update changelog/docs etc for new metadata feature

CHANGELOG.md

@@ -9,7 +9,7 @@ to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
 - Add support for more sites
 
-## [2.2.21] - 2023-02-11
+## [2.3.0] - 2023-02-11
 
 ### Added
 

MANIFEST.in

@@ -4,7 +4,10 @@ include *.properties
 include *.py
 include *.txt
 include *.yml
+include *.xml
 recursive-include contrib *.py
 recursive-include mangadlp *.py
+recursive-include mangadlp *.xml
 recursive-include tests *.py
+recursive-include tests *.xml
 recursive-include tests *.txt

README.md

@@ -117,6 +117,7 @@ verbosity: [mutually_exclusive]
 --hook-chapter-pre TEXT         Commands to execute before the chapter download starts
 --hook-chapter-post TEXT        Commands to execute after the chapter download finished
 --cache-path PATH               Where to store the cache-db. If no path is given, cache is disabled
+--add-metadata / --no-metadata  Enable/disable creation of metadata via ComicInfo.xml  [default: add-metadata]
 ```
 
 ## Contribution / Bugs

contrib/api_template.py

@@ -1,4 +1,5 @@
 # api template for manga-dlp
+from typing import Any
 
 
 class YourAPI:
@@ -97,21 +98,60 @@ class YourAPI:
                 The metadata as a dict
             """
 
-            # metadata types. have to be correct to be valid
+            # metadata types. have to be valid
+            # {key: (type, default value, valid values)}
             {
-                "Title": str,
-                "Series": str,
-                "Number": str,
-                "Count": int,
-                "Volume": int,
-                "Summary": str,
-                "Genre": str,
-                "Web": str,
-                "PageCount": int,
-                "LanguageISO": str,
-                "Format": str,
-                "ScanInformation": str,
-                "SeriesGroup": str,
+                "Title": (str, None, []),
+                "Series": (str, None, []),
+                "Number": (str, None, []),
+                "Count": (int, None, []),
+                "Volume": (int, None, []),
+                "AlternateSeries": (str, None, []),
+                "AlternateNumber": (str, None, []),
+                "AlternateCount": (int, None, []),
+                "Summary": (str, None, []),
+                "Notes": (
+                    str,
+                    "Downloaded with https://github.com/olofvndrhr/manga-dlp",
+                    [],
+                ),
+                "Year": (int, None, []),
+                "Month": (int, None, []),
+                "Day": (int, None, []),
+                "Writer": (str, None, []),
+                "Colorist": (str, None, []),
+                "Publisher": (str, None, []),
+                "Genre": (str, None, []),
+                "Web": (str, None, []),
+                "PageCount": (int, None, []),
+                "LanguageISO": (str, None, []),
+                "Format": (str, None, []),
+                "BlackAndWhite": (str, None, ["Yes", "No", "Unknown"]),
+                "Manga": (str, "Yes", ["Yes", "No", "Unknown", "YesAndRightToLeft"]),
+                "ScanInformation": (str, None, []),
+                "SeriesGroup": (str, None, []),
+                "AgeRating": (
+                    str,
+                    None,
+                    [
+                        "Unknown",
+                        "Adults Only 18+",
+                        "Early Childhood",
+                        "Everyone",
+                        "Everyone 10+",
+                        "G",
+                        "Kids to Adults",
+                        "M",
+                        "MA15+",
+                        "Mature 17+",
+                        "PG",
+                        "R18+",
+                        "Rating Pending",
+                        "Teen",
+                        "X18+",
+                    ],
+                ),
+                "CommunityRating": (int, None, [1, 2, 3, 4, 5]),
             }
 
             # example

docs/pages/download.md

@@ -7,6 +7,10 @@
 └── <download path>/
     └── <manga title>/
         └── <chapter title>/
+            └── ComicInfo.xml (optional)
+            └── 001.png
+            └── 002.png
+            └── etc.
 ```
 
 **Example:**
@@ -167,3 +171,12 @@ chapters will be
 tracked there, and the script doesn't have to check on disk if you already downloaded it.
 
 If the option is unset (default), then no caching will be done.
+
+## Add metadata
+
+manga-dlp supports the creation of metadata files in the downloaded chapter.
+The metadata is based on the newer [ComicRack/Anansi](https://anansi-project.github.io/docs/introduction) standard.
+The default option is to add the metadata in the folder/archive with the name `ComicInfo.xml`.
+If you don't want metadata, you can pass the `--no-metadata` flag.
+
+> pdf format does not support metadata at the moment

docs/pages/index.md

@@ -115,6 +115,7 @@ verbosity: [mutually_exclusive]
 --hook-chapter-pre TEXT         Commands to execute before the chapter download starts
 --hook-chapter-post TEXT        Commands to execute after the chapter download finished
 --cache-path PATH               Where to store the cache-db. If no path is given, cache is disabled
+--add-metadata / --no-metadata  Enable/disable creation of metadata via ComicInfo.xml  [default: add-metadata]
 ```
 
 ## Contribution / Bugs

mangadlp/__about__.py

@@ -1 +1 @@
-__version__ = "2.2.21"
+__version__ = "2.3.0"

mangadlp/metadata.py

@@ -4,8 +4,10 @@ from typing import Any
 import xmltodict
 from loguru import logger as log
 
+METADATA_FILENAME = "ComicInfo.xml"
 METADATA_TEMPLATE = Path("mangadlp/metadata/ComicInfo_v2.0.xml")
-# define metadata types and valid values. an empty list means no value check
+# define metadata types, defaults and valid values. an empty list means no value check
+# {key: (type, default value, valid values)}
 METADATA_TYPES: dict[str, tuple[type, Any, list]] = {
     "Title": (str, None, []),
     "Series": (str, None, []),
@@ -105,7 +107,7 @@ def write_metadata(chapter_path: Path, metadata: dict) -> None:
         log.warning("Can't add metadata for pdf format. Skipping")
         return
 
-    metadata_file = chapter_path / "ComicInfo.xml"
+    metadata_file = chapter_path / METADATA_FILENAME
 
     log.debug(f"Metadata items: {metadata}")
     metadata_valid = validate_metadata(metadata)

pyproject.toml

@@ -30,6 +30,7 @@ dependencies = [
     "loguru>=0.6.0",
     "click>=8.1.3",
     "click-option-group>=0.5.5",
+    "xmltodict>=0.13.0"
 ]
 
 [project.urls]
@@ -60,6 +61,8 @@ dependencies = [
     "loguru>=0.6.0",
     "click>=8.1.3",
     "click-option-group>=0.5.5",
+    "xmltodict>=0.13.0",
+    "xmlschema>=2.2.1",
     "img2pdf>=0.4.4",
     "hatch>=1.6.0",
     "hatchling>=1.11.0",