From a7c1174c60b6207bcaabe9a19e1c751edbdcd817 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Mika=C3=ABl=20Capelle?= <capelle.mikael@gmail.com>
Date: Sun, 14 Apr 2024 13:35:04 +0200
Subject: [PATCH] Update command line.

---
 src/holt59/scans/__main__.py | 39 +++++++++++++++++++++++++-----------
 src/holt59/scans/lelscans.py | 12 +++++++++--
 2 files changed, 37 insertions(+), 14 deletions(-)

diff --git a/src/holt59/scans/__main__.py b/src/holt59/scans/__main__.py
index 9fa97ec..a40a32f 100644
--- a/src/holt59/scans/__main__.py
+++ b/src/holt59/scans/__main__.py
@@ -9,13 +9,6 @@ from .scans import Chapter, Manga, ScanFetcher
 _MangaT = TypeVar("_MangaT", bound=Manga)
 _ChapterT = TypeVar("_ChapterT", bound=Chapter)
 
-# List of scan numbers to ignore
-IGNORE_NUMBERS: dict[str, set[str]] = {
-    "One Piece": {str(i) for i in range(910 + 1)},
-    "Solo Leveling": set(),
-    "Hunter X Hunter": {str(i) for i in range(390 + 1)} | {"357.1"},
-}
-
 
 def list_mangas(fetcher: ScanFetcher[_MangaT, _ChapterT]):
     for manga in fetcher.list_mangas():
@@ -27,11 +20,16 @@ def list_chapters(fetcher: ScanFetcher[_MangaT, _ChapterT], name: str):
     assert manga is not None
 
     chapters = fetcher.list_chapters(manga)
-    for chapter in chapters:
-        print(chapter)
+    print(
+        "Found {} chapters for {}: {}".format(
+            len(chapters), name, ", ".join(chapter.number for chapter in chapters)
+        )
+    )
 
 
-def fetch_chapters(fetcher: ScanFetcher[_MangaT, _ChapterT], name: str, folder: Path):
+def fetch_chapters(
+    fetcher: ScanFetcher[_MangaT, _ChapterT], name: str, folder: Path, ignore: set[str]
+):
     manga = fetcher.find_manga(name)
     assert manga is not None
 
@@ -47,7 +45,7 @@ def fetch_chapters(fetcher: ScanFetcher[_MangaT, _ChapterT], name: str, folder:
         number = chapter.number
 
         # ignore the number
-        if number in IGNORE_NUMBERS.get(name, set()):
+        if number in ignore:
             continue
 
         pdf = folder.joinpath("ops_{}.pdf".format(number))
@@ -62,6 +60,21 @@ def fetch_chapters(fetcher: ScanFetcher[_MangaT, _ChapterT], name: str, folder:
             )
 
 
+def parse_ignore(value: str) -> set[str]:
+    ignore: set[str] = set()
+
+    for part in value.split(","):
+        part = part.strip()
+        try:
+            start, end = (int(p) for p in part.split("-"))
+            for number in range(start, end + 1):
+                ignore.add(str(number))
+        except ValueError:
+            ignore.add(part)
+
+    return ignore
+
+
 def main() -> None:
     parser = argparse.ArgumentParser("Manga Scan Fetcher")
     parser.add_argument(
@@ -70,6 +83,7 @@ def main() -> None:
     sub_parsers = parser.add_subparsers(dest="command")
 
     fetch_parser = sub_parsers.add_parser("fetch")
+    fetch_parser.add_argument("-i", "--ignore", type=str, required=False, default="")
     fetch_parser.add_argument("-o", "--output", type=Path, required=False, default=None)
     fetch_parser.add_argument("manga", type=str)
 
@@ -99,11 +113,12 @@ def main() -> None:
         case "fetch":
             manga = args.manga
             folder: Path | None = args.output
+            ignore: str = args.ignore
             if folder is None:
                 folder = Path("scans", manga)
             folder.mkdir(exist_ok=True)
 
-            fetch_chapters(fetcher, manga, folder)
+            fetch_chapters(fetcher, manga, folder, parse_ignore(ignore))
 
 
 if __name__ == "__main__":
diff --git a/src/holt59/scans/lelscans.py b/src/holt59/scans/lelscans.py
index cf2f946..04c7b7d 100644
--- a/src/holt59/scans/lelscans.py
+++ b/src/holt59/scans/lelscans.py
@@ -2,6 +2,7 @@
 
 import logging
 import tempfile
+import urllib.error
 import urllib.request
 from dataclasses import dataclass
 from multiprocessing.pool import ThreadPool
@@ -41,7 +42,6 @@ class LelScansChapter(Chapter):
 class LelScansFetcher(ScanFetcher[LelScansManga, LelScansChapter]):
     def _request(self, url: str) -> bytes | str:
         request = urllib.request.Request(url=url, headers=_REQUEST_HEADERS)
-
         return cast(bytes | str, urllib.request.urlopen(request).read())
 
     def list_mangas(self) -> list[LelScansManga]:
@@ -110,7 +110,15 @@ class LelScansFetcher(ScanFetcher[LelScansManga, LelScansChapter]):
                 .attrs["src"]
                 .strip()
             )
-            data = self._request(url)
+            try:
+                data = self._request(url)
+            except urllib.error.HTTPError:
+                LOGGER.warning(
+                    "    Failed to retrieve page {:02}/{:02d} from {}.".format(
+                        number, len(pages), url
+                    )
+                )
+                return None
 
             filepath = folder.joinpath(url.split("/")[-1].split("?")[0])
             with open(filepath, "wb") as fp: