#78 is for elsevier
records = downloader.get_dict_from_search(
'ascorbic acid+extraction+fruit&filter=member:78', 3000)
for i, record in enumerate(records):
print(i)
cur_title = re.sub('[\[\]\'\.\/]', '', str(record['title']))
replaced_doi = re.sub('[\[\]\'\.\/()]', '', str(record['doi']))
print(replaced_doi)
cur_filename = './elsevier/' + replaced_doi + '.' + filetype
try:
my_file = open(cur_filename, 'wb') # Need to use 'wb' on Windows
except Exception as e:
print(str(e))
#my_html_file = open('./crossref/'+str(i)+'.html', 'wb')
ret = downloader.get_xml_from_doi(record['doi'], my_file, 'elsevier')
#downloader.get_html_from_doi(doi, my_html_file, 'elsevier')
my_file.close()
if ret != True:
continue
if filetype == 'xml':
rawtext = findText(cur_filename)
print(rawtext)
if rawtext == '':
rawtext = 'empty'
body = {
'doi': replaced_doi,
'text': rawtext,
'url': str(record['url']),
