From 0325babd8bae26e3d853429eb8484e80d5809d35 Mon Sep 17 00:00:00 2001
From: "Jochens, Florian" <fj@andaco.de>
Date: Thu, 4 Nov 2021 12:37:30 +0100
Subject: [PATCH] implemented get_acrticle_info() and get_download_url()
---
input/input_fj.py | 28 ++++++++++++++++++++++++----
1 file changed, 24 insertions(+), 4 deletions(-)
diff --git a/input/input_fj.py b/input/input_fj.py
index 07c292f..25d06b8 100755
--- a/input/input_fj.py
+++ b/input/input_fj.py
@@ -1,6 +1,6 @@
#!/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"
from bs4 import BeautifulSoup as bs
import requests as req
import sys
+from pathlib import Path
class Publication:
#_registry = []
@@ -53,11 +54,27 @@ def get_article_info():
pub = Publication(article_title, publication_date, contributors, doi_url)
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:
sys.stderr.write('Usage: {} <url>\n'.format(sys.argv[0]))
@@ -74,3 +91,6 @@ Contributors:''')
print(*(pub.contributors), sep = ", ")
print(f'''
DOI-URL: {pub.doi_url}''')
+
+url = get_download_url()
+download(url)
--
GitLab