updated processing_test_doi_ueberarbeitet

verarbeitung/Processing_test_doi_ueberarbeitet.py

@@ -10,12 +10,13 @@ import requests as req
 import sys  
 from pathlib import Path
 from input_fj import input
+from json_demo import output_to_json
 
 
 
-def process_main(array, depth):
+def process_main(doi_input_array, depth):
     # ERROR-Handling doi_array = NULL
-    if (len(array) == 0):
+    if (len(doi_input_array) == 0):
         print("Error, no input data")
 
     # ERROR- wenn für die Tiefe eine negative Zahl eingegeben wird
@@ -30,14 +31,21 @@ def process_main(array, depth):
     edges = []
     
     # Jede Publikation aus dem Input-Array wird in den Knoten-Array(nodes) eingefügt.
-    for pub in array:
-        if (pub not in nodes):
+    for pub_doi in doi_input_array:
+        pub = input(pub_doi)
+        not_in_nodes = True
+        for node in nodes:
+            if (pub.doi_url == node.doi_url):
+                not_in_nodes = False
+                break
+        if (not_in_nodes):
             nodes.append(pub)
         else:
-            array.remove(pub)
+            doi_input_array.remove(pub_doi)
 
-    process_rec_depth(array, 0, depth)
+    process_rec_depth(doi_input_array, 0, depth)
 
+    output_to_json(nodes,edges)
     return(nodes,edges)
     
     
@@ -56,9 +64,14 @@ def process_rec_depth(array, depth, depth_max):
             # Wenn die citation noch nicht im Knoten-Array(nodes) existiert UND die maximale Tiefe 
             # noch nicht erreicht wurde, wird diese als Knoten im Knoten-Array gespeichert. Zusätzlich 
             # wird die Verbindung zur Publikation als Tupel im Kanten-Array(edges) gespeichert. 
-            if (citation.doi_url not in nodes):
+            not_in_nodes = True
+            for node in nodes:
+                if (citation.doi_url == node.doi_url):
+                    not_in_nodes = False
+                    break
+            if (not_in_nodes):
                 if (depth <= depth_max):
-                    nodes.append(citation.doi_url)
+                    nodes.append(citation)
                     edges.append([pub.doi_url,citation.doi_url])
 
             # Wenn die citaion bereits im Knoten-Array existiert, wird nur die Verbindung zur Publikation 
@@ -85,8 +98,8 @@ def process_rec_depth(array, depth, depth_max):
 # Programmtest, weil noch keine Verbindung zum Input besteht.
 arr = []
 arr.append('https://pubs.acs.org/doi/10.1021/acs.jcim.9b00249')
-#arr.append('https://pubs.acs.org/doi/10.1021/acs.jcim.9b00249')
-#arr.append('https://doi.org/10.1021/acs.jmedchem.0c01332')
+arr.append('https://pubs.acs.org/doi/10.1021/acs.jcim.9b00249')
+arr.append('https://doi.org/10.1021/acs.jmedchem.0c01332')
 #arr.append('https://doi.org/10.1021/acs.jcim.0c00741')
 
 #arr.append('https://doi.org/10.1021/ci700007b')
@@ -97,8 +110,8 @@ arr.append('https://pubs.acs.org/doi/10.1021/acs.jcim.9b00249')
 nodes,edges = process_main(arr,1)
 
 print("Knoten:\n")
-for vortex in nodes:
-    print(vortex, "\n")
+for node in nodes:
+    print(node.title, "\n")
 print("\nKanten:\n")
 for edge in edges:
     print(edge,"\n")
\ No newline at end of file

verarbeitung/json_demo.py

 #!/usr/bin/env python3
 import json
+from input_fj import input
 
 def output_to_json(V,E):
-  list_of_node_dicts = list()
-  list_of_edge_dicts = list()
-  dict_of_all = dict()
-  for node in V:
-    new_dict = dict()
-    new_dict["doi"] = node
-    list_of_node_dicts.append(new_dict)
-  for edge in E:
-    new_dict_2 = dict()
-    new_dict_2["source"] = edge[0]
-    new_dict_2["target"] = edge[1]
-    list_of_edge_dicts.append(new_dict_2)
-  dict_of_all["nodes"] = list_of_node_dicts
-  dict_of_all["links"] = list_of_edge_dicts
-  return(dict_of_all)
-  with open('json_text_json','w') as outfile:
-    json_dump(dict_of_all, outfile)
+    list_of_node_dicts = list()
+    list_of_edge_dicts = list()
+    dict_of_all = dict()
+    for node in V:
+        new_dict = dict()
+        new_dict["name"] = node.title
+        new_dict["author"] = node.contributors
+        new_dict["year"] = node.publication_date
+        new_dict["doi"] = node.doi_url
+        
+        
+        list_of_node_dicts.append(new_dict)
+    for edge in E:
+        new_dict_2 = dict()
+        new_dict_2["source"] = edge[0]
+        new_dict_2["target"] = edge[1]
+        list_of_edge_dicts.append(new_dict_2)
+    dict_of_all["nodes"] = list_of_node_dicts
+    dict_of_all["links"] = list_of_edge_dicts
+    #return(dict_of_all)
+    with open('json_text.txt','w') as outfile:
+        json.dump(dict_of_all, outfile)
   
 
-knoten = ["doi1", "doi2", "doi3"]
-kanten = [[1,2],[3,4],[5,6]]
-output_to_json(knoten,kanten)
+#knoten = ["doi1", "doi2", "doi3"]
+#kanten = [[1,2],[3,4],[5,6]]
+#output_to_json(knoten,kanten)
 

verarbeitung/json_text.txt

+{"nodes": [{"name": "Comparing Molecular Patterns Using the Example of SMARTS: Applications and Filter Collection Analysis", "doi": "https://doi.org/10.1021/acs.jcim.9b00249"}, {"name": "Combining Machine Learning and Computational Chemistry for Predictive Insights Into Chemical Systems ", "doi": "https://doi.org/10.1021/acs.chemrev.1c00107"}, {"name": "Disconnected Maximum Common Substructures under Constraints ", "doi": "https://doi.org/10.1021/acs.jcim.0c00741"}, {"name": "Evolution of Novartis\u2019 Small Molecule Screening Deck Design ", "doi": "https://doi.org/10.1021/acs.jmedchem.0c01332"}, {"name": "Comparing Molecular Patterns Using the Example of SMARTS: Theory and Algorithms ", "doi": "https://doi.org/10.1021/acs.jcim.9b00250"}, {"name": "Machine learning accelerates quantum mechanics predictions of molecular crystals ", "doi": "https://doi.org/10.1016/j.physrep.2021.08.002"}, {"name": "The Growing Importance of Chirality in 3D Chemical Space Exploration and Modern Drug Discovery Approaches for Hit-ID ", "doi": "https://doi.org/10.1021/acsmedchemlett.1c00251"}, {"name": "Target-Based Evaluation of \u201cDrug-Like\u201d Properties and Ligand Efficiencies ", "doi": "https://doi.org/10.1021/acs.jmedchem.1c00416"}, {"name": "BonMOLi\u00e8re: Small-Sized Libraries of Readily Purchasable Compounds, Optimized to Produce Genuine Hits in Biological Screens across the Protein Space ", "doi": "https://doi.org/10.3390/ijms22157773"}, {"name": "Accelerating high-throughput virtual screening through molecular pool-based active learning ", "doi": "https://doi.org/10.1039/D0SC06805E"}, {"name": "Compound Screening ", "doi": "https://doi.org/10.1016/B978-0-12-820472-6.00078-5"}], "links": [{"source": "https://doi.org/10.1021/acs.jcim.9b00249", "target": "https://doi.org/10.1021/acs.chemrev.1c00107"}, {"source": "https://doi.org/10.1021/acs.jcim.9b00249", "target": "https://doi.org/10.1021/acs.jcim.0c00741"}, {"source": "https://doi.org/10.1021/acs.jcim.9b00249", "target": "https://doi.org/10.1021/acs.jmedchem.0c01332"}, {"source": "https://doi.org/10.1021/acs.jcim.9b00249", "target": "https://doi.org/10.1021/acs.jcim.9b00250"}, {"source": "https://doi.org/10.1021/acs.jcim.9b00249", "target": "https://doi.org/10.1016/j.physrep.2021.08.002"}, {"source": "https://doi.org/10.1021/acs.jmedchem.0c01332", "target": "https://doi.org/10.1021/acsmedchemlett.1c00251"}, {"source": "https://doi.org/10.1021/acs.jmedchem.0c01332", "target": "https://doi.org/10.1021/acs.jmedchem.1c00416"}, {"source": "https://doi.org/10.1021/acs.jmedchem.0c01332", "target": "https://doi.org/10.3390/ijms22157773"}, {"source": "https://doi.org/10.1021/acs.jmedchem.0c01332", "target": "https://doi.org/10.1039/D0SC06805E"}, {"source": "https://doi.org/10.1021/acs.jmedchem.0c01332", "target": "https://doi.org/10.1016/B978-0-12-820472-6.00078-5"}]}
\ No newline at end of file