Skip to content
Snippets Groups Projects
Commit 261601c9 authored by Malte Schokolowski's avatar Malte Schokolowski
Browse files

deleted input_fj

parent 117e9b49
No related branches found
No related tags found
1 merge request!11merge verarbeitung to main repo
Hide whitespace changes
Inline Side-by-side
verarbeitung/input_fj.py deleted 100644 → 0
+ 0
− 154
View file @ 117e9b49
#!/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 = []
_references = []
def __init__(self, title, publication_date, contributors, doi_url,
subjects = None, num_citations = None):
#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
#self._citations = []
#self._references = []
class Citation:
def __init__(self, title, journal, contributors, doi_url):
self.title = title
self.journal = journal
self.contributors = contributors
self.doi_url = doi_url
class References:
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)
verarbeitung/json_text.json
+ 1
− 1
View file @ 261601c9
{"nodes": [{"name": "Comparing Molecular Patterns Using the Example of SMARTS: Applications and Filter Collection Analysis", "author": ["Emanuel S. R. Ehmki", "Robert Schmidt", "Farina Ohm", "Matthias Rarey"], "year": "May 24, 2019", "journal": "Journal of Chemical Information and Modeling", "doi": "https://doi.org/10.1021/acs.jcim.9b00249", "group": "input", "citations": 5}, {"name": "Combining Machine Learning and Computational Chemistry for Predictive Insights Into Chemical Systems", "author": ["John A. Keith", "Valentin Vassilev-Galindo", "Bingqing Cheng", "Stefan Chmiela", "Michael Gastegger", "Klaus-Robert M\u00fcller", "Alexandre Tkatchenko"], "year": "July 7, 2021", "journal": "Chem. Rev.", "doi": "https://doi.org/10.1021/acs.chemrev.1c00107", "group": "height", "citations": 2}, {"name": "Disconnected Maximum Common Substructures under Constraints", "author": ["Robert Schmidt", "Florian Krull", "Anna Lina Heinzke", "Matthias Rarey"], "year": "December 16, 2020", "journal": "Journal of Chemical Information and Modeling", "doi": "https://doi.org/10.1021/acs.jcim.0c00741", "group": "height", "citations": 0}, {"name": "Evolution of Novartis\u2019 Small Molecule Screening Deck Design", "author": ["Ansgar Schuffenhauer", "Nadine Schneider", "Samuel Hintermann", "Douglas Auld", "Jutta Blank", "Simona Cotesta", "Caroline Engeloch", "Nikolas Fechner", "Christoph Gaul", "Jerome Giovannoni", "Johanna Jansen", "John Joslin", "Philipp Krastel", "Eugen Lounkine", "John Manchester", "Lauren G. Monovich", "Anna Paola Pelliccioli", "Manuel Schwarze", "Michael D. Shultz", "Nikolaus Stiefl", "Daniel K. Baeschlin"], "year": "November 3, 2020", "journal": "Journal of Medicinal Chemistry", "doi": "https://doi.org/10.1021/acs.jmedchem.0c01332", "group": "height", "citations": 8}, {"name": "Comparing Molecular Patterns Using the Example of SMARTS: Theory and Algorithms", "author": ["Robert Schmidt", "Emanuel S. R. Ehmki", "Farina Ohm", "Hans-Christian Ehrlich", "Andriy Mashychev", "Matthias Rarey"], "year": "May 23, 2019", "journal": "Journal of Chemical Information and Modeling", "doi": "https://doi.org/10.1021/acs.jcim.9b00250", "group": "height", "citations": 12}, {"name": "AutoDock Vina 1.2.0: New Docking Methods, Expanded Force Field, and Python Bindings", "author": ["Jerome Eberhardt", "Diogo Santos-Martins", "Andreas F. Tillack", "Stefano Forli"], "year": "July 19, 2021", "journal": "Journal of Chemical Information and Modeling", "doi": "https://doi.org/10.1021/acs.jcim.1c00203", "group": "input", "citations": 1}, {"name": "Accelerating AutoDock4 with GPUs and Gradient-Based Local Search", "author": ["Diogo Santos-Martins", "Leonardo Solis-Vasquez", "Andreas F Tillack", "Michel F Sanner", "Andreas Koch", "Stefano Forli"], "year": "January 6, 2021", "journal": "Journal of Chemical Theory and Computation", "doi": "https://doi.org/10.1021/acs.jctc.0c01006", "group": "depth", "citations": 14}, {"name": "Docking Flexible Cyclic Peptides with AutoDock CrankPep", "author": ["Yuqi Zhang", "Michel F. Sanner"], "year": "September 11, 2019", "journal": "Journal of Chemical Theory and Computation", "doi": "https://doi.org/10.1021/acs.jctc.9b00557", "group": "depth", "citations": 9}, {"name": "Lessons Learned in Empirical Scoring with smina from the CSAR 2011 Benchmarking Exercise", "author": ["David Ryan Koes", "Matthew P. Baumgartner", "Carlos J. Camacho"], "year": "February 4, 2013", "journal": "Journal of Chemical Information and Modeling", "doi": "https://doi.org/10.1021/ci300604z", "group": "depth", "citations": 100}, {"name": "Vina-Carb: Improving Glycosidic Angles during Carbohydrate Docking", "author": ["Anita K. Nivedha", "David F. Thieker", "Spandana Makeneni", "Huimin Hu", "Robert J. Woods"], "year": "January 8, 2016", "journal": "Journal of Chemical Theory and Computation", "doi": "https://doi.org/10.1021/acs.jctc.5b00834", "group": "depth", "citations": 48}, {"name": "Lennard-Jones Potential and Dummy Atom Settings to Overcome the AUTODOCK Limitation in Treating Flexible Ring Systems", "author": ["Stefano Forli", "Maurizio Botta"], "year": "June 22, 2007", "journal": "Journal of Chemical Information and Modeling", "doi": "https://doi.org/10.1021/ci700036j", "group": "depth", "citations": 32}, {"name": "AutoDock4Zn: An Improved AutoDock Force Field for Small-Molecule Docking to Zinc Metalloproteins", "author": ["Diogo Santos-Martins", "Stefano Forli", "Maria Jo\u00e3o Ramos", "Arthur J. Olson"], "year": "June 15, 2014", "journal": "Journal of Chemical Information and Modeling", "doi": "https://doi.org/10.1021/ci500209e", "group": "depth", "citations": 100}, {"name": "A Force Field with Discrete Displaceable Waters and Desolvation Entropy for Hydrated Ligand Docking", "author": ["Stefano Forli", "Arthur J. Olson"], "year": "December 9, 2011", "journal": "Journal of Medicinal Chemistry", "doi": "https://doi.org/10.1021/jm2005145", "group": "depth", "citations": 100}, {"name": "Consensus Docking: Improving the Reliability of Docking in a Virtual Screening Context", "author": ["Douglas R. Houston", "Malcolm D. Walkinshaw"], "year": "January 27, 2013", "journal": "Journal of Chemical Information and Modeling", "doi": "https://doi.org/10.1021/ci300399w", "group": "depth", "citations": 100}, {"name": "Inhomogeneous Fluid Approach to Solvation Thermodynamics. 1. Theory", "author": ["Themis Lazaridis"], "year": "April 14, 1998", "journal": "Journal of Physical Chemistry B", "doi": "https://doi.org/10.1021/jp9723574", "group": "depth", "citations": 100}, {"name": "Inhomogeneous Fluid Approach to Solvation Thermodynamics. 2. Applications to Simple Fluids", "author": ["Themis Lazaridis"], "year": "April 14, 1998", "journal": "Journal of Physical Chemistry B", "doi": "https://doi.org/10.1021/jp972358w", "group": "depth", "citations": 100}, {"name": "ZINC20\u2014A Free Ultralarge-Scale Chemical Database for Ligand Discovery", "author": ["John J. Irwin", "Khanh G. Tang", "Jennifer Young", "Chinzorig Dandarchuluun", "Benjamin R. Wong", "Munkhzul Khurelbaatar", "Yurii S. Moroz", "John Mayfield", "Roger A. Sayle"], "year": "October 29, 2020", "journal": "Journal of Chemical Information and Modeling", "doi": "https://doi.org/10.1021/acs.jcim.0c00675", "group": "depth", "citations": 25}, {"name": "Structural Biology-Inspired Discovery of Novel KRAS\u2013PDE\u03b4 Inhibitors", "author": ["Yan Jiang", "Chunlin Zhuang", "Long Chen", "Junjie Lu", "Guoqiang Dong", "Zhenyuan Miao", "Wannian Zhang", "Jian Li", "Chunquan Sheng"], "year": "September 20, 2017", "journal": "Journal of Medicinal Chemistry", "doi": "https://doi.org/10.1021/acs.jmedchem.7b01243", "group": "depth", "citations": 12}, {"name": "Directory of Useful Decoys, Enhanced (DUD-E): Better Ligands and Decoys for Better Benchmarking", "author": ["Michael M. Mysinger", "Michael Carchia", "John. J. Irwin", "Brian K. Shoichet"], "year": "June 20, 2012", "journal": "Journal of Medicinal Chemistry", "doi": "https://doi.org/10.1021/jm300687e", "group": "depth", "citations": 100}, {"name": "Evaluation of AutoDock and AutoDock Vina on the CASF-2013 Benchmark", "author": ["Thomas Gaillard"], "year": "July 10, 2018", "journal": "Journal of Chemical Information and Modeling", "doi": "https://doi.org/10.1021/acs.jcim.8b00312", "group": "depth", "citations": 74}, {"name": "Autodock Vina Adopts More Accurate Binding Poses but Autodock4 Forms Better Binding Affinity", "author": ["Nguyen Thanh Nguyen", "Trung Hai Nguyen", "T. Ngoc Han Pham", "Nguyen Truong Huy", "Mai Van Bay", "Minh Quan Pham", "Pham Cam Nam", "Van V. Vu", "Son Tung Ngo"], "year": "December 30, 2019", "journal": "Journal of Chemical Information and Modeling", "doi": "https://doi.org/10.1021/acs.jcim.9b00778", "group": "depth", "citations": 65}, {"name": "Glide:\u2009 A New Approach for Rapid, Accurate Docking and Scoring. 1. Method and Assessment of Docking Accuracy", "author": ["Richard A. Friesner", "Jay L. Banks", "Robert B. Murphy", "Thomas A. Halgren", "Jasna J. Klicic", "Daniel T. Mainz", "Matthew P. Repasky", "Eric H. Knoll", "Mee Shelley", "Jason K. Perry", "David E. Shaw", "Perry Francis", "Peter S. Shenkin"], "year": "February 27, 2004", "journal": "Journal of Medicinal Chemistry", "doi": "https://doi.org/10.1021/jm0306430", "group": "depth", "citations": 97}, {"name": "Surflex:\u2009 Fully Automatic Flexible Molecular Docking Using a Molecular Similarity-Based Search Engine", "author": ["Ajay N. Jain"], "year": "January 21, 2003", "journal": "Journal of Medicinal Chemistry", "doi": "https://doi.org/10.1021/jm020406h", "group": "depth", "citations": 100}, {"name": "ID-Score: A New Empirical Scoring Function Based on a Comprehensive Set of Descriptors Related to Protein\u2013Ligand Interactions", "author": ["Guo-Bo Li", "Ling-Ling Yang", "Wen-Jing Wang", "Lin-Li Li", "Sheng-Yong Yang"], "year": "February 9, 2013", "journal": "Journal of Chemical Information and Modeling", "doi": "https://doi.org/10.1021/ci300493w", "group": "depth", "citations": 99}, {"name": "A Knowledge-Based Energy Function for Protein\u2212Ligand, Protein\u2212Protein, and Protein\u2212DNA Complexes", "author": ["Chi Zhang", "Song Liu", "Qianqian Zhu", "Yaoqi Zhou"], "year": "February 16, 2005", "journal": "Journal of Medicinal Chemistry", "doi": "https://doi.org/10.1021/jm049314d", "group": "depth", "citations": 100}, {"name": "Novel Anti-Hepatitis B Virus Activity of Euphorbia schimperi and Its Quercetin and Kaempferol Derivatives", "author": ["Mohammad K. Parvez", "Sarfaraz Ahmed", "Mohammed S. Al-Dosari", "Mazin A. S. Abdelwahid", "Ahmed H. Arbab", "Adnan J. Al-Rehaily", "Mai M. Al-Oqail"], "year": "October 21, 2021", "journal": "ACS Omega", "doi": "https://doi.org/10.1021/acsomega.1c04320", "group": "height", "citations": 0}], "links": [{"source": "https://doi.org/10.1021/acs.chemrev.1c00107", "target": "https://doi.org/10.1021/acs.jcim.9b00249"}, {"source": "https://doi.org/10.1021/acs.jcim.0c00741", "target": "https://doi.org/10.1021/acs.jcim.9b00249"}, {"source": "https://doi.org/10.1021/acs.jmedchem.0c01332", "target": "https://doi.org/10.1021/acs.jcim.9b00249"}, {"source": "https://doi.org/10.1021/acs.jcim.9b00250", "target": "https://doi.org/10.1021/acs.jcim.9b00249"}, {"source": "https://doi.org/10.1021/acs.jcim.1c00203", "target": "https://doi.org/10.1021/acs.jctc.0c01006"}, {"source": "https://doi.org/10.1021/acs.jcim.1c00203", "target": "https://doi.org/10.1021/acs.jctc.9b00557"}, {"source": "https://doi.org/10.1021/acs.jcim.1c00203", "target": "https://doi.org/10.1021/ci300604z"}, {"source": "https://doi.org/10.1021/acs.jcim.1c00203", "target": "https://doi.org/10.1021/acs.jctc.5b00834"}, {"source": "https://doi.org/10.1021/acs.jcim.1c00203", "target": "https://doi.org/10.1021/ci700036j"}, {"source": "https://doi.org/10.1021/acs.jcim.1c00203", "target": "https://doi.org/10.1021/ci500209e"}, {"source": "https://doi.org/10.1021/acs.jcim.1c00203", "target": "https://doi.org/10.1021/jm2005145"}, {"source": "https://doi.org/10.1021/acs.jcim.1c00203", "target": "https://doi.org/10.1021/ci300399w"}, {"source": "https://doi.org/10.1021/acs.jcim.1c00203", "target": "https://doi.org/10.1021/jp9723574"}, {"source": "https://doi.org/10.1021/acs.jcim.1c00203", "target": "https://doi.org/10.1021/jp972358w"}, {"source": "https://doi.org/10.1021/acs.jcim.1c00203", "target": "https://doi.org/10.1021/acs.jcim.0c00675"}, {"source": "https://doi.org/10.1021/acs.jcim.1c00203", "target": "https://doi.org/10.1021/acs.jmedchem.7b01243"}, {"source": "https://doi.org/10.1021/acs.jcim.1c00203", "target": "https://doi.org/10.1021/jm300687e"}, {"source": "https://doi.org/10.1021/acs.jcim.1c00203", "target": "https://doi.org/10.1021/acs.jcim.8b00312"}, {"source": "https://doi.org/10.1021/acs.jcim.1c00203", "target": "https://doi.org/10.1021/acs.jcim.9b00778"}, {"source": "https://doi.org/10.1021/acs.jcim.1c00203", "target": "https://doi.org/10.1021/jm0306430"}, {"source": "https://doi.org/10.1021/acs.jcim.1c00203", "target": "https://doi.org/10.1021/jm020406h"}, {"source": "https://doi.org/10.1021/acs.jcim.1c00203", "target": "https://doi.org/10.1021/ci300493w"}, {"source": "https://doi.org/10.1021/acs.jcim.1c00203", "target": "https://doi.org/10.1021/jm049314d"}, {"source": "https://doi.org/10.1021/acsomega.1c04320", "target": "https://doi.org/10.1021/acs.jcim.1c00203"}, {"source": "https://doi.org/10.1021/acs.chemrev.1c00107", "target": "https://doi.org/10.1021/acs.jcim.9b00250"}, {"source": "https://doi.org/10.1021/acs.jcim.0c00741", "target": "https://doi.org/10.1021/acs.jcim.9b00250"}, {"source": "https://doi.org/10.1021/acs.jmedchem.0c01332", "target": "https://doi.org/10.1021/acs.jcim.9b00250"}, {"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.8b00312", "target": "https://doi.org/10.1021/ci300604z"}, {"source": "https://doi.org/10.1021/acs.jctc.0c01006", "target": "https://doi.org/10.1021/ci700036j"}, {"source": "https://doi.org/10.1021/acs.jctc.9b00557", "target": "https://doi.org/10.1021/ci700036j"}, {"source": "https://doi.org/10.1021/ci500209e", "target": "https://doi.org/10.1021/ci700036j"}, {"source": "https://doi.org/10.1021/acs.jctc.0c01006", "target": "https://doi.org/10.1021/ci500209e"}, {"source": "https://doi.org/10.1021/acs.jctc.0c01006", "target": "https://doi.org/10.1021/jm2005145"}, {"source": "https://doi.org/10.1021/acs.jcim.8b00312", "target": "https://doi.org/10.1021/jm2005145"}, {"source": "https://doi.org/10.1021/ci500209e", "target": "https://doi.org/10.1021/jm2005145"}, {"source": "https://doi.org/10.1021/acs.jcim.0c00741", "target": "https://doi.org/10.1021/jm300687e"}, {"source": "https://doi.org/10.1021/acs.jcim.9b00778", "target": "https://doi.org/10.1021/acs.jcim.8b00312"}, {"source": "https://doi.org/10.1021/acs.jctc.0c01006", "target": "https://doi.org/10.1021/acs.jcim.9b00778"}]} {"nodes": [{"name": "title_h02", "author": ["contributor_h02"], "year": "date_h02", "journal": "journal_h02", "doi": "doi_h02", "group": "input", "citations": 1}, {"name": "title_h1", "author": ["contributor_h1"], "year": "date_h1", "journal": "journal_h1", "doi": "doi_h1", "group": "height", "citations": 1}, {"name": "title_h2", "author": ["contributor_h2"], "year": "date_h2", "journal": "journal_h2", "doi": "doi_h2", "group": "height", "citations": 1}], "links": [{"source": "doi_h1", "target": "doi_h02"}, {"source": "doi_h2", "target": "doi_h1"}]}
\ No newline at end of file \ No newline at end of file
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment