Added functionality to search for articles using CrossRef

.pre-commit-config.yaml

@@ -1,20 +1,21 @@
 repos:
-  - repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v3.2.0
-    hooks:
-      - id: trailing-whitespace
-      - id: end-of-file-fixer
-      - id: check-yaml
-  - repo: https://github.com/astral-sh/ruff-pre-commit
-    # Ruff version.
-    rev: v0.3.3
-    hooks:
-      # Run the linter.
-      - id: ruff
-        args: [ --fix ]
-      # Run the formatter.
-      - id: ruff-format
-  - repo: https://github.com/pre-commit/mirrors-mypy
-    rev: 'v1.9.0'
-    hooks:
-    -   id: mypy
+    - repo: https://github.com/pre-commit/pre-commit-hooks
+      rev: v4.6.0
+      hooks:
+          - id: trailing-whitespace
+          - id: end-of-file-fixer
+          - id: check-yaml
+    - repo: https://github.com/astral-sh/ruff-pre-commit
+      # Ruff version.
+      rev: v0.5.1
+      hooks:
+          # Run the linter.
+          - id: ruff
+            args: [--fix]
+          # Run the formatter.
+          - id: ruff-format
+    - repo: https://github.com/pre-commit/mirrors-mypy
+      rev: 'v1.10.1'
+      hooks:
+          - id: mypy
+            additional_dependencies: ['types-requests']

pyproject.toml

@@ -18,6 +18,7 @@ dependencies = [
     "networkx~=3.0",
     "typer[all]~=0.9.0",
     "xlsxwriter~=3.2.0",
+    "types-requests~=2.32.0.20240622",
 ]
 
 [project.optional-dependencies]

src/bibx/_entities/collection_builders/cross_ref.py

@@ -1,4 +1,6 @@
-from bibx._entities.collection import Collection
+import requests
+
+from bibx._entities.collection import Article, Collection
 from bibx._entities.collection_builders.base import CollectionBuilder
 
 
@@ -12,4 +14,56 @@ def with_count(self, count: int):
         return self
 
     def build(self) -> Collection:
-        return Collection([])
+        url = f"https://api.crossref.org/works?query={self._query.lower().replace(' ', '+')}&filter=has-orcid:true,type:journal-article,has-references:true,from-pub-date:2003-01-01&rows={self._count}"
+        response = requests.get(url)
+        data = response.json()
+        items = data.get("message", {}).get("items", [])
+
+        articles = []
+        for item in items:
+            author_list = item.get("author", [])
+            authors = [
+                f"{author.get('given', '')} {author.get('family', '')}"
+                for author in author_list
+            ]
+            publication_year = item.get("published").get("date-parts", [[2000]])[0][0]
+            title = item.get("title", None)[0]
+            journal = item.get("container-title", None)[0]
+            volume = item.get("volume", None)
+            issue = item.get("issue", None)
+            page = item.get("page", None)
+            doi = item.get("DOI", None)
+            times_cited = item.get("is-referenced-by-count", 0)
+            reference = item.get("reference", [])
+            references = []
+            for ref in reference:
+                if ref.get("unstructured", None) is not None:
+                    unique_reference = Article(title=ref.get("unstructured", None))
+                else:
+                    unique_reference = Article(
+                        authors=[ref.get("author", [])],
+                        year=ref.get("year", None),
+                        title=ref.get("article-title", None),
+                        journal=ref.get("journal-title", None),
+                        volume=ref.get("volume", None),
+                        issue=ref.get("issue", None),
+                        page=ref.get("page", None),
+                        doi=ref.get("DOI", None),
+                    )
+                references.append(unique_reference)
+
+            article = Article(
+                authors=authors,
+                year=publication_year,
+                title=title,
+                journal=journal,
+                volume=volume,
+                issue=issue,
+                page=page,
+                doi=doi,
+                times_cited=times_cited,
+                references=references,
+            )
+            articles.append(article)
+
+        return Collection(articles)

src/bibx/_entities/collection_builders/scopus_ris.py

@@ -177,7 +177,7 @@ def _article_from_record(cls, record: str) -> Article:
     @classmethod
     def _parse_file(cls, file: TextIO) -> Iterable[Article]:
         if not _size(file):
-            return []
+            yield from []
         for item in file.read().split("\n\n"):
             if item.isspace():
                 continue