def query_service (self, index, value, results):
"""
A generalised query for ISBNdb.
:Parameters:
index : string
The index to search in ISBNdb.
value : string
The value to search for in the index..
results : iterable
A list of the data to include in the response.
:Returns:
The response received from the service.
This serves a general way of accessing all the methods available for
ISBNdb. It also normalises the ISBN to a suitable form for submission.
Note that it is probably possible to form a bad query with the wrong
combination of parameters.
"""
## Preconditions & preparation:
if (index == 'isbn'):
value = utils.normalize_isbn (value)
## Main:
sub_url = 'index1=%(indx)s&value1=%(val)s' % {
'indx': index,
'val': value,
}
if (results):
res_str = ','.join (list(results))
sub_url += '&results=' + res_str
return self.request (sub_url)
def query_service (self, isbn, method, format, fields=['*']):
"""
A generalised query for xISBN.
:Parameters:
isbn : string
A normalised ISBN-10 or -13.
method : string
The request type to make of xISBN.
format : string
The form for the response.
fields : iterable
A list of the fields to include in the response.
:Returns:
The response received from the service.
This serves a general way of accessing all the methods available for
xISBN. It also normalises the ISBn to a suitable form for submission.
"""
## Preconditions & preparation:
assert (format in FORMATS), \
"unrecognised format '%s', must be one of %s" % (format, FORMATS)
## Main:
sub_url = "%(isbn)s?method=%(mthd)s&format=%(fmt)s&fl=%(flds)s" % {
'mthd': method,
'fmt': format,
'isbn': utils.normalize_isbn (isbn),
'flds': ','.join (fields),
}
return self.request (sub_url)
def info(epub):
data = {}
try:
z = zipfile.ZipFile(epub)
except zipfile.BadZipFile:
logger.debug('invalid epub file %s', epub)
return data
opf = [f.filename for f in z.filelist if f.filename.endswith('opf')]
if opf:
info = ET.fromstring(z.read(opf[0]))
metadata = info.findall('{http://www.idpf.org/2007/opf}metadata')
if metadata:
metadata = metadata[0]
for e in metadata.getchildren():
if e.text and e.text.strip() and e.text not in ('unknown', 'none'):
key = e.tag.split('}')[-1]
key = {
'creator': 'author',
}.get(key, key)
value = e.text.strip()
if key == 'identifier':
value = normalize_isbn(value)
if stdnum.isbn.is_valid(value):
data['isbn'] = [value]
elif key == 'author':
data[key] = value.split(', ')
else:
data[key] = value
if 'description' in data:
data['description'] = strip_tags(decode_html(data['description']))
text = extract_text(epub)
data['textsize'] = len(text)
if not 'isbn' in data:
isbn = extract_isbn(text)
if isbn:
data['isbn'] = [isbn]
if 'date' in data and 'T' in data['date']:
data['date'] = data['date'].split('T')[0]
if 'language' in data and isinstance(data['language'], str):
data['language'] = get_language(data['language'])
return data
def getMetadata(data):
'''
takes {
key: value
includeEdits: boolean
}
key can be one of the supported identifiers: isbn, oclc, olid,...
'''
logger.debug('getMetadata %s', data)
if 'includeEdits' in data:
include_edits = data.pop('includeEdits')
else:
include_edits = False
key, value = next(iter(data.items()))
if key == 'isbn':
value = utils.normalize_isbn(value)
logger.debug('getMetadata key=%s value=%s', key, value)
response = meta.lookup(key, value)
if response:
response['primaryid'] = [key, value]
return response
def getMetadata(data):
'''
takes {
key: value
includeEdits: boolean
}
key can be one of the supported identifiers: isbn, oclc, olid,...
'''
logger.debug('getMetadata %s', data)
if 'includeEdits' in data:
include_edits = data.pop('includeEdits')
else:
include_edits = False
key, value = next(iter(data.items()))
if key == 'isbn':
value = utils.normalize_isbn(value)
logger.debug('getMetadata key=%s value=%s', key, value)
response = meta.lookup(key, value)
if response:
response['primaryid'] = [key, value]
return response
def info(opf):
data = {}
try:
with open(opf, 'rb') as fd:
opf = ET.fromstring(fd.read().decode())
except:
logger.debug('failed to load opf %s', opf, exc_info=1)
return data
ns = '{http://www.idpf.org/2007/opf}'
metadata = opf.findall(ns + 'metadata')[0]
for e in metadata.getchildren():
if e.text:
key = e.tag.split('}')[-1]
key = {
'creator': 'author',
}.get(key, key)
value = e.text
if key == 'identifier':
isbn = normalize_isbn(value)
if stdnum.isbn.is_valid(isbn):
if not 'isbn' in data:
data['isbn'] = [isbn]
else:
data['isbn'].append(isbn)
if e.attrib.get(ns + 'scheme') == 'AMAZON':
if not 'asin' in data:
data['asin'] = [value]
else:
data['asin'].append(value)
else:
data[key] = strip_tags(e.text)
#YYY-MM-DD
if 'date' in data and len(data['date']) > 10:
data['date'] =data['date'][:10]
if 'language' in data:
data['language'] = get_language(data['language'])
return data
def info(opf):
data = {}
try:
with open(opf, 'rb') as fd:
opf = ET.fromstring(fd.read().decode())
except:
logger.debug('failed to load opf %s', opf, exc_info=1)
return data
ns = '{http://www.idpf.org/2007/opf}'
metadata = opf.findall(ns + 'metadata')[0]
for e in metadata.getchildren():
if e.text:
key = e.tag.split('}')[-1]
key = {
'creator': 'author',
}.get(key, key)
value = e.text
if key == 'identifier':
isbn = normalize_isbn(value)
if stdnum.isbn.is_valid(isbn):
if not 'isbn' in data:
data['isbn'] = [isbn]
else:
data['isbn'].append(isbn)
if e.attrib.get(ns + 'scheme') == 'AMAZON':
if not 'asin' in data:
data['asin'] = [value]
else:
data['asin'].append(value)
else:
data[key] = strip_tags(e.text)
#YYY-MM-DD
if 'date' in data and len(data['date']) > 10:
data['date'] = data['date'][:10]
if 'language' in data:
data['language'] = get_language(data['language'])
return data
def info(pdf):
data = {}
with open(pdf, 'rb') as fd:
try:
pdfreader = PdfFileReader(fd)
data['pages'] = pdfreader.numPages
if pdfreader.getIsEncrypted():
pdfreader.decrypt('')
info = pdfreader.getDocumentInfo()
if info:
for key in info:
if info[key]:
try:
value = info[key]
if len(value) == 1:
value = value[0]
if isinstance(value, bytes):
value = value.decode('utf-16')
data[key[1:].lower()] = value
except:
pass
xmp = pdfreader.getXmpMetadata()
if xmp:
for key in dir(xmp):
if key.startswith('dc_'):
value = getattr(xmp, key)
if isinstance(value, dict) and 'x-default' in value:
value = value['x-default']
elif isinstance(value, list):
value = [
v.strip() if isinstance(v, str) else v
for v in value if v
]
value = [
v.strftime('%Y-%m-%d') if isinstance(
v, datetime) else v for v in value
]
if len(value) == 1:
value = value[0]
_key = key[3:]
if value and _key not in data:
data[_key] = value
except:
logger.debug('FAILED TO PARSE %s', pdf, exc_info=1)
'''
cmd = ['pdfinfo', pdf]
p = subprocess.Popen(cmd, stdout=subprocess.PIPE, stderr=subprocess.PIPE, close_fds=True)
stdout, stderr = p.communicate()
for line in stdout.strip().split('\n'):
parts = line.split(':')
key = parts[0].lower().strip()
if key:
data[key] = ':'.join(parts[1:]).strip()
for key in data.keys():
if not data[key]:
del data[key]
'''
if 'identifier' in data:
value = normalize_isbn(data['identifier'])
if stdnum.isbn.is_valid(value):
data['isbn'] = [value]
del data['identifier']
for key, value in data.items():
if isinstance(value, dict):
value = ' '.join(list(value.values()))
data[key] = value.strip()
for key in list(data):
if data[key] in ('Unknown', ):
del data[key]
if key == 'language':
data[key] = get_language(data[key])
text = extract_text(pdf)
data['textsize'] = len(text)
if settings.server['extract_text']:
if not 'isbn' in data:
isbn = extract_isbn(text)
if isbn:
data['isbn'] = [isbn]
if 'isbn' in data and isinstance(data['isbn'], str):
data['isbn'] = [data['isbn']]
if 'date' in data and len(data['date']) == 8 and data['date'].isdigit():
d = data['date']
data['date'] = '%s-%s-%s' % (d[:4], d[4:6], d[6:])
if 'author' in data and isinstance(data['author'], str):
data['author'] = data['author'].split(', ')
return data
def info(pdf):
data = {}
with open(pdf, 'rb') as fd:
try:
pdfreader = PdfFileReader(fd)
data['pages'] = pdfreader.numPages
if pdfreader.getIsEncrypted():
pdfreader.decrypt('')
info = pdfreader.getDocumentInfo()
if info:
for key in info:
if info[key]:
try:
value = info[key]
if len(value) == 1:
value = value[0]
if isinstance(value, bytes):
value = value.decode('utf-16')
data[key[1:].lower()] = value
except:
pass
xmp = pdfreader.getXmpMetadata()
if xmp:
for key in dir(xmp):
if key.startswith('dc_'):
value = getattr(xmp, key)
if isinstance(value, dict) and 'x-default' in value:
value = value['x-default']
elif isinstance(value, list):
value = [v.strip() if isinstance(v, str) else v for v in value if v]
value = [v.strftime('%Y-%m-%d') if isinstance(v, datetime) else v for v in value]
if len(value) == 1:
value = value[0]
_key = key[3:]
if value and _key not in data:
data[_key] = value
except:
logger.debug('FAILED TO PARSE %s', pdf, exc_info=1)
'''
cmd = ['pdfinfo', pdf]
p = subprocess.Popen(cmd, stdout=subprocess.PIPE, stderr=subprocess.PIPE, close_fds=True)
stdout, stderr = p.communicate()
for line in stdout.strip().split('\n'):
parts = line.split(':')
key = parts[0].lower().strip()
if key:
data[key] = ':'.join(parts[1:]).strip()
for key in data.keys():
if not data[key]:
del data[key]
'''
if 'identifier' in data:
value = normalize_isbn(data['identifier'])
if stdnum.isbn.is_valid(value):
data['isbn'] = [value]
del data['identifier']
for key, value in data.items():
if isinstance(value, dict):
value = ' '.join(list(value.values()))
data[key] = value.strip()
for key in list(data):
if data[key] in ('Unknown',):
del data[key]
if key == 'language':
data[key] = get_language(data[key])
text = extract_text(pdf)
data['textsize'] = len(text)
if settings.server['extract_text']:
if not 'isbn' in data:
isbn = extract_isbn(text)
if isbn:
data['isbn'] = [isbn]
if 'isbn' in data and isinstance(data['isbn'], str):
data['isbn'] = [data['isbn']]
if 'date' in data and len(data['date']) == 8 and data['date'].isdigit():
d = data['date']
data['date'] = '%s-%s-%s' % (d[:4], d[4:6], d[6:])
if 'author' in data and isinstance(data['author'], str):
data['author'] = data['author'].split(', ')
return data
