def initialize(self):
self.beginResetModel()
self.plugins = list(all_metadata_plugins())
self.plugins.sort(key=attrgetter('name'))
self.enabled_overrides = {}
self.cover_overrides = {}
self.endResetModel()
def option_parser():
parser = OptionParser(_('''\
%prog [options]
Fetch book metadata from online sources. You must specify at least one
of title, authors or ISBN.
'''
))
parser.add_option('-t', '--title', help=_('Book title'))
parser.add_option('-a', '--authors', help=_('Book author(s)'))
parser.add_option('-i', '--isbn', help=_('Book ISBN'))
parser.add_option('-I', '--identifier', action='append', default=[], help=_(
'Identifiers such as ASIN/goodreads id etc. Can be specified multiple times for multiple identifiers.'
' For example: ') + '--identifier asin:B0082BAJA0')
parser.add_option('-v', '--verbose', default=False, action='store_true',
help=_('Print the log to the console (stderr)'))
parser.add_option('-o', '--opf', help=_('Output the metadata in OPF format instead of human readable text.'), action='store_true', default=False)
parser.add_option('-c', '--cover',
help=_('Specify a filename. The cover, if available, will be saved to it. Without this option, no cover will be downloaded.'))
parser.add_option('-d', '--timeout', default='30',
help=_('Timeout in seconds. Default is 30'))
parser.add_option('-p', '--allowed-plugin', action='append', default=[],
help=_('Specify the name of a metadata download plugin to use.'
' By default, all metadata plugins will be used.'
' Can be specified multiple times for multiple plugins.'
' All plugin names: {}').format(', '.join(p.name for p in all_metadata_plugins())))
return parser
def option_parser():
parser = OptionParser(_('''\
%prog [options]
Fetch book metadata from online sources. You must specify at least one
of title, authors or ISBN.
'''
))
parser.add_option('-t', '--title', help=_('Book title'))
parser.add_option('-a', '--authors', help=_('Book author(s)'))
parser.add_option('-i', '--isbn', help=_('Book ISBN'))
parser.add_option('-I', '--identifier', action='append', default=[], help=_(
'Identifiers such as ASIN/goodreads id etc. Can be specified multiple times for multiple identifiers.'
' For example: ') + '--identifier asin:B0082BAJA0')
parser.add_option('-v', '--verbose', default=False, action='store_true',
help=_('Print the log to the console (stderr)'))
parser.add_option('-o', '--opf', help=_('Output the metadata in OPF format instead of human readable text.'), action='store_true', default=False)
parser.add_option('-c', '--cover',
help=_('Specify a filename. The cover, if available, will be saved to it. Without this option, no cover will be downloaded.'))
parser.add_option('-d', '--timeout', default='30',
help=_('Timeout in seconds. Default is 30'))
parser.add_option('-p', '--allowed-plugin', action='append', default=[],
help=_('Specify the name of a metadata download plugin to use.'
' By default, all metadata plugins will be used.'
' Can be specified multiple times for multiple plugins.'
' All plugin names: {}').format(', '.join(p.name for p in all_metadata_plugins())))
return parser
def urls_from_identifiers(identifiers): # {{{
identifiers = dict([(k.lower(), v) for k, v in identifiers.iteritems()])
ans = []
for plugin in all_metadata_plugins():
try:
id_type, id_val, url = plugin.get_book_url(identifiers)
ans.append((plugin.get_book_url_name(id_type, id_val, url), id_type, id_val, url))
except:
pass
isbn = identifiers.get('isbn', None)
if isbn:
ans.append((isbn, 'isbn', isbn,
'http://www.worldcat.org/isbn/'+isbn))
doi = identifiers.get('doi', None)
if doi:
ans.append(('DOI', 'doi', doi,
'http://dx.doi.org/'+doi))
arxiv = identifiers.get('arxiv', None)
if arxiv:
ans.append(('arXiv', 'arxiv', arxiv,
'http://arxiv.org/abs/'+arxiv))
oclc = identifiers.get('oclc', None)
if oclc:
ans.append(('OCLC', 'oclc', oclc,
'http://www.worldcat.org/oclc/'+oclc))
url = identifiers.get('uri', None)
if url is None:
url = identifiers.get('url', None)
if url and url.startswith('http'):
url = url[:8].replace('|', ':') + url[8:].replace('|', ',')
parts = urlparse(url)
name = parts.netloc
ans.append((name, 'url', url, url))
return ans
def initialize(self):
self.beginResetModel()
self.plugins = list(all_metadata_plugins())
self.plugins.sort(key=attrgetter('name'))
self.enabled_overrides = {}
self.cover_overrides = {}
self.endResetModel()
def urls_from_identifiers(identifiers): # {{{
identifiers = dict([(k.lower(), v) for k, v in identifiers.iteritems()])
ans = []
for plugin in all_metadata_plugins():
try:
id_type, id_val, url = plugin.get_book_url(identifiers)
ans.append((plugin.get_book_url_name(id_type, id_val,
url), id_type, id_val, url))
except:
pass
isbn = identifiers.get('isbn', None)
if isbn:
ans.append(
(isbn, 'isbn', isbn, 'http://www.worldcat.org/isbn/' + isbn))
doi = identifiers.get('doi', None)
if doi:
ans.append(('DOI', 'doi', doi, 'http://dx.doi.org/' + doi))
arxiv = identifiers.get('arxiv', None)
if arxiv:
ans.append(('arXiv', 'arxiv', arxiv, 'http://arxiv.org/abs/' + arxiv))
oclc = identifiers.get('oclc', None)
if oclc:
ans.append(
('OCLC', 'oclc', oclc, 'http://www.worldcat.org/oclc/' + oclc))
url = identifiers.get('uri', None)
if url is None:
url = identifiers.get('url', None)
if url and url.startswith('http'):
url = url[:8].replace('|', ':') + url[8:].replace('|', ',')
parts = urlparse(url)
name = parts.netloc
ans.append((name, 'url', url, url))
return ans
def no_tags_from_other_plugins():
from calibre.customize.ui import all_metadata_plugins
for plugin in all_metadata_plugins():
if plugin.name == GoodreadsMoreTags.name:
continue
if 'ignore_fields' not in plugin.prefs:
plugin.prefs['ignore_fields'] = []
plugin.prefs['ignore_fields'].append('tags')
def initialize(self):
fields = set()
for p in all_metadata_plugins():
fields |= p.touched_fields
self.fields = []
for x in fields:
if not x.startswith('identifier:') and x not in self.exclude:
self.fields.append(x)
self.fields.sort(key=lambda x:self.descs.get(x, x))
self.reset()
def initialize(self):
fields = set()
for p in all_metadata_plugins():
fields |= p.touched_fields
self.fields = []
for x in fields:
if not x.startswith('identifier:') and x not in self.exclude:
self.fields.append(x)
self.fields.sort(key=lambda x: self.descs.get(x, x))
self.reset()
def urls_from_identifiers(identifiers): # {{{
identifiers = {k.lower(): v for k, v in identifiers.iteritems()}
ans = []
rules = msprefs['id_link_rules']
if rules:
formatter = EvalFormatter()
for k, val in identifiers.iteritems():
vals = {
'id':
quote(val if isinstance(val, bytes) else val.encode('utf-8')).
decode('ascii')
}
items = rules.get(k) or ()
for name, template in items:
try:
url = formatter.safe_format(template, vals, '', vals)
except Exception:
import traceback
traceback.format_exc()
continue
ans.append((name, k, val, url))
for plugin in all_metadata_plugins():
try:
for id_type, id_val, url in plugin.get_book_urls(identifiers):
ans.append(
(plugin.get_book_url_name(id_type, id_val,
url), id_type, id_val, url))
except:
pass
isbn = identifiers.get('isbn', None)
if isbn:
ans.append(
(isbn, 'isbn', isbn, 'http://www.worldcat.org/isbn/' + isbn))
doi = identifiers.get('doi', None)
if doi:
ans.append(('DOI', 'doi', doi, 'http://dx.doi.org/' + doi))
arxiv = identifiers.get('arxiv', None)
if arxiv:
ans.append(('arXiv', 'arxiv', arxiv, 'http://arxiv.org/abs/' + arxiv))
oclc = identifiers.get('oclc', None)
if oclc:
ans.append(
('OCLC', 'oclc', oclc, 'http://www.worldcat.org/oclc/' + oclc))
issn = check_issn(identifiers.get('issn', None))
if issn:
ans.append(
(issn, 'issn', issn, 'http://www.worldcat.org/issn/' + issn))
for k, url in identifiers.iteritems():
if url and re.match(r'ur[il]\d*$', k) is not None:
url = url[:8].replace('|', ':') + url[8:].replace('|', ',')
if url.partition(':')[0].lower() in {'http', 'file', 'https'}:
parts = urlparse(url)
name = parts.netloc or parts.path
ans.append((name, k, url, url))
return ans
def urls_from_identifiers(identifiers): # {{{
identifiers = {k.lower():v for k, v in identifiers.iteritems()}
ans = []
rules = msprefs['id_link_rules']
if rules:
formatter = EvalFormatter()
for k, val in identifiers.iteritems():
vals = {'id':quote(val if isinstance(val, bytes) else val.encode('utf-8')).decode('ascii')}
items = rules.get(k) or ()
for name, template in items:
try:
url = formatter.safe_format(template, vals, '', vals)
except Exception:
import traceback
traceback.format_exc()
continue
ans.append((name, k, val, url))
for plugin in all_metadata_plugins():
try:
for id_type, id_val, url in plugin.get_book_urls(identifiers):
ans.append((plugin.get_book_url_name(id_type, id_val, url), id_type, id_val, url))
except:
pass
isbn = identifiers.get('isbn', None)
if isbn:
ans.append((isbn, 'isbn', isbn,
'http://www.worldcat.org/isbn/'+isbn))
doi = identifiers.get('doi', None)
if doi:
ans.append(('DOI', 'doi', doi,
'http://dx.doi.org/'+doi))
arxiv = identifiers.get('arxiv', None)
if arxiv:
ans.append(('arXiv', 'arxiv', arxiv,
'http://arxiv.org/abs/'+arxiv))
oclc = identifiers.get('oclc', None)
if oclc:
ans.append(('OCLC', 'oclc', oclc,
'http://www.worldcat.org/oclc/'+oclc))
issn = check_issn(identifiers.get('issn', None))
if issn:
ans.append((issn, 'issn', issn,
'http://www.worldcat.org/issn/'+issn))
for k, url in identifiers.iteritems():
if url and re.match(r'ur[il]\d*$', k) is not None:
url = url[:8].replace('|', ':') + url[8:].replace('|', ',')
if url.partition(':')[0].lower() in {'http', 'file', 'https'}:
parts = urlparse(url)
name = parts.netloc or parts.path
ans.append((name, k, url, url))
return ans
def urls_from_identifiers(identifiers): # {{{
identifiers = {k.lower(): v for k, v in identifiers.iteritems()}
ans = []
for plugin in all_metadata_plugins():
try:
for id_type, id_val, url in plugin.get_book_urls(identifiers):
ans.append(
(plugin.get_book_url_name(id_type, id_val,
url), id_type, id_val, url))
except:
pass
isbn = identifiers.get('isbn', None)
if isbn:
ans.append(
(isbn, 'isbn', isbn, 'http://www.worldcat.org/isbn/' + isbn))
doi = identifiers.get('doi', None)
if doi:
ans.append(('DOI', 'doi', doi, 'http://dx.doi.org/' + doi))
arxiv = identifiers.get('arxiv', None)
if arxiv:
ans.append(('arXiv', 'arxiv', arxiv, 'http://arxiv.org/abs/' + arxiv))
oclc = identifiers.get('oclc', None)
if oclc:
ans.append(
('OCLC', 'oclc', oclc, 'http://www.worldcat.org/oclc/' + oclc))
issn = check_issn(identifiers.get('issn', None))
if issn:
ans.append(
(issn, 'issn', issn, 'http://www.worldcat.org/issn/' + issn))
for k, url in identifiers.iteritems():
if url and re.match(r'ur[il]\d*$', k) is not None and url.partition(
':')[0].lower() in {'http', 'file', 'https'}:
url = url[:8].replace('|', ':') + url[8:].replace('|', ',')
parts = urlparse(url)
name = parts.netloc or parts.path
ans.append((name, k, url, url))
return ans
def urls_from_identifiers(identifiers): # {{{
identifiers = {k.lower():v for k, v in identifiers.iteritems()}
ans = []
for plugin in all_metadata_plugins():
try:
for id_type, id_val, url in plugin.get_book_urls(identifiers):
ans.append((plugin.get_book_url_name(id_type, id_val, url), id_type, id_val, url))
except:
pass
isbn = identifiers.get('isbn', None)
if isbn:
ans.append((isbn, 'isbn', isbn,
'http://www.worldcat.org/isbn/'+isbn))
doi = identifiers.get('doi', None)
if doi:
ans.append(('DOI', 'doi', doi,
'http://dx.doi.org/'+doi))
arxiv = identifiers.get('arxiv', None)
if arxiv:
ans.append(('arXiv', 'arxiv', arxiv,
'http://arxiv.org/abs/'+arxiv))
oclc = identifiers.get('oclc', None)
if oclc:
ans.append(('OCLC', 'oclc', oclc,
'http://www.worldcat.org/oclc/'+oclc))
issn = check_issn(identifiers.get('issn', None))
if issn:
ans.append((issn, 'issn', issn,
'http://www.worldcat.org/issn/'+issn))
for k, url in identifiers.iteritems():
if url and re.match(r'ur[il]\d*$', k) is not None and url.partition(':')[0].lower() in {'http', 'file', 'https'}:
url = url[:8].replace('|', ':') + url[8:].replace('|', ',')
parts = urlparse(url)
name = parts.netloc or parts.path
ans.append((name, k, url, url))
return ans
def test_identify_plugin(
name,
tests,
modify_plugin=lambda plugin: None, # {{{
fail_missing_meta=True):
'''
:param name: Plugin name
:param tests: List of 2-tuples. Each two tuple is of the form (args,
test_funcs). args is a dict of keyword arguments to pass to
the identify method. test_funcs are callables that accept a
Metadata object and return True iff the object passes the
test.
'''
plugin = None
for x in all_metadata_plugins():
if x.name == name and 'identify' in x.capabilities:
plugin = x
break
modify_plugin(plugin)
prints('Testing the identify function of', plugin.name)
prints('Using extra headers:', plugin.browser.addheaders)
tdir, lf, log, abort = init_test(plugin.name)
prints('Log saved to', lf)
times = []
for kwargs, test_funcs in tests:
log('')
log('#' * 80)
log('### Running test with:', kwargs)
log('#' * 80)
prints('Running test with:', kwargs)
rq = Queue()
args = (log, rq, abort)
start_time = time.time()
plugin.running_a_test = True
try:
err = plugin.identify(*args, **kwargs)
finally:
plugin.running_a_test = False
total_time = time.time() - start_time
times.append(total_time)
if err is not None:
prints('identify returned an error for args', args)
prints(err)
break
results = []
while True:
try:
results.append(rq.get_nowait())
except Empty:
break
prints('Found', len(results), 'matches:', end=' ')
prints('Smaller relevance means better match')
results.sort(key=plugin.identify_results_keygen(
title=kwargs.get('title', None),
authors=kwargs.get('authors', None),
identifiers=kwargs.get('identifiers', {})))
for i, mi in enumerate(results):
prints('*' * 30, 'Relevance:', i, '*' * 30)
if mi.rating:
mi.rating *= 2
prints(mi)
prints('\nCached cover URL :',
plugin.get_cached_cover_url(mi.identifiers))
prints('*' * 75, '\n\n')
possibles = []
for mi in results:
test_failed = False
for tfunc in test_funcs:
if not tfunc(mi):
test_failed = True
break
if not test_failed:
possibles.append(mi)
if not possibles:
prints('ERROR: No results that passed all tests were found')
prints('Log saved to', lf)
log.close()
dump_log(lf)
raise SystemExit(1)
good = [x for x in possibles if plugin.test_fields(x) is None]
if not good:
prints('Failed to find', plugin.test_fields(possibles[0]))
if fail_missing_meta:
raise SystemExit(1)
if results[0] is not possibles[0]:
prints('Most relevant result failed the tests')
raise SystemExit(1)
if 'cover' in plugin.capabilities:
rq = Queue()
mi = results[0]
plugin.download_cover(log,
rq,
abort,
title=mi.title,
authors=mi.authors,
identifiers=mi.identifiers)
results = []
while True:
try:
results.append(rq.get_nowait())
except Empty:
break
if not results and fail_missing_meta:
prints('Cover download failed')
raise SystemExit(1)
elif results:
cdata = results[0]
cover = os.path.join(
tdir,
plugin.name.replace(' ', '') + '-%s-cover.jpg' %
sanitize_file_name(mi.title.replace(' ', '_')))
with open(cover, 'wb') as f:
f.write(cdata[-1])
prints('Cover downloaded to:', cover)
if len(cdata[-1]) < 10240:
prints('Downloaded cover too small')
raise SystemExit(1)
prints('Average time per query', sum(times) / len(times))
if os.stat(lf).st_size > 10:
prints('There were some errors/warnings, see log', lf)
def test_identify_plugin(name, tests, modify_plugin=lambda plugin:None,
fail_missing_meta=True): # {{{
'''
:param name: Plugin name
:param tests: List of 2-tuples. Each two tuple is of the form (args,
test_funcs). args is a dict of keyword arguments to pass to
the identify method. test_funcs are callables that accept a
Metadata object and return True iff the object passes the
test.
'''
plugin = None
for x in all_metadata_plugins():
if x.name == name and 'identify' in x.capabilities:
plugin = x
break
modify_plugin(plugin)
prints('Testing the identify function of', plugin.name)
prints('Using extra headers:', plugin.browser.addheaders)
tdir, lf, log, abort = init_test(plugin.name)
prints('Log saved to', lf)
times = []
for kwargs, test_funcs in tests:
prints('Running test with:', kwargs)
rq = Queue()
args = (log, rq, abort)
start_time = time.time()
plugin.running_a_test = True
try:
err = plugin.identify(*args, **kwargs)
finally:
plugin.running_a_test = False
total_time = time.time() - start_time
times.append(total_time)
if err is not None:
prints('identify returned an error for args', args)
prints(err)
break
results = []
while True:
try:
results.append(rq.get_nowait())
except Empty:
break
prints('Found', len(results), 'matches:', end=' ')
prints('Smaller relevance means better match')
results.sort(key=plugin.identify_results_keygen(
title=kwargs.get('title', None), authors=kwargs.get('authors',
None), identifiers=kwargs.get('identifiers', {})))
for i, mi in enumerate(results):
prints('*'*30, 'Relevance:', i, '*'*30)
prints(mi)
prints('\nCached cover URL :',
plugin.get_cached_cover_url(mi.identifiers))
prints('*'*75, '\n\n')
possibles = []
for mi in results:
test_failed = False
for tfunc in test_funcs:
if not tfunc(mi):
test_failed = True
break
if not test_failed:
possibles.append(mi)
if not possibles:
prints('ERROR: No results that passed all tests were found')
prints('Log saved to', lf)
raise SystemExit(1)
good = [x for x in possibles if plugin.test_fields(x) is
None]
if not good:
prints('Failed to find', plugin.test_fields(possibles[0]))
if fail_missing_meta:
raise SystemExit(1)
if results[0] is not possibles[0]:
prints('Most relevant result failed the tests')
raise SystemExit(1)
if 'cover' in plugin.capabilities:
rq = Queue()
mi = results[0]
plugin.download_cover(log, rq, abort, title=mi.title,
authors=mi.authors, identifiers=mi.identifiers)
results = []
while True:
try:
results.append(rq.get_nowait())
except Empty:
break
if not results and fail_missing_meta:
prints('Cover download failed')
raise SystemExit(1)
elif results:
cdata = results[0]
cover = os.path.join(tdir, plugin.name.replace(' ',
'')+'-%s-cover.jpg'%sanitize_file_name2(mi.title.replace(' ',
'_')))
with open(cover, 'wb') as f:
f.write(cdata[-1])
prints('Cover downloaded to:', cover)
if len(cdata[-1]) < 10240:
prints('Downloaded cover too small')
raise SystemExit(1)
prints('Average time per query', sum(times)/len(times))
if os.stat(lf).st_size > 10:
prints('There were some errors/warnings, see log', lf)
def urls_from_identifiers(identifiers, sort_results=False): # {{{
identifiers = {k.lower(): v for k, v in iteritems(identifiers)}
ans = []
keys_left = set(identifiers)
def add(name, k, val, url):
ans.append((name, k, val, url))
keys_left.discard(k)
rules = msprefs['id_link_rules']
if rules:
formatter = EvalFormatter()
for k, val in iteritems(identifiers):
val = val.replace('|', ',')
vals = {
'id':
unicode_type(
quote(val if isinstance(val, bytes) else val.encode('utf-8'
))),
'id_unquoted':
str(val),
}
items = rules.get(k) or ()
for name, template in items:
try:
url = formatter.safe_format(template, vals, '', vals)
except Exception:
import traceback
traceback.format_exc()
continue
add(name, k, val, url)
for plugin in all_metadata_plugins():
try:
for id_type, id_val, url in plugin.get_book_urls(identifiers):
add(plugin.get_book_url_name(id_type, id_val, url), id_type,
id_val, url)
except Exception:
pass
isbn = identifiers.get('isbn', None)
if isbn:
add(isbn, 'isbn', isbn, 'https://www.worldcat.org/isbn/' + isbn)
doi = identifiers.get('doi', None)
if doi:
add('DOI', 'doi', doi, 'https://dx.doi.org/' + doi)
arxiv = identifiers.get('arxiv', None)
if arxiv:
add('arXiv', 'arxiv', arxiv, 'https://arxiv.org/abs/' + arxiv)
oclc = identifiers.get('oclc', None)
if oclc:
add('OCLC', 'oclc', oclc, 'https://www.worldcat.org/oclc/' + oclc)
issn = check_issn(identifiers.get('issn', None))
if issn:
add(issn, 'issn', issn, 'https://www.worldcat.org/issn/' + issn)
q = {'http', 'https', 'file'}
for k, url in iteritems(identifiers):
if url and re.match(r'ur[il]\d*$', k) is not None:
url = url[:8].replace('|', ':') + url[8:].replace('|', ',')
if url.partition(':')[0].lower() in q:
parts = urlparse(url)
name = parts.netloc or parts.path
add(name, k, url, url)
for k in tuple(keys_left):
val = identifiers.get(k)
if val:
url = val[:8].replace('|', ':') + val[8:].replace('|', ',')
if url.partition(':')[0].lower() in q:
parts = urlparse(url)
name = parts.netloc or parts.path
add(name, k, url, url)
if sort_results:
def url_key(x):
return primary_sort_key(str(x[0]))
ans = sorted(ans, key=url_key)
return ans