diff --git a/example_input.py b/example_input.py
index a8331cb93912fb21a1d184ab97beda8996413c74..febbc7b05ced9c093adc0fe413fbd2d5e3094e1e 100755
--- a/example_input.py
+++ b/example_input.py
@@ -1,14 +1,10 @@
#!/usr/bin/env python3
-from input.interface import InputInterface
-import input.publication
+from input.interface import InputInterface as Input
def main(url: str):
- #print(get_publication(url))
- print(InputInterface.get_publication(url))
- #pub.print_pub()
+ print(Input.get_publication(url))
if __name__ == "__main__":
#main("https://doi.org/10.1021/acs.jcim.1c00203")
- #main("https://doi.org/10.1021/acs.jcim.1c00917")
- main("https://doi.org/10.1021/acs.jcim.5b00332")
+ main("https://pubs.acs.org/doi/10.1021/acs.jcim.5b00332")
diff --git a/input/.publication.py.swp b/input/.publication.py.swp
deleted file mode 100644
index d2a0a137478b10579a081fbe5111873dda6877d0..0000000000000000000000000000000000000000
Binary files a/input/.publication.py.swp and /dev/null differ
diff --git a/input/README.md b/input/README.md
index 0ebd7e1c0a72a1cd23caf15f227e2b8c186a75b4..7776ee0c3e01c24b0fc99c9025783dbc1d02c563 100644
--- a/input/README.md
+++ b/input/README.md
@@ -5,12 +5,12 @@ Input-Package to fetch publication information with a given url.
## Usage/Examples
```python
-from input.interface import get_publication
+from input.interface import InputInterface as Input
from input.publication import Publication
def main(url):
try:
- pub = get_publication(url)
+ pub = Input.get_publication(url)
except Exception as error:
raise error
@@ -21,6 +21,14 @@ def main(url):
if __name__=="__main__":
main("https://doi.org/10.1021/acs.chemrev.8b00728")
```
+
+## Testing
+
+``` c
+python -m unittest input/test/<file.py> -v
+# for all tests in directory
+python -m unittest discover input/test -v
+```
## Authors
- Florian Jochens
- Sam Ockenden
diff --git a/input/get/acs.py b/input/get/acs.py
index 3a54a1512944196285651315fc47a821a463e2d2..cfc1d6db0372c4267fc971a4f3dd0064ea5a63fa 100755
--- a/input/get/acs.py
+++ b/input/get/acs.py
@@ -21,13 +21,16 @@ class Fetcher(JournalFetcher):
SUPPORTED_JOURNALS = ['1021']
@staticmethod
- def can_use_url(url: str) -> bool:
+ def can_use_url(url: str) -> str:
"""
Uses Regex to extract journal specific substrings in Doi.
TODO: Support non Doi-urls
"""
- matched_url = re.match(r'(https?://)?(doi.org/)?(10.(\d{4})/\w+.\S+)', url)
- return matched_url[4] in Fetcher.SUPPORTED_JOURNALS
+ matched_url = re.match(r'^(https?://)?(doi.org/|pubs.acs.org/doi/)?(10.(\d{4})/\w+.\S+)', url.strip(". \t\r\n"))
+ if matched_url is not None:
+ return matched_url[4] in Fetcher.SUPPORTED_JOURNALS
+ else:
+ return False
@staticmethod
def get_publication(url: str) -> Publication:
@@ -65,16 +68,19 @@ class Fetcher(JournalFetcher):
references_soup = ref_cit_soup.select('ol#references')
if references_soup != []:
for reference in references_soup[0].select('li'):
- ref_doi = "https://doi.org/{}".format(reference.select('.refDoi')[0].text.strip()[5:])\
- if reference.select('.refDoi') != [] else "None"
+ if reference.select('.refDoi') != []:
+ ref_doi = "https://doi.org/{}".format(reference.select('.refDoi')[0].text.strip()[5:])
+ else:
+ # No Doi -> No Paper
+ continue
ref_title = reference.select('.NLM_article-title')[0].text\
- if reference.select('.NLM_article-title') != [] else "None"
+ if reference.select('.NLM_article-title') != [] else None
ref_journal = reference.select('i')[0].text\
- if reference.select('i') != [] else "None"
+ if reference.select('i') != [] else None
ref_contributors=[]
for author in reference.select('.NLM_contrib-group'):
- ref_contributors.append(author.text)
+ ref_contributors.append(author.text.replace("\n", " ").replace("\r", ""))
references.append(Citation(ref_doi, ref_title, ref_journal, ref_contributors, cit_type="Reference"))
@@ -82,14 +88,18 @@ class Fetcher(JournalFetcher):
citation_soup = ref_cit_soup.select('.cited-content_cbyCitation')
if citation_soup != []:
for citation in citation_soup[0].select('li'):
- cit_doi = citation.select('a[title="DOI URL"]')[0].text\
- if citation.select('a[title="DOI URL"]') != [] else "None"
+ if citation.select('a[title="DOI URL"]') != []:
+ cit_doi = citation.select('a[title="DOI URL"]')[0].text
+ else:
+ # No Doi -> No Paper
+ continue
cit_title = citation.select('.cited-content_cbyCitation_article-title')[0].text\
if citation.select('.cited-content_cbyCitation_article-title')!= [] else "None"
cit_journal = citation.select('.cited-content_cbyCitation_journal-name')[0].text\
if citation.select('.cited-content_cbyCitation_journal-name') != [] else "None"
cit_contributors =[]
- cit_contributors = citation.select('.cited-content_cbyCitation_article-contributors')[0].text.split(', ')
+ cit_contributors = citation.select('.cited-content_cbyCitation_article-contributors')[0]\
+ .text.replace("\n", " ").replace("\r", "").split(', ')
# clean up of the last Entry
cit_contributors_last = cit_contributors.pop().strip(". ")
if cit_contributors_last != '':
@@ -98,8 +108,3 @@ class Fetcher(JournalFetcher):
return Publication(doi_url, title, contributors, journal, published
, subjects, num_citations, references, citations)
-
-
- @staticmethod
- def test_fetcher():
- pass
diff --git a/input/get/acs_fj.py b/input/get/acs_fj.py
deleted file mode 100755
index 28808382951156c919eecc4cfc827ea8059fe835..0000000000000000000000000000000000000000
--- a/input/get/acs_fj.py
+++ /dev/null
@@ -1,100 +0,0 @@
-#!/usr/bin/env python3
-
-"""
-Child class of JournalFetcher
-JCIM
-"""
-
-# import re
-from input.get.journal_fetcher import JournalFetcher
-from input.publication import Publication, Citation, Reference
-import requests as req
-from bs4 import BeautifulSoup as bs
-
-class Fetcher(JournalFetcher):
-
- """
- """
-
- # TODO: Naming-Convention:
- # Class: 'Fetcher'
- # file: input_get_[journal-/organisation-name]
- # format = "input_get_[a-z]*.py" allowed
- # TODO: List of Compatable Journals
- _SUPPORTED_JOURNALS = []
-
- @staticmethod
- def can_use_url(url: str) -> bool:
- """
- Checks if given url links to a supported journal.
- """
-
- # TODO: Check the URL for compatability
- # re.match in _SUPPORTED_JOURNALS
- return True
-
- @staticmethod
- def get_publication(url: str) -> Publication:
- return input(url)
-
-
- @staticmethod
- def test_fetcher():
- pass
-
-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(doi_url, article_title, contributors, "JCIM",
- publication_date, subjects, num_citations)
- #pub = Publication(article_title, publication_date, contributors, doi_url,
- # subjects, num_citations)
- return pub
-
-
-def get_citation_info(pub, num_citations, soup):
- 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'))
- # TODO: There are a few diffrent types how Contributors are listed
- 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(doi_urls[i], titles[i], journal_names[i], \
- contributors[i]))
-
-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
diff --git a/input/get/journal_fetcher.py b/input/get/journal_fetcher.py
index 097eb2456676bd06ab6ca697c80eed1b7c03c475..aad5857016a25c95b572ffdd32dfd69c67d67388 100755
--- a/input/get/journal_fetcher.py
+++ b/input/get/journal_fetcher.py
@@ -14,6 +14,7 @@ class JournalFetcher(metaclass=ABCMeta):
"""
This is a abstract-class for fetcher modules
"""
+
@staticmethod
def get_soup(url: str) -> BeautifulSoup:
"""
@@ -31,7 +32,8 @@ class JournalFetcher(metaclass=ABCMeta):
raise SystemExit(err)
return BeautifulSoup(req.content, 'html.parser')
-
+
+
@staticmethod
@abstractmethod
def can_use_url(url: str) -> bool:
@@ -41,6 +43,7 @@ class JournalFetcher(metaclass=ABCMeta):
"""
raise AttributeError("JournalFetcher for '{}' hasnt implemented 'can_use_url()'".format(url))
+
@staticmethod
@abstractmethod
def get_publication(url: str) -> Publication:
@@ -49,12 +52,3 @@ class JournalFetcher(metaclass=ABCMeta):
Creates a Publication-instance.
"""
raise AttributeError("JournalFetcher for '{}' hasnt implemented 'get_publication()'".format(url))
-
- @staticmethod
- @abstractmethod
- def test_fetcher():
- """
- Abstract-function to be implemented in subclass.
- Unit-test for the class.
- """
- raise AttributeError("JournalFetcher: Subclass hasnt implemented 'test_fetcher()'")
diff --git a/input/get/nature.py b/input/get/nature.py
old mode 100755
new mode 100644
index d08d74f636687eb8510ad51167a9c9380272ed18..4d206f426d06575e1e7829ec8ec42631b3fe6493
--- a/input/get/nature.py
+++ b/input/get/nature.py
@@ -57,7 +57,3 @@ class Fetcher(JournalFetcher):
# TODO: Exceptions-handling
# raise ValueException("Cant Fetch: '{}'".format(error))
# return None
-
- @staticmethod
- def test_fetcher():
- pass
diff --git a/input/get/template_.py b/input/get/template_.py
index 72f3cf913f8d9165d09fd897d0bb68ba9b30183a..da200bcfff5ea91445d476852f3763d97541dec9 100755
--- a/input/get/template_.py
+++ b/input/get/template_.py
@@ -31,7 +31,9 @@ class Fetcher(JournalFetcher):
# TODO: Check the URL for compatability
# url_re = re.match(r'(https?://)?(doi.org/)?(10.(\d{4})/\w+.\S+)', url)
- # return url_re[4] in SUPPORTED_JOURNALS
+ # if url_re is not None:
+ # return url_re[4] in SUPPORTED_JOURNALS
+ # else:
return False
@staticmethod
@@ -45,8 +47,4 @@ class Fetcher(JournalFetcher):
# doi,title,contributors[],journal,publication_date,subjects[],references[],citations[]
# TODO: Create new Publication-instance
# return Publication(doi,title,contributors[],journal,publication_date,subjects[],num_citation=None ,references[],citations[])
- return None
-
- @staticmethod
- def test_fetcher():
- pass
+ return None
\ No newline at end of file
diff --git a/input/publication.py b/input/publication.py
index f819bedea7d1ad944e34d915dfc0027a21054cc8..6de23733972a02ced3fe41d015e52b39c4f404f3 100755
--- a/input/publication.py
+++ b/input/publication.py
@@ -4,10 +4,10 @@ class Publication:
"""
Represents a Publications
"""
- def __init__(self, doi_url: str, title: str
- , contributors: str, journal: str
- , publication_date: str, subjects = None, num_citations = None
- , references = None, citations = None ):
+ def __init__(self, doi_url: str, title: str \
+ , contributors: list[str], journal: str \
+ , publication_date: str, subjects: list[str], num_citations: int = None \
+ , references: list[any] = None, citations: list[any] = None ):
"""
Parameters
----------
@@ -72,7 +72,7 @@ class Publication:
citation_string.append(citation.__str__())
return citation_string
- def citations(self, citation) -> None:
+ def add_citations(self, citation) -> None:
"""
Appends a list of Citations or Citation to self.citations.
@@ -132,9 +132,9 @@ Subjects:''')
class Citation:
- def __init__(self, doi_url: str, title: str
- , journal: str, contributors = None
- , cit_type = "Citation"):
+ def __init__(self, doi_url: str, title: str \
+ , journal: str, contributors: list[str] \
+ , cit_type: str = "Citation"):
"""
Parameters
----------
@@ -168,7 +168,7 @@ class Citation:
# This is just a replica of Citations
class Reference:
- def __init__(self, doi_url, title, journal, contributors):
+ def __init__(self, doi_url: str, title: str, journal: str, contributors: list[str]):
self.title = title
self.doi_url = doi_url
self.journal = journal
diff --git a/input/tempdir/input_fj.py b/input/tempdir/input_fj.py
deleted file mode 100755
index 00bb0126e2ae1abf6563bf99a16cc585b6d88077..0000000000000000000000000000000000000000
--- a/input/tempdir/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/input/tempdir/pub.py b/input/tempdir/pub.py
deleted file mode 100644
index 13b90e804cd485813b731385b319b3077a017dd2..0000000000000000000000000000000000000000
--- a/input/tempdir/pub.py
+++ /dev/null
@@ -1,32 +0,0 @@
-class Publication:
- #_registry = []
- #_citations = []
- #_references = []
-
- 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
- self.num_references = num_references
- 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
-
diff --git a/input/tempdir/test.py b/input/tempdir/test.py
deleted file mode 100755
index bdd12e849ed5a239cadf5f8180d319a114512f9f..0000000000000000000000000000000000000000
--- a/input/tempdir/test.py
+++ /dev/null
@@ -1,15 +0,0 @@
-#!/usr/bin/env python3
-
-from input_fj import input, print_pub_info
-import sys
-
-if len(sys.argv) != 3:
- sys.stderr.write('Usage: {} <url>\n'.format(sys.argv[0]))
- exit(1)
-url = sys.argv[1]
-url2 = sys.argv[2]
-pub = input(url)
-print_pub_info(pub)
-pub2 = input(url2)
-print_pub_info(pub2)
-
diff --git a/input/test_input_get_publication.py b/input/test_input_get_publication.py
deleted file mode 100755
index 941dbc76b5fb190ebf906ebfea8b60fbbbdd5d40..0000000000000000000000000000000000000000
--- a/input/test_input_get_publication.py
+++ /dev/null
@@ -1,28 +0,0 @@
-import unittest
-"""
-Testing the Publication fetcher
-
-Publication 1: 'https://doi.org/10.1021/acs.jcim.1c00203'
-Publication 2: 'doi.org/10.1021/acs.jcim.1c00917'
-Publication 3: '10.1038/nchem.1781'
-Publication 4: '11.12/jaj'
-Publication 5: '11.12/'
-Publication 6: 'https://doi.org/10.1021/acs.jmedchem.0c01332' # Paper is a PDF
-"""
-
-
-class TestGetPublication(unittest.TestCase):
-
- def test_publication1(self):
- pass
-
- def test_publication2(self):
- pass
-
- def test_publication3(self):
- pass
-
-
-if __name__=="__main__":
- print("test")
- unittest.main()
\ No newline at end of file