允许指定 title_xpath

GeneralNewsExtractor · Sep 22, 2019 · 00bc70c · 00bc70c
1 parent b02841f
commit 00bc70c
Showing 1 changed file with 2 additions and 2 deletions.
diff --git a/gne/__init__.py b/gne/__init__.py
@@ -9,11 +9,11 @@ def __init__(self):
         self.author_extractor = AuthorExtractor()
         self.time_extractor = TimeExtractor()
 
-    def extract(self, html, noise_node_list=None):
+    def extract(self, html, title_xpath='', noise_node_list=None):
         element = pre_parse(html)
         remove_noise_node(element, noise_node_list)
         content = self.content_extractor.extract(element)
-        title = self.title_extractor.extract(element)
+        title = self.title_extractor.extract(element, title_xpath=title_xpath)
         publish_time = self.time_extractor.extractor(element)
         author = self.author_extractor.extractor(element)
         return {'title': title,