From 30836634a39a9a9f7d6d8889a5c61e0e31ea8c57 Mon Sep 17 00:00:00 2001
From: Florian Jochens <fj@andaco.de>
Date: Wed, 1 Dec 2021 12:35:05 +0100
Subject: [PATCH] added get_pub_light function only fetches information for
the given article and not it's citations and references
---
example_input.py | 5 +++--
input/get/acs.py | 52 ++++++++++++++++++++++++++++++++++++++++++++++
input/interface.py | 28 +++++++++++++++++++++++--
3 files changed, 81 insertions(+), 4 deletions(-)
diff --git a/example_input.py b/example_input.py
index 76eede0..c9bca41 100755
--- a/example_input.py
+++ b/example_input.py
@@ -4,9 +4,10 @@ from input.interface import InputInterface as Input
def main(url: str):
i = Input()
- print(i.get_publication(url))
+ #print(i.get_publication(url))
+ print(i.get_pub_light(url))
# print(i.get_supported_fetchers()) Useless because all classes are called the same
if __name__ == "__main__":
#main("https://doi.org/10.1021/acs.jcim.1c0023")
- main("https://doi.org/10.1021/acs.jcim.5b00332")
+ main("https://doi.org/10.1021/acs.jcim.5b00332")
diff --git a/input/get/acs.py b/input/get/acs.py
index 892cf98..9691845 100755
--- a/input/get/acs.py
+++ b/input/get/acs.py
@@ -35,6 +35,58 @@ class Fetcher(JournalFetcher):
return False
@staticmethod
+
+
+ def get_pub_light(url: str) -> Publication:
+ """
+ Fetches html and creates Beatifulsoup-instance in parent class.
+ Specific css-searches for ACS-Journals and creates Publication-instance.
+ """
+
+ # Creation of Soup
+ try:
+ soup = JournalFetcher.get_soup(url)
+ except Exception as error:
+ raise error
+
+ # Raise Error if re recognizes Pattern, but url isnt correct:
+ # For other Urls
+ if soup.text.strip(" \t\n")=="Missing resource null":
+ raise ValueError("'{}' matches Pattern for 'ACS', but doesnt link to Paper.".format(url))
+
+ # For Dois
+ if soup.title is not None:
+ if soup.title.text == "Error: DOI Not Found":
+ raise ValueError("'{}' matches Pattern for 'ACS', but doesnt link to Paper.".format(url))
+
+
+ soup_header = soup.select('.article_header')[0]
+
+ # Creates Publication
+ doi_url = soup_header.select('a[title="DOI URL"]')[0].string
+ title = soup_header.select(".hlFld-Title")[0].text
+
+ contributors = []
+ for author in soup_header.select(".hlFld-ContribAuthor"):
+ contributors.append(author.text)
+
+ journal = soup_header.select(".cit-title")[0].text
+
+ # Replaces abbreviation with whole name
+ if journal in JournalFetcher.abbrev_dict:
+ journal = JournalFetcher.abbrev_dict[journal]
+
+
+ published = soup_header.select(".pub-date-value")[0].text
+
+ subjects = []
+ subject_soup = soup_header.select('.article_header-taxonomy')[0]
+ for subject in subject_soup.select('a'):
+ subjects.append(subject.text)
+
+ return Publication(doi_url, title, contributors, journal, published,
+ subjects)
+
def get_publication(url: str) -> Publication:
"""
Fetches html and creates Beatifulsoup-instance in parent class.
diff --git a/input/interface.py b/input/interface.py
index 8f0af9d..59515b3 100755
--- a/input/interface.py
+++ b/input/interface.py
@@ -41,6 +41,7 @@ class InputInterface:
def get_publication(self, url: str) -> Publication:
"""
The interface-method to get a Publication-instance
+ (including it's citations and references)
Parameters
----------
@@ -49,7 +50,8 @@ class InputInterface:
:return: Publication instance or None if not supported
"""
- # Checks if module supports the 'url' and returns a Publication if it does.
+ # Checks if module supports the 'url' and
+ # returns a Publication if it does.
for fetcher_class in InputInterface.fetcher_classes:
if fetcher_class.can_use_url(url):
return fetcher_class.get_publication(url)
@@ -57,8 +59,30 @@ class InputInterface:
# No Module for given url was found
raise ValueError("'{}' is not supported".format(url))
+ def get_pub_light(self, url: str) -> Publication:
+ """
+ The interface-method to get a Publication-instance
+ (only for main article)
+
+ Parameters
+ ----------
+ :param url: url to a Publication
+ :type url: str
+ :return: Publication instance or None if not supported
+ """
+
+ # Checks if module supports the 'url' and
+ # returns a Publication if it does.
+ for fetcher_class in InputInterface.fetcher_classes:
+ if fetcher_class.can_use_url(url):
+ return fetcher_class.get_pub_light(url)
+
+ # No Module for given url was found
+ raise ValueError("'{}' is not supported".format(url))
+
def get_supported_fetchers(self):
- # print(self.fetcher_classes[0].__name__) Useless right now, because all classes are called the same
+ # print(self.fetcher_classes[0].__name__) Useless right now,
+ # because all classes are called the same
return [a.__name__ for a in self.fetcher_classes]
def import_fetcher_classes(self):
--
GitLab