diff --git "a/verarbeitung/Processing_test_doi_\303\274berarbeitet.py" b/verarbeitung/Processing.py
similarity index 77%
rename from "verarbeitung/Processing_test_doi_\303\274berarbeitet.py"
rename to verarbeitung/Processing.py
index ac6ce63dc512a4e53303ad75f74f04bf6221e191..bfa533a3161063b7ec82231cbc2c34950336eb11 100644
--- "a/verarbeitung/Processing_test_doi_\303\274berarbeitet.py"
+++ b/verarbeitung/Processing.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
diff --git a/verarbeitung/Processing_test.py b/verarbeitung/Processing_test.py
deleted file mode 100644
index 83631bffd92012e7dec57079cee9755fc673a295..0000000000000000000000000000000000000000
--- a/verarbeitung/Processing_test.py
+++ /dev/null
@@ -1,101 +0,0 @@
-# -*- coding: utf-8 -*-
-"""
-Created on Wed Nov 3 16:54:43 2021
-
-@author: Malte Schokolowski
-"""
-
-from bs4 import BeautifulSoup as bs
-import requests as req
-import sys
-from pathlib import Path
-import input_test as inp
-
-
-def process_main(array, depth):
- #ERROR-Handling doi_array = NULL, Tiefe < 0 oder 1 ??? +
- if (depth < 0):
- print("Error, depth of search must be positive")
-
-
-
- # leeres Array für die Knoten wird erstellt
- # leeres Array für die Kanten wird erstellt
- global V, E
- V = []
- E = []
-
- # Füge in Knoten-Array alle Starterknoten ein
- for pub_doi in array:
- pub = inp.input(pub_doi)
- V.append(pub)
- #print("\n")
- process_rec(array, 0, depth)
- return(V,E)
-
-
-def process_rec(array, depth, depth_max):
- depth += 1
- for pub_doi in array:
- # Input aufrufen und speichern
- pub = inp.input(pub_doi)
-
- # Klasseninstanz bestehend aus u.a.
- # Name, Autoren, DOI, Jahr,
- # was_wir_zitiert_haben, wo_wir_zitiert_wurden
- for citation in pub._citations:
- #print(pub.doi_url, ".\t", citation.doi_url, "\n")
- #Knoten j erstellen, wenn noch unbekannt
- if (citation not in V):
- if (depth <= depth_max):
- V.append(citation)
- #print(citation.doi_url, "\n")
- E.append([pub,citation])
- #print(pub.doi_url, ".\t", citation.doi_url, "\n")
-
- else:
- E.append([pub,citation]) # Kante erstellen, wenn citation bekannt, also wenn beide im Input sind oder bei Zyklus
- #print(pub.doi_url, ".\t", citation.doi_url, "\n")
-
-
- #for k in wo_wir_zitiert_wurden:
- #if (i != k):
- #Knoten k erstellen, wenn noch unbekannt
- #Kante erstellen von k nach i
-
- if (depth < depth_max):
- cit_arr = []
- for citation in pub._citations:
- if ("acs" in citation.doi_url):
- cit_arr.append(citation.doi_url)
- process_rec(cit_arr, depth, depth_max)
-
-
-
- # Knoten- und Kantenmenge zurückgeben
- # {1,2,3,4,5} oder
- # {{1="paper1",0}, {2 = "paper2"},1} oder
- # {1="paper1", 2 = "paper2"}
- # {(1,2),(2,3),(2,4)}
-
-
-arr = []
-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/acs.accounts.1c00440')
-
-#arr.append('https://doi.org/10.1021/ci700007b')
-#arr.append('https://doi.org/10.1021/acs.jcim.5b00292')
-#url = sys.argv[1]
-#arr.append[url]
-
-V,E = process_main(arr,1)
-
-for vortex in V:
- #print(vortex, "\n")
- print(vortex.doi_url, "\n")
-print("\n")
-for i in range(len(E)):
- #print(edge,"\n")
- print(E[i][0].doi_url, ", ",E[i][1].doi_url, "\n")
\ No newline at end of file
diff --git a/verarbeitung/Processing_test_doi.py b/verarbeitung/Processing_test_doi.py
deleted file mode 100644
index 898ab1a0265a1d7e1ef8f51a99cb4be1bc33ad87..0000000000000000000000000000000000000000
--- a/verarbeitung/Processing_test_doi.py
+++ /dev/null
@@ -1,104 +0,0 @@
-# -*- coding: utf-8 -*-
-"""
-Created on Wed Nov 3 16:54:43 2021
-
-@author: Malte Schokolowski
-"""
-
-from bs4 import BeautifulSoup as bs
-import requests as req
-import sys
-from pathlib import Path
-import input_test as inp
-
-
-
-def process_main(array, depth):
- #ERROR-Handling doi_array = NULL, Tiefe < 0 oder 1 ??? +
-
- if (depth < 0):
- print("Error, depth of search must be positive")
-
-
-
- # leeres Array für die Knoten wird erstellt
- # leeres Array für die Kanten wird erstellt
- global V, E
- V = []
- E = []
-
- # Füge in Knoten-Array alle Starterknoten ein
- for pub in array:
- V.append(pub)
- #print("\n")
- process_rec(array, 0, depth)
- return(V,E)
-
-
-def process_rec(array, depth, depth_max):
- depth += 1
- for pub_doi in array:
- # Input aufrufen und speichern
- #print(pub_doi)
- pub = inp.input(pub_doi)
- #for cit in pub._citations:
- #print(pub.doi_url, cit.doi_url)
- # Klasseninstanz bestehend aus u.a.
- # Name, Autoren, DOI, Jahr,
- # was_wir_zitiert_haben, wo_wir_zitiert_wurden
-
- for citation in pub._citations:
- #print(pub.doi_url, ".\t", citation.doi_url, "\n")
- #Knoten j erstellen, wenn noch unbekannt
- if (citation.doi_url not in V):
- if (depth <= depth_max):
- V.append(citation.doi_url)
- #print(citation.doi_url, "\n")
- E.append([pub.doi_url,citation.doi_url])
- #print(pub.doi_url, ".\t", citation.doi_url, "\n")
-
- else:
- E.append([pub.doi_url,citation.doi_url]) # Kante erstellen, wenn citation bekannt, also wenn beide in gleicher Tiefe sind oder bei Zyklus
- #print(pub.doi_url, ".\t", citation.doi_url, "\n")
-
-
- #for k in wo_wir_zitiert_wurden:
- #if (i != k):
- #Knoten k erstellen, wenn noch unbekannt
- #Kante erstellen von k nach i
-
- if (depth < depth_max):
- cit_arr = []
- for citation in pub._citations:
- if ("acs" in citation.doi_url):
- cit_arr.append(citation.doi_url)
- process_rec(cit_arr, depth, depth_max)
- #else:
- #print("--- %s seconds ---" % (time.time() - start_time))
- #process_rec(wo_wir_zitiert_wurden, depth -1)'''
-
-
- # Knoten- und Kantenmenge zurückgeben
- # {1,2,3,4,5} oder
- # {{1="paper1",0}, {2 = "paper2"},1} oder
- # {1="paper1", 2 = "paper2"}
- # {(1,2),(2,3),(2,4)}
-
-
-arr = []
-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')
-#arr.append('https://doi.org/10.1021/acs.jcim.5b00292')
-#url = sys.argv[1]
-#arr.append[url]
-
-V,E = process_main(arr,2)
-
-for vortex in V:
- print(vortex, "\n")
-print("\n")
-for edge in E:
- print(edge,"\n")
\ No newline at end of file
diff --git a/verarbeitung/input_fj.py b/verarbeitung/input_fj.py
deleted file mode 100644
index 00bb0126e2ae1abf6563bf99a16cc585b6d88077..0000000000000000000000000000000000000000
--- a/verarbeitung/input_fj.py
+++ /dev/null
@@ -1,144 +0,0 @@
-#!/usr/bin/env python3
-"""
-Functions for information retrieval of articles from the ACS journal JCIM
-
-"""
-
-__author__ = "Florian Jochens"
-__email__ = "fj@andaco.de"
-__status__ = "Production"
-#__copyright__ = ""
-#__credits__ = ["", "", "", ""]
-#__license__ = ""
-#__version__ = ""
-#__maintainer__ = ""
-
-from bs4 import BeautifulSoup as bs
-import requests as req
-import sys
-from pathlib import Path
-
-class Publication:
- #_registry = []
- _citations = []
-
- def __init__(self, title, publication_date, contributors, doi_url,
- subjects, num_citations):
- #self._registry.append(self)
- self.title = title
- self.publication_date = publication_date
- self.contributors = contributors
- self.doi_url = doi_url
- self.subjects = subjects
- self.num_citations = num_citations
-
-class Citation:
- def __init__(self, title, journal, contributors, doi_url):
- self.title = title
- self.journal = journal
- self.contributors = contributors
- self.doi_url = doi_url
-
-def get_article_info(soup):
- header = soup.find('div', class_ = 'article_header-left pull-left')
- article_title = header.find('span', class_ = 'hlFld-Title').text
- publication_date = header.find('span', class_ = 'pub-date-value').text
- for link in header.find('div', class_ = 'article_header-doiurl'):
- doi_url = link.get('href')
- subs = header.find('div', class_ = 'article_header-taxonomy')
- subjects = []
- for sub in subs.find_all('a'):
- subjects.append(sub.get('title'))
- cons = header.find('ul', class_ = 'loa')
- contributors = []
- for con in cons.find_all('span', class_ = 'hlFld-ContribAuthor'):
- contributors.append(con.text)
- numc = header.find('div', class_ = 'articleMetrics_count')
- if not numc.a:
- num_citations = 0
- else:
- num_citations = numc.a.text
-
- pub = Publication(article_title, publication_date, contributors, doi_url,
- subjects, num_citations)
- return pub
-
-def get_download_url():
- export = soup.find('div', class_ = 'cit-download-dropdown_content')
- url = 'https://pubs.acs.org'
- for link in export.find_all('a'):
- if link.get('title') == 'Citation and references':
- url += link.get('href')
- print(url)
- return url
-
-def download(url): # Download citation and references file
- if url.find('='):
- filename = url.rsplit('=', 1)[1]
- path = Path(('./files/' + filename))
- if path.is_file():
- print("File already exists")
- else:
- print("File does not exist")
-
-def get_citation_info(pub, num_citations, soup):
- pub._citations = []
- details = soup.find('ol', class_ = 'cited-content_cbyCitation')
- titles = []
- for title in details.find_all('span',
- class_ = 'cited-content_cbyCitation_article-title'):
- titles.append(title.text.replace('.', ''))
- journal_names = []
- for name in details.find_all('span',
- class_ = 'cited-content_cbyCitation_journal-name'):
- journal_names.append(name.text)
- doi_urls = []
- for url in details.find_all('a'):
- doi_urls.append(url.get('href'))
- contributors = []
- for contrib in details.find_all('span',
- class_ = 'cited-content_cbyCitation_article-contributors'):
- contributors.append(contrib.text)
- for i in range(0, int(num_citations)):
- pub._citations.append(Citation(titles[i], journal_names[i],
- contributors[i], doi_urls[i]))
-def print_pub_info(pub):
- print(f'''Article title: {pub.title}
-Publication date: {pub.publication_date}
-DOI-URL: {pub.doi_url}
-
-Subjects:''')
- print(*(pub.subjects), sep = ", ")
- print('\nContributors:')
- print(*(pub.contributors), sep = ", ")
-
- if int(pub.num_citations) > 0:
- if int(pub.num_citations) == 1:
- print(f'\nThis publication is cited by the following publication:\n')
- else:
- print(f'\nThis publication is cited by the following {pub.num_citations} publications:\n')
- for citation in pub._citations:
- print(f'''
- Title: {citation.title}
- Journal: {citation.journal}
- Contributors: {citation.contributors}
- DOI-URL: {citation.doi_url}
- ''')
- else:
- print('\nThis publication is not cited by any other publication.')
-
-def input(url):
- html_text = req.get(url).text
- soup = bs(html_text, 'html.parser')
-
- pub = get_article_info(soup)
- if int(pub.num_citations) > 0:
- get_citation_info(pub, int(pub.num_citations), soup)
- return pub
-
-#if len(sys.argv) != 2:
-# sys.stderr.write('Usage: {} <url>\n'.format(sys.argv[0]))
-# exit(1)
-#url = sys.argv[1]
-#pub = input(url)
-#print_pub_info(pub)
diff --git a/verarbeitung/json_text.txt b/verarbeitung/json_text.txt
deleted file mode 100644
index b5e7fa9b225b911bcd2d80c5d74097bdf4d40e1c..0000000000000000000000000000000000000000
--- a/verarbeitung/json_text.txt
+++ /dev/null
@@ -1 +0,0 @@
-{"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
diff --git a/verarbeitung/json_text_json.txt b/verarbeitung/json_text_json.txt
deleted file mode 100644
index e69de29bb2d1d6434b8b29ae775ad8c2e48c5391..0000000000000000000000000000000000000000
diff --git a/verarbeitung/processing_pseudo.py b/verarbeitung/processing_pseudo.py
deleted file mode 100644
index 0d5f5da87e9402fbbdd2dc0294a47363b4aca3ca..0000000000000000000000000000000000000000
--- a/verarbeitung/processing_pseudo.py
+++ /dev/null
@@ -1,38 +0,0 @@
-# -*- coding: utf-8 -*-
-"""
-@author: Malte Schokolowski
-"""
-
-def process_main(doi_array, depth):
- #ERROR-Handling doi_array = NULL, Tiefe < 0 oder 1 ???
-
- # leeres Array für die Knoten wird erstellt
- # leeres Array für die Kanten wird erstellt
-
- # Füge in Knoten-Array alle Starterknoten ein
- process_rec(doi_array, depth)
-
-def process_rec(doi_array, depth):
- for i in range(len(doi_array)):
- # Input aufrufen und speichern
- # Klasseninstanz bestehend aus u.a.
- # Name, Autoren, DOI, Jahr,
- # was_wir_zitiert_haben, wo_wir_zitiert_wurden
- for j in range(len(was_wir_zitiert_haben)):
- #Knoten j erstellen, wenn noch unbekannt
- #Kante erstellen von i nach j
- for k in range(len(wo_wir_zitiert_wurden)):
- if (i != k):
- #Knoten k erstellen, wenn noch unbekannt
- #Kante erstellen von k nach i
- process_rec(was_wir_zitiert_haben, depth-1)
- process_rec(wo_wir_zitiert_wurden, depth -1)
-
-
- # Knoten- und Kantenmenge zurückgeben
- # {1,2,3,4,5} oder
- # {{1="paper1",0}, {2 = "paper2"},1} oder
- # {1="paper1", 2 = "paper2"}
- # {(1,2),(2,3),(2,4)}
-
-
\ No newline at end of file