Skip to content
Snippets Groups Projects
Commit 0325babd authored by Jochens, Florian's avatar Jochens, Florian
Browse files

implemented get_acrticle_info() and get_download_url()

parent dbd3e102
No related branches found
No related tags found
1 merge request!1input
#!/usr/bin/env python3 #!/usr/bin/env python3
""" """
Functions for information retrievel of articles from the ACS journal Functions for information retrievel of articles from the ACS journal JCIM
""" """
...@@ -16,6 +16,7 @@ __status__ = "Production" ...@@ -16,6 +16,7 @@ __status__ = "Production"
from bs4 import BeautifulSoup as bs from bs4 import BeautifulSoup as bs
import requests as req import requests as req
import sys import sys
from pathlib import Path
class Publication: class Publication:
#_registry = [] #_registry = []
...@@ -53,11 +54,27 @@ def get_article_info(): ...@@ -53,11 +54,27 @@ def get_article_info():
pub = Publication(article_title, publication_date, contributors, doi_url) pub = Publication(article_title, publication_date, contributors, doi_url)
return pub return pub
"""def get_citation_info(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')
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)
return pub # return pub
def input():""" #def input():
if len(sys.argv) != 2: if len(sys.argv) != 2:
sys.stderr.write('Usage: {} <url>\n'.format(sys.argv[0])) sys.stderr.write('Usage: {} <url>\n'.format(sys.argv[0]))
...@@ -74,3 +91,6 @@ Contributors:''') ...@@ -74,3 +91,6 @@ Contributors:''')
print(*(pub.contributors), sep = ", ") print(*(pub.contributors), sep = ", ")
print(f''' print(f'''
DOI-URL: {pub.doi_url}''') DOI-URL: {pub.doi_url}''')
url = get_download_url()
download(url)
0% Loading or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment