papers-cli 2.14.1__tar.gz → 2.14.3__tar.gz

{papers_cli-2.14.1 → papers_cli-2.14.3}/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.2
+Metadata-Version: 2.4
 Name: papers-cli
-Version: 2.14.1
+Version: 2.14.3
 Summary: utilities to keep your PDF library organized
 Author-email: Mahé Perrette <mahe.perrette@gmail.com>
 License: MIT
@@ -17,6 +17,8 @@ Requires-Dist: bibtexparser
 Requires-Dist: scholarly
 Requires-Dist: rapidfuzz
 Requires-Dist: normality
+Requires-Dist: bs4
+Dynamic: license-file
 
 [![test](https://github.com/perrette/papers/workflows/CI/badge.svg?query=branch%3Amaster)](https://github.com/perrette/papers/actions)
 [![python](https://img.shields.io/badge/python-3.9-blue.svg)]()

{papers_cli-2.14.1 → papers_cli-2.14.3}/papers/_version.py

@@ -17,5 +17,5 @@ __version__: str
 __version_tuple__: VERSION_TUPLE
 version_tuple: VERSION_TUPLE
 
-__version__ = version = '2.14.1'
-__version_tuple__ = version_tuple = (2, 14, 1)
+__version__ = version = '2.14.3'
+__version_tuple__ = version_tuple = (2, 14, 3)

{papers_cli-2.14.1 → papers_cli-2.14.3}/papers/bib.py

@@ -420,11 +420,21 @@ class Biblio:
 
     def add_pdf(self, pdf, attachments=None, search_doi=True, search_fulltext=True, scholar=False, doi=None, **kw):
 
+        if str(pdf).startswith("http"):
+            # if pdf is a URL, download it
+            import requests, tempfile
+            response = requests.get(pdf)
+            if response.status_code == 200:
+                pdf = tempfile.NamedTemporaryFile(delete=False, suffix='.pdf').name
+                with open(pdf, 'wb') as f:
+                    f.write(response.content)
+            else:
+                raise ValueError(f"Failed to download PDF from {pdf}")
+
         if doi:
             bibtex = fetch_bibtex_by_doi(doi)
         else:
             bibtex = extract_pdf_metadata(pdf, search_doi, search_fulltext, scholar=scholar)
-
         bib = bibtexparser.loads(bibtex)
         entry = bib.entries[0]
 
@@ -881,4 +891,4 @@ def clean_filesdir(biblio, interactive=True, ignore_files=None, ignore_folders=N
 
         break
 
-    return removed_files
+    return removed_files

{papers_cli-2.14.1 → papers_cli-2.14.3}/papers/extract.py

@@ -14,6 +14,10 @@ from papers import logger
 from papers.encoding import family_names
 from bibtexparser.customization import convert_to_unicode
 
+from bs4 import BeautifulSoup
+from urllib.parse import urljoin
+
+
 my_etiquette = Etiquette('papers', papers.__version__, 'https://github.com/perrette/papers', 'mahe.perrette@gmail.com')
 work = Works(etiquette=my_etiquette)
 
@@ -265,12 +269,22 @@ def fetch_bibtex_by_arxiv(arxiv_id):
     else:
         return f"Error: Unable to fetch BibTeX (HTTP {response.status_code})"
 
-# @cached('crossref-bibtex.json')
 def fetch_bibtex_by_doi(doi):
     if "arxiv" in doi.lower():
         return fetch_bibtex_by_arxiv(doi.split("arXiv.")[1])
-    json_data = fetch_crossref_by_doi(doi)
-    return crossref_to_bibtex(json_data['message'])
+    try:
+        json_data = fetch_crossref_by_doi(doi)
+        return crossref_to_bibtex(json_data['message'])
+    except DOIRequestError as error:
+        pass
+
+    try:
+        return fetch_bibtex_on_journal_website(doi, as_string=True)
+    except:
+        pass
+
+    raise DOIRequestError(f"Unable to fetch BibTeX for DOI {doi}")
+
 
 @cached('crossref-json.json')
 def fetch_json_by_doi(doi):
@@ -477,3 +491,50 @@ def fetch_entry(e):
             ValueError('no author nor title field')
     db = bibtexparser.loads(bibtex)
     return db.entries[0]
+
+
+
+############### HERE A HACK DESIGNED FOR THE ESD JOURNAL ################
+# That journal often provides DOI that are not yet registered in crossref
+# so we need to fetch the bibtex from the journal website
+# Thanks Le Chat for near-instantaneous and elegantly designed code
+
+def fetch_html(url):
+    response = requests.get(url)
+    response.raise_for_status()  # Raise an error for bad status codes
+    return response.text
+
+def find_bibtex_links(html_content, base_url):
+    soup = BeautifulSoup(html_content, 'html.parser')
+
+    for link in soup.find_all('a', href=True):
+        href = link['href']
+        if href.endswith('.bib'):
+            full_url = urljoin(base_url, href)
+            yield full_url
+
+def download_bibtex(url):
+    response = requests.get(url)
+    response.raise_for_status()
+    return response.text
+
+def parse_bibtex(bibtex_content, target_doi):
+    bib_database = bibtexparser.loads(bibtex_content)
+    for entry in bib_database.entries:
+        if (entry.get('doi', '') or entry.get('DOI', '')).lower() == target_doi.lower():
+            return entry
+    return None
+
+def fetch_bibtex_on_journal_website(doi, as_string=False):
+    base_url = f"https://doi.org/{doi}"
+    html_content = fetch_html(base_url)
+    for bibtex_url in find_bibtex_links(html_content, base_url):
+        bibtex_content = download_bibtex(bibtex_url)
+        bibtex_entry = parse_bibtex(bibtex_content, doi)
+        if bibtex_entry:
+            if as_string:
+                return bibtex_content
+            else:
+                return bibtex_entry
+
+    raise DOIRequestError("No matching BibTeX entry found for the given DOI.")

{papers_cli-2.14.1 → papers_cli-2.14.3}/papers_cli.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.2
+Metadata-Version: 2.4
 Name: papers-cli
-Version: 2.14.1
+Version: 2.14.3
 Summary: utilities to keep your PDF library organized
 Author-email: Mahé Perrette <mahe.perrette@gmail.com>
 License: MIT
@@ -17,6 +17,8 @@ Requires-Dist: bibtexparser
 Requires-Dist: scholarly
 Requires-Dist: rapidfuzz
 Requires-Dist: normality
+Requires-Dist: bs4
+Dynamic: license-file
 
 [![test](https://github.com/perrette/papers/workflows/CI/badge.svg?query=branch%3Amaster)](https://github.com/perrette/papers/actions)
 [![python](https://img.shields.io/badge/python-3.9-blue.svg)]()

{papers_cli-2.14.1 → papers_cli-2.14.3}/papers_cli.egg-info/requires.txt

@@ -5,3 +5,4 @@ bibtexparser
 scholarly
 rapidfuzz
 normality
+bs4

{papers_cli-2.14.1 → papers_cli-2.14.3}/pyproject.toml

@@ -23,6 +23,7 @@ dependencies = [
     "scholarly",
     "rapidfuzz",
     "normality",
+    "bs4",
 ]
 dynamic = ["version"]
 
@@ -65,6 +66,7 @@ deps =
     rapidfuzz
     unidecode
     normality
+    bs4
     pytest
     pytest-cov
 depends =

{papers_cli-2.14.1 → papers_cli-2.14.3}/requirements.txt

@@ -4,4 +4,5 @@ crossrefapi
 bibtexparser < 2.0.0
 scholarly
 rapidfuzz
-normality
+normality
+bs4