dosage/dosage
2013-03-01 20:56:32 +01:00

323 lines
11 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) 2012-2013 Bastian Kleineidam
from __future__ import print_function
import sys
import os
import argparse
import pydoc
from collections import OrderedDict
from dosagelib import events, scraper
from dosagelib.output import out
from dosagelib.util import internal_error, getDirname, strlimit
from dosagelib.ansicolor import get_columns
from dosagelib.configuration import App, Freeware, Copyright, SupportUrl
class ArgumentParser(argparse.ArgumentParser):
"""Custom argument parser."""
def print_help(self, file=None):
"""Paginate help message on TTYs."""
msg = self.format_help()
if file is None:
file = sys.stdout
if hasattr(file, "isatty") and file.isatty():
pydoc.pager(msg)
else:
print(msg, file=file)
Examples = """\
EXAMPLES
List available comics (ca. 3000 at the moment):
dosage -l
Get the latest comic of for example CalvinAndHobbes and save it in the "Comics"
directory:
dosage CalvinAndHobbes
If you already have downloaded several comics and want to get the latest
strips of all of them:
dosage --continue @
On Unix, xargs(1) can download several comic strips in parallel,
for example using up to 4 processes:
cd Comics && find . -type d | xargs -n1 -P4 dosage -b . -v
"""
def setupOptions():
"""Construct option parser.
@return: new option parser
@rtype argparse.ArgumentParser
"""
kwargs = dict(
description = "A commandline webcomic downloader and archiver.",
epilog = Examples,
formatter_class=argparse.RawDescriptionHelpFormatter,
)
if sys.argv[0].endswith("mainline"):
out.warn("the 'mainline' program is deprecated, please use the new 'dosage' program")
kwargs["prog"] = "dosage"
parser = ArgumentParser(**kwargs)
parser.add_argument('-v', '--verbose', action='count', default=0, help='provides verbose output, use multiple times for more verbosity')
parser.add_argument('-n', '--numstrips', action='store', type=int, default=0, help='traverse and retrieve the given number of comic strips; use --all to retrieve all comic strips')
parser.add_argument('-a', '--all', action='store_true', default=None, help='traverse and retrieve all comic strips')
parser.add_argument('-c', '--continue', action='store_true', dest='cont', default=None, help='traverse and retrieve comic strips until an existing one is found')
parser.add_argument('-b', '--basepath', action='store', default='Comics', help='set the path to create invidivual comic directories in, default is Comics', metavar='PATH')
parser.add_argument('--baseurl', action='store', default=None, help='the base URL of your comics directory (for RSS, HTML, etc.); this should correspond to --base-path', metavar='PATH')
parser.add_argument('-l', '--list', action='store_const', const=1, help='list available comic modules')
parser.add_argument('--singlelist', action='store_const', const=2, dest='list', help='list available comic modules in a single list')
parser.add_argument('--version', action='store_true', help='display the version number')
parser.add_argument('-m', '--modulehelp', action='store_true', help='display help for comic modules')
parser.add_argument('-t', '--timestamps', action='store_true', default=False, help='print timestamps for all output at any info level')
parser.add_argument('-o', '--output', action='store', choices=events.getHandlers(), help='output formatting for downloaded comics')
parser.add_argument('--adult', action='store_true', default=False, help='confirms that you are old enough to view adult content')
parser.add_argument('--multimatch', action='store_true', default=False, help='')
parser.add_argument('comic', nargs='+', help='comic module name (including case insensitive substrings)')
try:
import argcomplete
argcomplete.autocomplete(parser)
except ImportError:
pass
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.error('Could not save image at %s to %s: %s' % (image.referrer, image.filename, msg))
errors += 1
return errors, allskipped
def displayHelp(comics):
"""Print help for comic strips."""
try:
for scraperobj in getScrapers(comics):
displayComicHelp(scraperobj)
except ValueError as msg:
out.error(msg)
return 1
return 0
def displayComicHelp(scraperobj):
"""Print description and help for a comic."""
out.context = scraperobj.get_name()
try:
if scraperobj.description:
out.info("Description: " + scraperobj.description)
if scraperobj.help:
for line in scraperobj.help.splitlines():
out.info(line)
finally:
out.context = ''
def getComics(options):
"""Retrieve comics."""
errors = 0
if options.output:
events.installHandler(options.output, options.basepath, options.baseurl)
events.getHandler().start()
try:
for scraperobj in getScrapers(options.comic, options.basepath, options.adult, options.multimatch):
errors += getStrips(scraperobj, options)
except ValueError as msg:
out.error(msg)
errors += 1
finally:
out.context = ''
events.getHandler().end()
return errors
def getStrips(scraperobj, options):
"""Get all strips from a scraper."""
errors = 0
out.context = scraperobj.get_name()
if options.all:
strips = scraperobj.getAllStrips()
elif options.numstrips:
strips = scraperobj.getAllStrips(options.numstrips)
else:
strips = scraperobj.getCurrentStrips()
try:
for strip in strips:
_errors, skipped = saveComicStrip(strip, options.basepath)
errors += _errors
if skipped and options.cont:
# stop when retrieval skipped an image for one comic strip
out.info("Stop retrieval because image file already exists")
break
except (ValueError, IOError) as msg:
out.error(msg)
errors += 1
return errors
def run(options):
"""Execute comic commands."""
setOutputInfo(options)
if options.version:
return displayVersion()
if options.list:
return doList(options.list == 1)
if options.modulehelp:
return displayHelp(options.comic)
return getComics(options)
def doList(columnList):
"""List available comics."""
out.info('Available comic scrapers:')
out.info('Comics marked with [A] require age confirmation with the --adult option.')
scrapers = sorted(getScrapers(['@@']), key=lambda s: s.get_name())
try:
if columnList:
num = doColumnList(scrapers)
else:
num = doSingleList(scrapers)
out.info('%d supported comics.' % num)
except IOError:
pass
return 0
def doSingleList(scrapers):
"""Get list of scraper names, one per line."""
for num, scraperobj in enumerate(scrapers):
print(getScraperName(scraperobj))
return num
def doColumnList(scrapers):
"""Get list of scraper names with multiple names per line."""
screenWidth = get_columns(sys.stdout)
# limit name length so at least two columns are there
limit = (screenWidth / 2) - 8
names = [getScraperName(scraperobj, limit=limit) for scraperobj in scrapers]
num = len(names)
maxlen = max(len(name) for name in names)
namesPerLine = max(int(screenWidth / (maxlen + 1)), 1)
while names:
print(''.join(name.ljust(maxlen) for name in names[:namesPerLine]))
del names[:namesPerLine]
return num
def getScraperName(scraperobj, limit=None):
"""Get comic scraper name."""
suffix = " [A]" if scraperobj.adult else ""
name = scraperobj.get_name()
if limit is not None:
name = strlimit(name, limit)
return name + suffix
def getScrapers(comics, basepath=None, adult=True, multiple_allowed=False):
"""Get scraper objects for the given comics."""
if '@' in comics:
# only scrapers whose directory already exists
if len(comics) > 1:
out.warn("using '@' as comic name ignores all other specified comics.")
for scraperclass in scraper.get_scraperclasses():
if not adult and scraperclass.adult:
warn_adult(scraperclass)
continue
dirname = getDirname(scraperclass.get_name())
if os.path.isdir(os.path.join(basepath, dirname)):
yield scraperclass()
elif '@@' in comics:
# all scrapers
for scraperclass in scraper.get_scraperclasses():
if not adult and scraperclass.adult:
warn_adult(scraperclass)
continue
yield scraperclass()
else:
# get only selected comic scrapers
# store them in an ordered set to eliminate duplicates
scrapers = OrderedDict()
for comic in comics:
if ':' in comic:
name, index = comic.split(':', 1)
indexes = index.split(',')
else:
name = comic
indexes = None
for scraperclass in scraper.find_scraperclasses(name, multiple_allowed=multiple_allowed):
if not adult and scraperclass.adult:
warn_adult(scraperclass)
continue
scraperobj = scraperclass(indexes=indexes)
if scraperobj not in scrapers:
scrapers[scraperobj] = True
for scraperobj in scrapers:
yield scraperobj
def warn_adult(scraperclass):
"""Print warning about adult content."""
out.warn("skipping adult comic %s; use the --adult option to confirm your age" % scraperclass.get_name())
def main():
"""Parse options and execute commands."""
try:
parser = setupOptions()
res = run(parser.parse_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_scraperclasses()", "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()