Feature/urls

dosagelib/cmd.py

@@ -115,7 +115,7 @@ def setup_options(console: console.Console) -> ArgumentParser:
     parser.add_argument('--list-all', action='store_true',
         help=argparse.SUPPRESS)
     comic_arg = parser.add_argument('comic', nargs='*',
-        help='comic module name (including case insensitive substrings)')
+        help='comic module name (including case insensitive substrings).  Also accepts URLs on certain websites (ComicFury, WebToons).')
     comic_arg.completer = scraper_completion
     with contextlib.suppress(ImportError):
         completers = importlib.import_module('argcomplete.completers')

dosagelib/director.py

@@ -210,13 +210,17 @@ def getScrapers(comics: Collection[str], basepath: str, adult=True, listing=Fals
                 # make the following command work:
                 # find Comics -type d | xargs -n1 -P10 dosage -b Comics
                 comic = comic[len(basepath) + 1:].lstrip(os.sep)
-            if ':' in comic:
-                name, index = comic.split(':', 1)
-                indexes = index.split(',')
+            if comic.startswith("http:") or comic.startswith("https:"):
+              scraper = scrapercache.findbyurl(comic)
+              indexes = None
             else:
-                name = comic
-                indexes = None
-            scraper = scrapercache.find(name)
+              if ':' in comic:
+                  name, index = comic.split(':', 1)
+                  indexes = index.split(',')
+              else:
+                  name = comic
+                  indexes = None
+              scraper = scrapercache.find(name)
             if shouldRunScraper(scraper, adult, listing):
                 # FIXME: Find a better way to work with indexes
                 scraper.indexes = indexes

dosagelib/plugins/comicfury.py

@@ -88,6 +88,26 @@ def shouldSkipUrl(self, url, data):
         return (self.match(data, '//div[@id="comicimagewrap"]//video') and
             not self.match(data, '//div[@id="comicimagewrap"]//img'))
 
+    @classmethod
+    def handleurl(cls, url) -> list[ParserScraper]:
+        import re
+        rs = [
+            r"^http.*comicfury\.com/read/([^/]+)/?.*",
+            r"^http.*://(.+?)\.thecomicseries\.com/?.*",
+            r"^http.*://(.+?)\.the-comic\.org/?.*",
+            r"^http.*://(.+?)\.thecomicstrip\.org/?.*",
+            r"^http.*://(.+?)\.cfw\.me/?.*",
+            r"^http.*://(.+?)\.webcomic\.ws/?.*"
+        ]
+        for r in rs:
+            m = re.match(r, url.lower())
+            if m != None:
+                name = m.group(1)
+                ps = cls(name, name)
+                ps.multipleImagesPerStrip = True
+                return [ps]
+        return []
+
     @classmethod
     def getmodules(cls):
         return (

dosagelib/plugins/webtoons.py

@@ -47,6 +47,16 @@ def namer(self, imageUrl, pageUrl):
         imageExt = pageUrl.rsplit('.', 1)[-1].split('?', 1)[0]
         return "%s-%03d.%s" % (episodeNum, imageNum, imageExt)
 
+    @classmethod
+    def handleurl(cls, url) -> list[ParserScraper]:
+        import re
+        m = re.match(r"^http.*webtoons\.com/.+?/(.+?/.+?)/.+title_no=(\d+)", url.lower())
+        if m != None:
+            path = m.group(1)
+            number = m.group(2)
+            return [cls(path, path, number)]
+        return []
+
     @classmethod
     def getmodules(cls):
         return (

dosagelib/scraper.py

@@ -54,6 +54,7 @@ class Scraper:
     # Stop search for previous URLs at this URL
     firstStripUrl: Optional[str] = None
 
+    #THINK Is there harm in defaulting this to True?
     # if more than one image per URL is expected
     multipleImagesPerStrip: bool = False
 
@@ -95,6 +96,10 @@ class Scraper:
     # HTTP session for configuration & cookies
     session: http.Session = http.default_session
 
+    @classmethod
+    def handleurl(cls, url) -> list[Scraper]:
+        return []
+
     @classmethod
     def getmodules(cls) -> Collection[Scraper]:
         if cls.url is None:
@@ -537,6 +542,7 @@ class Cache:
     """
     def __init__(self) -> None:
         self.data: List[Scraper] = []
+        self.plugins: List[Scraper] = []
         self.userdirs: set[pathlib.Path] = set()
 
     def find(self, comic: str) -> Scraper:
@@ -547,6 +553,7 @@ def find(self, comic: str) -> Scraper:
         if not comic:
             raise ValueError("empty comic name")
         candidates = []
+
         cname = comic.lower()
         for scraper in self.all(include_removed=True):
             lname = scraper.name.lower()
@@ -600,6 +607,7 @@ def addmodule(self, module) -> int:
         classes = 0
         for plugin in loader.get_module_plugins(module, Scraper):
             classes += 1
+            self.plugins.append(plugin)
             self.data.extend(plugin.getmodules())
         return classes
 
@@ -615,6 +623,18 @@ def all(self, include_removed=False) -> list[Scraper]:
         else:
             return [x for x in self.data if x.url]
 
+    def findbyurl(self, url) -> list[Scraper]:
+        candidates = []
+        for plugin in self.plugins:
+            candidates.extend(plugin.handleurl(url))
+
+        if len(candidates) > 1:
+            comics = ", ".join(x.name for x in candidates)
+            raise ValueError('multiple comics found: %s' % comics)
+        elif not candidates:
+            raise ValueError('comic %r not found' % comic)
+        return candidates[0]
+
     def validate(self) -> None:
         """Check for duplicate scraper names."""
         d: Dict[str, Scraper] = {}