/ src / python / txtai / workflow / task / url.py
url.py
 1  """
 2  UrlTask module
 3  """
 4  
 5  import re
 6  
 7  from .base import Task
 8  
 9  
10  class UrlTask(Task):
11      """
12      Task that processes urls
13      """
14  
15      # URL prefix
16      PREFIX = r"\w+:\/\/"
17  
18      def accept(self, element):
19          # Only accept elements that start with a url prefix
20          return super().accept(element) and re.match(UrlTask.PREFIX, element.lower())