def _get_pdf(k, title):
# Skip if exists
if os.path.isdir(out_dir(k)) and os.listdir(out_dir(k)):
return os.path.join(out_dir(k), os.listdir(out_dir(k))[0])
# Normalize title
google_search = scholarly.search_pubs(title)
google_result = next(google_search)
print(title)
title = google_result['bib']['title'] + ' ' + (' '.join(
google_result['bib']['author']))
print(title)
# Get DOI
try:
found, bib_string = get_bib_from_title(title)
except Exception as e:
print("Error while getting DOI", e)
return None
# Download
if found:
bib = bibtexparser.loads(bib_string).entries
if bib and ("doi" in bib[0]) and (bib[0]['ENTRYTYPE'] == 'article'):
doi = bib[0]["doi"]
try:
SciHub(doi, out_dir(k)).download(choose_scihub_url_index=3)
except Exception as e:
print("Error while downloading", e)
return None
pdf = os.path.join(out_dir(k),
os.listdir(out_dir(k))[0]) if os.listdir(
out_dir(k)) else None
return pdf
else:
print(bib)
print("\tAbsent DOI")
return None
def update_bib(bib, get_first=True):
bib_id = bib["ID"]
if "doi" not in bib and "title" in bib:
found, bib_string = get_bib_from_title(bib["title"], get_first)
if found:
bib = bibtexparser.loads(bib_string).entries[0]
bib["ID"] = bib_id
return bib
def download_from_title(title, location="", use_libgen=False):
found, bib_string = get_bib_from_title(title)
if found:
bib = bibtexparser.loads(bib_string).entries[0]
if "doi" in bib:
pdf_name = "{}.pdf".format(bib["doi"].replace("/", "_"))
bib["pdf_file"] = location + pdf_name
if use_libgen:
download_from_libgen(bib["doi"], bib["pdf_file"])
else:
found, bib = download_from_scihub(bib["doi"], bib["pdf_file"])
else:
print("\tAbsent DOI")
def search(self, get_first=False):
"""
get doi from crossref
"""
new_paper = {}
found, bib_string = get_bib_from_title(self.title, get_first=get_first)
# print((bib_string))
if found:
try:
if bibtexparser.loads(bib_string).entries:
bib = bibtexparser.loads(bib_string).entries[0]
# return bib
new_paper['title'] = bib['title']
self.title = bib['title']
new_paper['doi'] = bib['doi']
self.doi = bib['doi']
else:
self.doi = re.search(r'doi = {(.*?)}', bib_string,
re.S).group(1)
# self.title = re.search(r'title = {(.*?)}',bib_string,re.S).group(1)
except:
raise IndexError("no doi find")