Fixes!

conjurer_librarian/conjurer_librarian.py

@@ -9,9 +9,6 @@ from json.decoder import JSONDecodeError
 from platform import uname
 from sys import platform
 from urllib.request import urlopen
-import asyncio
-from queue import Queue
-from threading import Thread
 from habanero import Crossref
 from waitress import serve
 
@@ -76,29 +73,15 @@ class Librarian(object):
         #TODO: Później robimy tak że query jest najpierw sprawdzane w sql - i dawane jako "zapisana lokalna kopia"
         #TODO: Paginacja - najpierw hity z pliku, potem na końcu to co nie zwróciło żadnych hitów - i to dopiero można crawlerem sprawdzić
 
-    def check_dois_in_file(self, file_name, dois, out_queue):
-        with open(f'{DATABASE_PATH}{file_name}', "r+", encoding=ENCODING) as file:
-            while True:
-                # Get next line from file
-                line = file.readline()
-                if line == dois:
-                    return True
-                # if line is empty
-                # end of file is reached
-                if not line:
-                    return False
 
     def check_dois_in_local_db(self, dois):
-        _sentinel = object()
-        chunk_list = []
-        q = Queue()
+        #odwolanie do search_bota
 
-        for file in chunk_list:
-            t = Thread(target = self.check_dois_in_file, args = (file ,dois, q))
-            t.start()
-        q.put(_sentinel)
+        result = False
+        return result
 
-    def check_if_exists(self, page_url):
+
+    def check_if_exists_brute_force(self, page_url):
         if not page_url.startswith(("http:", "https:")):
             raise ValueError("URL must start with 'http:' or 'https:'")
         # trunk-ignore(bandit/B310)
@@ -107,23 +90,31 @@ class Librarian(object):
             text = data.decode("utf-8")
             for line in text.splitlines():
                 if re.match(r".*Unfortunately, Sci-Hub doesn't have the requested document.*", line):
-                    return None
+                    return True
                 if m := re.match(r".*<embed type=\"application.pdf\"\s*src=\"(.*\.pdf)",line):
-                    return "https:" + str(m.group(1))
-        return None
+                    direct_download_link = "https:" + str(m.group(1))
+                    print (direct_download_link)
+                    return True
+        return False
 
     def provide_sci_hub_link(self, page_url):
         if self.check_if_exists(page_url):
             return page_url
         return None
 
-    def refine_query(self, unrefined_reqult):
+    def check_if_exists(self, doi, brute_force = False):
+        self.check_dois_in_local_db(doi)
+        if brute_force:
+            item_link = "https://sci-hub.se/" + doi
+            self.check_if_exists_brute_force(item_link)
+        return False
+
+    def refine_query(self, unrefined_reqult, brute_force = False):
         print("Refine result")
         refined_result = []
         for item in unrefined_reqult["summary"]:
             if item["container"] == "NO" and item["title"]:
-                item_link = "https://sci-hub.se/" + str(item['DOI'])
-                if self.check_if_exists(item_link):
+                if self.check_if_exists(str(item["DOI"])):
                     refined_result.append(item)
                     print ("HIT")
                     print(item["title"])
@@ -150,6 +141,7 @@ class Librarian(object):
                 if item["UUID"] == uuid:
                     print (item["UUID"])
                     uuid_found = True
+                    #TODO: THREAD IT
                     return self.refine_query(item)
 
         if not uuid_found: