Skip to content

Commit

Permalink
disabling wos functionality due to bugs
Browse files Browse the repository at this point in the history
  • Loading branch information
@J-A-Ha
J-A-Ha committed Aug 7, 2024
1 parent a1993b6 commit ddf83bd
Show file tree
Hide file tree
Showing 4 changed files with 122 additions and 122 deletions.
2 changes: 1 addition & 1 deletion art/__init__.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -32,7 +32,7 @@

from .importers.crossref import lookup_doi, lookup_dois, lookup_journal, lookup_journals, search_journals, get_journal_entries, search_journal_entries, lookup_funder, lookup_funders, search_funders, get_funder_works, search_funder_works
from .importers.crossref import search_works as search_crossref
from .importers.wos import search as search_wos
# from .importers.wos import search as search_wos
from .importers.scopus import search as search_scopus, lookup as lookup_scopus
from .importers.orcid import lookup_orcid, search as search_orcid
from .importers.search import search as api_search
Expand Down
174 changes: 87 additions & 87 deletions art/classes/review.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -6,7 +6,7 @@
from ..importers.crossref import search_works, lookup_doi, lookup_dois, lookup_journal, lookup_journals, search_journals, get_journal_entries, search_journal_entries, lookup_funder, lookup_funders, search_funders, get_funder_works, search_funder_works
from ..importers.crossref import query_builder as crossref_query_builder
from ..importers.scopus import query_builder as scopus_query_builder, search as search_scopus, lookup as lookup_scopus
from ..importers.wos import search as search_wos, query_builder as wos_query_builder
# from ..importers.wos import search as search_wos, query_builder as wos_query_builder
from ..importers.search import search as api_search

from ..internet.scrapers import scrape_article, scrape_doi, scrape_google_scholar, scrape_google_scholar_search
Expand Down Expand Up @@ -1778,92 +1778,92 @@ def search_scopus(self,

return df

def search_wos(self,
all_fields = None,
title = None,
year = None,
author = None,
author_identifier = None,
affiliation = None,
doctype = None,
doi = None,
issn = None,
isbn = None,
pubmed_id = None,
source_title = None,
volume = None,
page = None,
issue = None,
topics = None,
default_operator = 'AND',
database: str = 'WOK',
limit: int = 10,
page_limit: int = 1,
sort_field: str = 'RS+D',
modified_time_span = None,
tc_modified_time_span = None,
detail = None,
add_to_results = False,
drop_duplicates = False,
drop_empty_rows = False
):

df = search_wos(
all_fields = all_fields,
title = title,
year = year,
author = author,
author_identifier = author_identifier,
affiliation = affiliation,
doctype = doctype,
doi = doi,
issn = issn,
isbn = isbn,
pubmed_id = pubmed_id,
source_title = source_title,
volume = volume,
page = page,
issue = issue,
topics = topics,
default_operator = default_operator,
database = database,
limit = limit,
page_limit = page_limit,
sort_field = sort_field,
modified_time_span = modified_time_span,
tc_modified_time_span = tc_modified_time_span,
detail = detail
)

for c in df.columns:
if c not in self.results.columns:
df = df.drop(c, axis=1)

if add_to_results == True:
# def search_wos(self,
# all_fields = None,
# title = None,
# year = None,
# author = None,
# author_identifier = None,
# affiliation = None,
# doctype = None,
# doi = None,
# issn = None,
# isbn = None,
# pubmed_id = None,
# source_title = None,
# volume = None,
# page = None,
# issue = None,
# topics = None,
# default_operator = 'AND',
# database: str = 'WOK',
# limit: int = 10,
# page_limit: int = 1,
# sort_field: str = 'RS+D',
# modified_time_span = None,
# tc_modified_time_span = None,
# detail = None,
# add_to_results = False,
# drop_duplicates = False,
# drop_empty_rows = False
# ):

# df = search_wos(
# all_fields = all_fields,
# title = title,
# year = year,
# author = author,
# author_identifier = author_identifier,
# affiliation = affiliation,
# doctype = doctype,
# doi = doi,
# issn = issn,
# isbn = isbn,
# pubmed_id = pubmed_id,
# source_title = source_title,
# volume = volume,
# page = page,
# issue = issue,
# topics = topics,
# default_operator = default_operator,
# database = database,
# limit = limit,
# page_limit = page_limit,
# sort_field = sort_field,
# modified_time_span = modified_time_span,
# tc_modified_time_span = tc_modified_time_span,
# detail = detail
# )

# for c in df.columns:
# if c not in self.results.columns:
# df = df.drop(c, axis=1)

# if add_to_results == True:

query = wos_query_builder(all_fields = all_fields,
title = title,
year = year,
author = author,
author_identifier = author_identifier,
affiliation = affiliation,
doctype = doctype,
doi = doi,
issn = issn,
isbn = isbn,
pubmed_id = pubmed_id,
source_title = source_title,
volume = volume,
page = page,
issue = issue,
topics = topics,
default_operator = default_operator)

self.activity_log.add_activity(type='API search', activity='searched World of Science and added to results', location=['results'], database=database, query=query)
self.results.add_dataframe(dataframe=df, drop_duplicates=drop_duplicates, drop_empty_rows=drop_empty_rows) # type: ignore


return df
# query = wos_query_builder(all_fields = all_fields,
# title = title,
# year = year,
# author = author,
# author_identifier = author_identifier,
# affiliation = affiliation,
# doctype = doctype,
# doi = doi,
# issn = issn,
# isbn = isbn,
# pubmed_id = pubmed_id,
# source_title = source_title,
# volume = volume,
# page = page,
# issue = issue,
# topics = topics,
# default_operator = default_operator)

# self.activity_log.add_activity(type='API search', activity='searched World of Science and added to results', location=['results'], database=database, query=query)
# self.results.add_dataframe(dataframe=df, drop_duplicates=drop_duplicates, drop_empty_rows=drop_empty_rows) # type: ignore


# return df

def lookup_doi(self, doi = 'request_input', timeout = 60):
return lookup_doi(doi=doi, timeout=timeout)
Expand Down Expand Up @@ -2221,7 +2221,7 @@ def api_search(self,
timeout = 60,
crossref = True,
scopus = True,
wos = True,
wos = False,
add_to_results = False):

df = api_search(default_query = default_query,
Expand Down
4 changes: 2 additions & 2 deletions art/datasets/stopwords/stopwords.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -4,11 +4,11 @@

# Importing Stopwords corpus as an NLTK text
try:
from nltk.corpus import stopwords as nltk_stopwords
from nltk.corpus import stopwords as nltk_stopwords # type: ignore
nltk_stopwords.words()
except:
download('stopwords')
from nltk.corpus import stopwords as nltk_stopwords
from nltk.corpus import stopwords as nltk_stopwords # type: ignore

nltk_stopwords = list(nltk_stopwords.words())

Expand Down
64 changes: 32 additions & 32 deletions art/importers/search.py
View file
Original file line number Diff line number Diff line change
@@ -1,5 +1,5 @@
from .scopus import search as search_scopus
from .wos import search as search_wos
# from .wos import search as search_wos
from .crossref import search_works as search_crossref
from .orcid import search as search_orcid

Expand Down Expand Up @@ -107,41 +107,41 @@ def search(default_query = None,
print(f'Encountered Scopus search error: {e}')
pass

if wos == True:
# if wos == True:

if (all_fields is None) and (default_query is not None):
all_fields_updated = default_query
else:
all_fields_updated = all_fields
# if (all_fields is None) and (default_query is not None):
# all_fields_updated = default_query
# else:
# all_fields_updated = all_fields

try:
wos_result = search_wos(
all_fields = all_fields_updated,
title = title,
year = year,
author = author,
author_identifier = author_identifier,
affiliation = affiliation,
doctype = entry_type,
doi = doi,
issn = issn,
isbn = isbn,
pubmed_id = pubmed_id,
source_title = source_title,
volume = volume,
page = page,
issue = issue,
topics = topics,
default_operator = default_operator,
limit = limit_per_api)
# try:
# wos_result = search_wos(
# all_fields = all_fields_updated,
# title = title,
# year = year,
# author = author,
# author_identifier = author_identifier,
# affiliation = affiliation,
# doctype = entry_type,
# doi = doi,
# issn = issn,
# isbn = isbn,
# pubmed_id = pubmed_id,
# source_title = source_title,
# volume = volume,
# page = page,
# issue = issue,
# topics = topics,
# default_operator = default_operator,
# limit = limit_per_api)

wos_result['repository'] = 'WOK'
# wos_result['repository'] = 'WOK'

df = pd.concat([df, wos_result])
df = df.reset_index().drop('index',axis=1)
except Exception as e:
print(f'Encountered Web of Science search error: {e}')
pass
# df = pd.concat([df, wos_result])
# df = df.reset_index().drop('index',axis=1)
# except Exception as e:
# print(f'Encountered Web of Science search error: {e}')
# pass

if orcid == True:

Expand Down

0 comments on commit ddf83bd

Please sign in to comment.