Added epub support

paper2remarkable/providers/_base.py

@@ -34,6 +34,8 @@
 class Provider(metaclass=abc.ABCMeta):
     """ABC for providers of pdf sources"""
 
+    SUPPORTED_FORMATS = ["pdf", "ps", "epub"]
+
     def __init__(
         self,
         verbose=False,
@@ -77,20 +79,40 @@ def __init__(
             logger.disable()
 
         # Define the operations to run on the pdf. Providers can add others.
-        self.operations = [("rewrite", self.rewrite_pdf)]
-        if crop == "center":
-            self.operations.append(("center", self.center_pdf))
-        elif crop == "right":
-            self.operations.append(("right", self.right_pdf))
-        elif crop == "left":
-            self.operations.append(("crop", self.crop_pdf))
+        self.operations = {format: [] for format in self.SUPPORTED_FORMATS}
+        self._configure_operations(crop, blank)
+        logger.info("Starting %s provider" % type(self).__name__)
 
-        if blank:
-            self.operations.append(("blank", blank_pdf))
+    def _configure_operations(self, crop, blank):
+        """Configure operations for PDF and PS formats"""
+        # Formats that need PDF processing
+        # No processing for epubs is assumed
+        pdf_formats = ["pdf", "ps"]
 
-        self.operations.append(("shrink", self.shrink_pdf))
+        def add_operation(formats, operation_name, operation_func):
+            for fmt in formats:
+                self.operations[fmt].append((operation_name, operation_func))
 
-        logger.info("Starting %s provider" % type(self).__name__)
+        # Base operations
+        add_operation(pdf_formats, "rewrite", self.rewrite_pdf)
+
+        # Crop operations mapping
+        crop_operations = {
+            "center": ("center", self.center_pdf),
+            "right": ("right", self.right_pdf),
+            "left": ("crop", self.crop_pdf),
+        }
+
+        # Add crop operation if specified
+        if crop in crop_operations:
+            add_operation(pdf_formats, *crop_operations[crop])
+
+        # Add blank operation if specified
+        if blank:
+            add_operation(pdf_formats, "blank", blank_pdf)
+
+        # PDF-specific shrink operation
+        add_operation(["pdf"], "shrink", self.shrink_pdf)
 
     @staticmethod
     @abc.abstractmethod
@@ -210,17 +232,24 @@ def run(self, src, filename=None):
 
         # generate nice filename if needed
         clean_filename = filename or self.informer.get_filename(abs_url)
-        tmp_filename = "paper.pdf"
+        extension = clean_filename.split(".")[-1]
+        tmp_filename = f"paper.{extension}"
+
+        if extension not in self.SUPPORTED_FORMATS:
+            raise ValueError(
+                f"Unsupported file format {extension}. Must be one of {self.SUPPORTED_FORMATS}"
+            )
 
         self.initial_dir = os.getcwd()
         with tempfile.TemporaryDirectory(prefix="p2r_") as working_dir:
             with chdir(working_dir):
                 self.retrieve_pdf(pdf_url, tmp_filename)
 
-                assert_file_is_pdf(tmp_filename)
+                if extension in "pdf ps".split():
+                    assert_file_is_pdf(tmp_filename)
 
                 intermediate_fname = tmp_filename
-                for opname, op in self.operations:
+                for opname, op in self.operations[extension]:
                     intermediate_fname = op(intermediate_fname)
 
                 shutil.copy(intermediate_fname, clean_filename)

paper2remarkable/providers/arxiv.py

@@ -40,7 +40,9 @@ def __init__(self, *args, **kwargs):
         self.informer = ArxivInformer()
 
         # register the dearxiv operation
-        self.operations.insert(0, ("dearxiv", self.dearxiv))
+        for format in self.operations:
+            if format in "pdf ps".split():
+                self.operations[format].insert(0, ("dearxiv", self.dearxiv))
 
     def get_abs_pdf_urls(self, url):
         """Get the pdf and abs url from any given arXiv url"""

paper2remarkable/providers/pdf_url.py

@@ -33,11 +33,12 @@ def get_filename(self, abs_url):
             )
 
         filename = path_parts[-1]
-        if not filename.endswith(".pdf"):
+        ext = filename.split(".")[-1]
+        if ext not in [".pdf", "epub"]:
             raise FilenameMissingError(
                 provider="PdfUrl",
                 url=abs_url,
-                reason="URL path didn't end in .pdf",
+                reason="URL path didn't end in .pdf or .epub",
             )
         logger.warning(
             "Using filename {filename} extracted from url. "

tests/test_providers.py

@@ -193,6 +193,13 @@ def test_pdfurl_2(self):
         filename = prov.run(url)
         self.assertEqual("NoREC.pdf", os.path.basename(filename))
 
+    def test_epub(self):
+        prov = PdfUrl(upload=False, verbose=VERBOSE)
+        url = "https://www.gutenberg.org/ebooks/2701.epub.images"
+        filename = prov.run(url)
+        exp = "pg2701-images.epub"
+        self.assertEqual(exp, os.path.basename(filename))
+
     def test_jmlr_1(self):
         prov = JMLR(upload=False, verbose=VERBOSE)
         url = "http://www.jmlr.org/papers/volume17/14-526/14-526.pdf"