"""Retrieve given comics."""
errors = 0
if options.output:
events.installHandler(options.output, options.basepath, options.baseurl)
events.getHandler().start()
for scraperobj in getScrapers(comics, options.basepath):
out.context = scraperobj.get_name()
if options.all:
strips = scraperobj.getAllStrips()
else:
strips = scraperobj.getCurrentStrips()
first = True
for strip in strips:
_errors, skipped = saveComicStrip(strip, options.basepath)
errors += _errors
if not first and scraperobj.indexes:
# stop when indexed retrieval skipped all images for one
# comie strip (except the first one)
out.write("Stop retrieval because image file already exists")
break
first = False
events.getHandler().end()
return errors
def run(options, comics):
"""Execute comic commands."""
setOutputInfo(options)
if options.version:
return displayVersion()
if options.list:
return doList(options.list == 1)
if len(comics) <= 0:
out.write('Warning: No comics specified, bailing out!')
return 1
try:
if options.modhelp:
return displayHelp(comics, options.basepath)
return getComics(options, comics)
except ValueError as msg:
out.write("Error: %s" % msg)
return 1
def doList(columnList):
"""List available comics."""
out.write('Available comic scrapers:')
scrapers = getScrapers(['@@'])
if columnList:
num = doColumnList(scrapers)
else:
num = doSingleList(scrapers)
out.write('%d supported comics.' % num)
return 0
def doSingleList(scrapers):
"""Get list of scraper names, one per line."""
for num, scraperobj in enumerate(scrapers):
print(scraperobj.get_name())
return num
def doColumnList(scrapers):
"""Get list of scraper names with multiple names per line."""
screenWidth = get_columns(sys.stdout)
names = [scraperobj.get_name() for scraperobj in scrapers]
num = len(names)
maxlen = max([len(name) for name in names])
namesPerLine = int(screenWidth / (maxlen + 1))
while names:
print(''.join([name.ljust(maxlen) for name in names[:namesPerLine]]))
del names[:namesPerLine]
return num
def getScrapers(comics, basepath=None):
"""Get scraper objects for the given comics."""
if '@' in comics:
# only scrapers whose directory already exists
if len(comics) > 1:
out.write("WARN: using '@' as comic name ignores all other specified comics.\n")
for scraperclass in scraper.get_scrapers():
dirname = scraperclass.get_name().replace('/', os.sep)
if os.path.isdir(os.path.join(basepath, dirname)):
yield scraperclass()
elif '@@' in comics:
# all scrapers
for scraperclass in scraper.get_scrapers():
yield scraperclass()
else:
# only selected
for comic in comics:
if ':' in comic:
name, index = comic.split(':', 1)
indexes = index.split(',')
else:
name = comic
indexes = None
yield scraper.get_scraper(name)(indexes=indexes)
def main():
"""Parse options and execute commands."""
try:
parser = setupOptions()
options, args = parser.parse_args()
res = run(options, args)
except KeyboardInterrupt:
print("Aborted.")
res = 1
except Exception:
internal_error()
res = 2
return res
def profile():
"""Profile the loading of all scrapers."""
import cProfile
cProfile.run("scraper.get_scrapers()", "dosage.prof")
def viewprof():
"""View profile stats."""
import pstats
stats = pstats.Stats("dosage.prof")
stats.strip_dirs().sort_stats("cumulative").print_stats(100)
if __name__ == '__main__':
sys.exit(main())
#profile()
#viewprof()