feat(processors): processors of string type

acrawler/item.py

@@ -6,7 +6,7 @@
 
 from acrawler.exceptions import DropFieldError, SkipTaskImmediatelyError
 from acrawler.task import Task
-from acrawler.utils import to_asyncgen
+from acrawler.utils import to_asyncgen, partial
 from acrawler.processors import Processors
 
 _Function = Callable
@@ -396,6 +396,15 @@ def process(self, item):
         # Call field processors.
         for field, processors in self.field_processors.items():
             for processor in processors:
+                if isinstance(processor, str):
+                    li = processor.split(":", 1)
+                    func_name = li[0]
+                    args = li[1].split(",") if len(li) == 2 else []
+
+                    processor = partial(
+                        Processors.functions[func_name], *args, new_args_before=True
+                    )
+
                 self._on_field(field, processor)
 
     def _on_field(self, field, processor=lambda x: x, dest_field: str = None):

acrawler/utils.py

@@ -190,3 +190,19 @@ async def redis_push_start_urls_coro(
 def sync_coroutine(coro, loop=None):
     """Run a coroutine in synchronized way."""
     return (loop or asyncio.get_event_loop()).run_until_complete(coro)
+
+
+def partial(func, *args, new_args_before=False, **keywords):
+    def newfunc(*fargs, **fkeywords):
+        if new_args_before:
+            newkeywords = {**fkeywords, **keywords}
+            newargs = [*fargs, *args]
+        else:
+            newkeywords = {**keywords, **fkeywords}
+            newargs = [*args, *fargs]
+        return func(*newargs, **newkeywords)
+
+    newfunc.func = func
+    newfunc.args = args
+    newfunc.keywords = keywords
+    return newfunc