def googlebooks_scr(parsed_url, date_format='%Y-%m-%d') -> tuple:
"""Create the response namedtuple."""
parsed_query = parse_qs(parsed_url.query)
id_ = parsed_query.get('id')
if id_ is not None:
volume_id = id_[0]
else: # the new URL format
volume_id = parsed_url.path.rpartition('/')[2]
dictionary = ris_parse(
request(
f'https://{parsed_url.netloc}/books/download/?id={volume_id}'
f'&output=ris',
spoof=True).content.decode('utf8'))
dictionary['date_format'] = date_format
# manually adding page number to dictionary:
pg = parsed_query.get('pg')
if pg is not None:
pg0 = pg[0]
dictionary['page'] = pg0[2:]
dictionary['url'] += f'&pg={pg0}'
# although google does not provide a language field:
if not dictionary['language']:
dictionary['language'] = classify(dictionary['title'])[0]
return dict_to_sfn_cit_ref(dictionary)
def ris_fetcher_thread(url, ris_collection):
"""Fill the ris_dict. This function is called in a thread."""
ris_dict = ris_parse(get_ris(url))
language = ris_dict.get('language')
if language:
ris_collection['language'] = language
authors = ris_dict.get('authors')
if authors:
ris_collection['authors'] = authors
def ris_fetcher_thread(url, ris_collection):
"""Fill the ris_dict. This function is called in a thread."""
ris_dict = ris_parse(get_ris(url))
language = ris_dict.get('language')
if language:
ris_collection['language'] = language
authors = ris_dict.get('authors')
if authors:
ris_collection['authors'] = authors
def oclc_scr(oclc: str, date_format: str = '%Y-%m-%d') -> tuple:
text = request('https://www.worldcat.org/oclc/' + oclc + '?page=endnote'
'&client=worldcat.org-detailed_record').content.decode()
if '<html' in text: # invalid OCLC number
return ('Error processing OCLC number: ' + oclc,
'Perhaps you entered an invalid OCLC number?', '')
d = ris_parse(text)
authors = d['authors']
if authors:
# worldcat has a '.' the end of the first name
d['authors'] = [(
fn.rstrip('.') if not fn.isupper() else fn,
ln.rstrip('.') if not ln.isupper() else ln,
) for fn, ln in authors]
d['date_format'] = date_format
d['oclc'] = oclc
d['title'] = d['title'].rstrip('.')
return dict_to_sfn_cit_ref(d)
def googlebooks_sfn_cit_ref(url, date_format='%Y-%m-%d') -> tuple:
"""Create the response namedtuple."""
# bibtex_result = get_bibtex(url) [1]
# dictionary = bibtex.parse(bibtex_result) [1]
dictionary = ris_parse(get_ris(url))
dictionary['date_format'] = date_format
pu = urlparse(url)
pq = parse_qs(pu.query)
# default domain is prefered:
dictionary['url'] = 'https://' + pu.netloc + '/books?id=' + pq['id'][0]
# manually adding page number to dictionary:
if 'pg' in pq:
dictionary['page'] = pq['pg'][0][2:]
dictionary['url'] += '&pg=' + pq['pg'][0]
# although google does not provide a language field:
if not dictionary['language']:
dictionary['language'] = classify(dictionary['title'])[0]
return dict_to_sfn_cit_ref(dictionary)
def oclc_sfn_cit_ref(oclc: str, date_format: str = '%Y-%m-%d') -> tuple:
text = request(
'https://www.worldcat.org/oclc/' + oclc + '?page=endnote'
'&client=worldcat.org-detailed_record').text
if '<html' in text: # invalid OCLC number
return (
'Error processing OCLC number: ' + oclc,
'Perhaps you entered an invalid OCLC number?',
'')
d = ris_parse(text)
authors = d['authors']
if authors:
# worldcat has a '.' the end of the first name
d['authors'] = [(
fn.rstrip('.') if not fn.isupper() else fn,
ln.rstrip('.') if not ln.isupper() else ln,
) for fn, ln in authors]
d['date_format'] = date_format
d['oclc'] = oclc
d['title'] = d['title'].rstrip('.')
return dict_to_sfn_cit_ref(d)