espri.cgi

   1 #!/usr/bin/python
   2 #
   3 # Part of the Objavi2 package.  This script imports e-books into Booki
   4 #
   5 # Copyright (C) 2009 Douglas Bagnall
   6 #
   7 # This program is free software; you can redistribute it and/or modify
   8 # it under the terms of the GNU General Public License as published by
   9 # the Free Software Foundation; either version 2 of the License, or
  10 # (at your option) any later version.
  11 #
  12 # This program is distributed in the hope that it will be useful,
  13 # but WITHOUT ANY WARRANTY; without even the implied warranty of
  14 # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  15 # GNU General Public License for more details.
  16 #
  17 # You should have received a copy of the GNU General Public License along
  18 # with this program; if not, write to the Free Software Foundation, Inc.,
  19 # 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
  20
  21 import os, sys
  22 import re, time
  23 from urllib2 import urlopen, HTTPError
  24 from urlparse import urlsplit
  25 from urllib import unquote
  26 import traceback
  27
  28 from objavi import epub
  29 from objavi.book_utils import log
  30 from objavi.cgi_utils import output_blob_and_exit, parse_args, print_template_and_exit, output_blob_and_shut_up
  31 from objavi.cgi_utils import is_name, is_utf8, is_url
  32 from objavi import config
  33
  34 IA_EPUB_URL = "http://www.archive.org/download/%s/%s.epub"
  35
  36 def print_form_and_exit(booklink):
  37     print_template_and_exit('templates/espri.html',
  38                             {'booklink': booklink, }
  39                             )
  40
  41 def async_start(content, mimetype):
  42     """Begin (and in many cases, finish) http output.
  43     In asynchronous modes, fork and close down stdout.
  44     """
  45     output_blob_and_shut_up(content, mimetype)
  46     log(sys.stdout, sys.stderr, sys.stdin)
  47     if os.fork():
  48         os._exit(0)
  49     sys.stdout.close()
  50     sys.stdin.close()
  51     #log(sys.stdout, sys.stderr, sys.stdin)
  52
  53
  54 def async_callback(callback_url, **kwargs):
  55     """Call the callback url with each message."""
  56     pid = os.fork()
  57     if pid:
  58         log('child %s is doing callback with message %r' % (pid, kwargs, ))
  59         return
  60     from urllib2 import urlopen, URLError
  61     from urllib import urlencode
  62     data = urlencode(kwargs)
  63     try:
  64         f = urlopen(callback_url, data)
  65         time.sleep(2)
  66         f.close()
  67     except URLError, e:
  68         traceback.print_exc()
  69         log("ERROR in callback:\n %r\n %s %s" % (e.url, e.code, e.msg))
  70     os._exit(0)
  71
  72
  73 def espri(epuburl, zipurl):
  74     f = urlopen(epuburl)
  75     s = f.read()
  76     f.close()
  77     e = epub.Epub()
  78     e.load(s)
  79     e.parse_meta()
  80     e.parse_opf()
  81     e.parse_ncx()
  82     e.make_bookizip(zipurl)
  83
  84 def ia_espri(book_id):
  85     epuburl = IA_EPUB_URL % (book_id, book_id)
  86     log(epuburl)
  87     zipurl = '%s/%s.zip' % (config.BOOKI_BOOK_DIR, book_id)
  88     espri(epuburl, zipurl)
  89     return zipurl
  90
  91 def inet_espri(epuburl):
  92     filename = '_'.join(unquote(os.path.basename(urlsplit(epuburl).path)).split())
  93     if filename.lower().endswith('.epub'):
  94         filename = filename[:-5]
  95     zipurl = '%s/%s-%s.zip' % (config.BOOKI_BOOK_DIR, filename, time.strftime('%F_%T'))
  96     espri(epuburl, zipurl)
  97     return zipurl
  98
  99 def wikibooks_espri(book_id):
 100     epuburl = IA_EPUB_URL % (book_id, book_id)
 101     log(epuburl)
 102     zipurl = '%s/%s.zip' % (config.BOOKI_BOOK_DIR, book_id)
 103     espri(epuburl, zipurl)
 104     return zipurl
 105     pass
 106
 107
 108 SOURCES = {
 109     'archive.org': {'function': ia_espri},
 110     'url': {'function': inet_espri},
 111     'wikibooks': {'function': wikibooks_espri},
 112 }
 113 ARG_VALIDATORS = {
 114     "source": SOURCES.__contains__,
 115     "book": is_utf8,
 116     "url": is_url,  #obsolete
 117     'mode': ('zip', 'html', 'callback').__contains__,
 118     'callback': is_url,
 119 }
 120
 121 def ensure_backwards_compatibility(args):
 122     """Mutate args to match previous API"""
 123     if 'url' in args:
 124         args['source'] = 'url'
 125         args['book'] = args['url']
 126     if 'source' not in args:
 127         args['source'] = 'archive.org'
 128
 129
 130 if __name__ == '__main__':
 131     log('here')
 132     args = parse_args(ARG_VALIDATORS)
 133     ensure_backwards_compatibility(args)
 134     mode = args.get('mode', 'html')
 135     book = args.get('book')
 136     source = args.get('source', 'archive.org')
 137     source_fn = SOURCES.get(source)['function']
 138
 139     if mode == 'callback':
 140         callback_url = args['callback']
 141         async_start('OK, got it...  will call %r when done' % (callback_url,),
 142                     'text/plain')
 143     log('here')
 144     url = None
 145     if book is not None:
 146         try:
 147             url = source_fn(book)
 148             book_link = '<p>Download <a href="%s">%s</a>.</p>' % (url, url)
 149         except Exception, e:
 150             traceback.print_exc()
 151             log(e, args)
 152             book_link = '<p>Error: <b>%s</b> when trying to get <b>%s</b></p>' % (e, book)
 153             if mode != 'html':
 154                 raise
 155     else:
 156         book_link = ''
 157
 158     log('here')
 159     if mode == 'callback':
 160         async_callback(callback_url, url=url)
 161
 162     elif mode == 'zip' and url is not None:
 163         f = open(url)
 164         data = f.read()
 165         f.close()
 166         output_blob_and_exit(data, config.BOOKIZIP_MIMETYPE,
 167                              os.path.basename(url))
 168     else:
 169         log(book_link)
 170         print_form_and_exit(book_link)
 171     log('done!')