gitea/conjurer
1
0
Fork 0
mirror of https://github.com/migatu/conjurer.git synced 2026-07-19 08:12:09 +00:00
Code Issues Packages Projects Releases Wiki Activity

fx

Browse Source
This commit is contained in:
Migatu
2024-04-02 13:35:54 +02:00
parent 7ef10cf431
commit 61b929f148
1 changed files with 9 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files
conjurer_librarian/conjurer_librarian.py
+9 -9
View File
@@ -31,11 +31,10 @@ class Librarian(object):
netrc_mod = netrc.netrc(NETRC_FILE) netrc_mod = netrc.netrc(NETRC_FILE)
authTokens = netrc_mod.authenticators("crossref") authTokens = netrc_mod.authenticators("crossref")
self.cr = Crossref(mailto=authTokens[0]) self.cr = Crossref(mailto=authTokens[0])
self.last_search = ""
self.limit = 200 self.limit = 200
def search_crossref(self, query, uuid): def search_crossref(self, query, uuid):
self.last_search = self.cr.works(query = query, limit = self.limit) search_result_from_cr = self.cr.works(query = query, limit = self.limit)
#add to sql with UUID #add to sql with UUID
#sql row - title, doi, author, uuid, last retrieved, is_available #sql row - title, doi, author, uuid, last retrieved, is_available
with open("results.json", "r+", encoding="UTF-8") as data_file: with open("results.json", "r+", encoding="UTF-8") as data_file:
@@ -46,19 +45,20 @@ class Librarian(object):
file_data = [] file_data = []
# Join new_data with file_data inside emp_details # Join new_data with file_data inside emp_details
summarized_results = [] summarized_results = []
for item in self.last_search['message']['items']: for item in search_result_from_cr['message']['items']:
container = "NO" container = "NO"
if "container-title" in item: if "container-title" in item:
container = "YES" container = "YES"
print(item['title']) print(item['title'])
print(item['DOI']) print(item['DOI'])
summarized_results.append({"DOI" : item['DOI'], "title": item['title'], "type": item['type'], "container": container}) summarized_results.append({"DOI" : item['DOI'], "title": item['title'], "type": item['type'], "container": container})
result = {"UUID": uuid, "total_results": self.last_search['message']['total-results'], "on_page" : 1, "summary":summarized_results, "results":self.last_search['message']['items'], } result = {"UUID": uuid, "total_results": search_result_from_cr['message']['total-results'], "on_page" : 1, "summary":summarized_results, "results":search_result_from_cr['message']['items'], }
file_data.append(result) file_data.append(result)
print("Saving") print("Saving")
data_file.seek(0) data_file.seek(0)
# convert back to json. # convert back to json.
json.dump(file_data, data_file, indent=4) json.dump(file_data, data_file, indent=4)
return result
def check_if_exists(self,page_url): def check_if_exists(self,page_url):
@@ -117,11 +117,11 @@ class Librarian(object):
if item["UUID"] == uuid: if item["UUID"] == uuid:
print (item["UUID"]) print (item["UUID"])
uuid_found = True uuid_found = True
self.last_search = item self.refine_query(item)
if uuid_found:
return self.last_search if not uuid_found:
self.search_crossref(query=query, uuid=uuid) answer = self.search_crossref(query=query, uuid=uuid)
return self.refine_query(self.last_search) return self.refine_query(answer)
#example not exists #example not exists
#sample_non_existing_page_url = "https://sci-hub.se/10.4324/9781003006237" #sample_non_existing_page_url = "https://sci-hub.se/10.4324/9781003006237"