fix/improve various things

gallery_dl/extractor/danbooru.py

@@ -23,7 +23,7 @@ class DanbooruTagExtractor(DanbooruExtractor, booru.BooruTagExtractor):
     pattern = [(r"(?:https?://)?(?:www\.)?danbooru.donmai.us/posts"
                 r"\?(?:utf8=%E2%9C%93&)?tags=([^&]+)")]
     test = [("https://danbooru.donmai.us/posts?tags=bonocho", {
-        "url": "fb730af3f5e15650e5d924ffcda54b9ef232b89b",
+        "url": "f94774bcb5169e943efb4d7bb51c47ae786b05f3",
         "content": "b196fb9f1668109d7774a0a82efea3ffdda07746",
     })]
 

gallery_dl/job.py

@@ -53,16 +53,18 @@ class Job():
 
     def dispatch(self, msg):
         """Call the appropriate message handler"""
-        if msg[0] == Message.Url and self.pred_url:
+        if msg[0] == Message.Url:
-            self.update_kwdict(msg[2])
+            if self.pred_url:
-            self.handle_url(msg[1], msg[2])
+                self.update_kwdict(msg[2])
+                self.handle_url(msg[1], msg[2])
 
         elif msg[0] == Message.Directory:
             self.update_kwdict(msg[1])
             self.handle_directory(msg[1])
 
-        elif msg[0] == Message.Queue and self.pred_queue:
+        elif msg[0] == Message.Queue:
-            self.handle_queue(msg[1])
+            if self.pred_queue:
+                self.handle_queue(msg[1])
 
         elif msg[0] == Message.Headers:
             self.handle_headers(msg[1])

gallery_dl/text.py

@@ -15,15 +15,14 @@ import html
 import urllib.parse
 
 
-INVALID_XML_CHARS = [
+INVALID_XML_CHARS = (1, 2, 3, 4, 5, 6, 7, 8, 11, 12, 14, 15, 16, 17, 18,
-    chr(c) for c in (1, 2, 3, 4, 5, 6, 7, 8, 11, 12, 14, 15, 16, 17, 18,
                      19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31)
-]
 
 
 def clean_xml(xmldata, repl=""):
     """Replace/Remove invalid control characters in XML data"""
     for char in INVALID_XML_CHARS:
+        char = chr(char)
         if char in xmldata:
             xmldata = xmldata.replace(char, repl)
     return xmldata

scripts/create_test_data.py

@@ -38,11 +38,11 @@ def main():
 
     config.load()
     for url in urls:
-        hjob = job.HashJob(url, content=args.content)
+        tjob = job.TestJob(url, content=args.content)
-        hjob.run()
+        tjob.run()
-        print(hjob.extractor.__class__.__name__)
+        print(tjob.extractor.__class__.__name__)
-        print(TESTDATA_FMT.format(url, hjob.hash_url.hexdigest(),
+        print(TESTDATA_FMT.format(url, tjob.hash_url.hexdigest(),
-            hjob.hash_keyword.hexdigest(), hjob.hash_content.hexdigest()))
+            tjob.hash_keyword.hexdigest(), tjob.hash_content.hexdigest()))
 
 if __name__ == '__main__':
     main()