Add option to specifie extractor

2 files changed, 25 insertions, 5 deletions

diff --git a/extractors/common.py b/extractors/common.py
index db8f5c1..da3e59c 100644
--- a/extractors/common.py
+++ b/extractors/common.py
@@ -1,4 +1,5 @@
 import os
+import re
 from pathlib import Path
 from sh import youtube_dl
 from utils import read_file, write_file
@@ -7,7 +8,13 @@ from utils import read_file, write_file
 class Extractor():
 
     def __init__(self, reg, url):
-        self.root = reg.group(1)
+        self.root = None
+        if not reg:
+            r = re.search(r'(^http(?:s|):(?:\/\/.*?\/|\/\/.*))', url)
+            if r:
+                self.root = r.group(1)
+        if not self.root:
+            self.root = reg.group(1)
         self._albums = []
         self.root_path = self._root_path()
         self._update_cache(self.root)
@@ -26,7 +33,7 @@ class Extractor():
         for url in urls_cache:
             if url.startswith(self.root):
                 return
-        write_file(cache_file, self.root)
+        write_file(cache_file, self.root + "," + self.__class__.__name__)
 
     def _yt_wrapper(self, url, output):
         for line in youtube_dl(
diff --git a/extractors/job.py b/extractors/job.py
index 596a3ae..795617a 100644
--- a/extractors/job.py
+++ b/extractors/job.py
@@ -3,6 +3,8 @@ import re
 import importlib
 import sys
 
+from utils import NoExtractorException
+
 extrs = [
     'bandcamp'
 ]
@@ -10,12 +12,16 @@ extrs = [
 
 class DlJob():
 
-    def __init__(self, url, output):
-        self.extr = self._find(url)
+    def __init__(self, url, output, extractor=None):
+        if extractor in extrs:
+            cls = self._get_class(extractor)
+            self.extr = cls(reg=None, url=url)
+        else:
+            self.extr = self._find(url)
         self.output = output
         self._albums = []
         if not self.extr:
-            logging.error("No extractor found for " + url + ".")
+            raise NoExtractorException("No extractor found for " + url + ".")
 
     def _find(self, url):
         for cls in self._list_extractors():
@@ -41,6 +47,13 @@ class DlJob():
             )
         ]
 
+    def _get_class(self, extractor):
+        module = importlib.import_module('.' + extractor, __package__)
+        classes = self._get_classes(module)
+        for cls in classes:
+            if cls.__name__ == extractor:
+                return cls
+
     def run(self):
         self.extr.get_albums()
         self.extr.download_albums(self.output)