Add summary_with_score.

5 years ago · fdb2ebe3d7
parent b21235d0a0
commit fdb2ebe3d7
2 changed files with 21 additions and 1 deletions
--- a/README.rst
+++ b/README.rst
@ -33,11 +33,18 @@ Usage
    'Example Domain'
    
    >>> doc.summary()
+    u'<html><body><div><body id="readabilityBody">\n<div>\n    <h1>Example Domain</h1>\n
+    <p>This domain is established to be used for illustrative examples in documents. You may
+    use this\n    domain in examples without prior coordination or asking for permission.</p>
+    \n    <p><a href="http://www.iana.org/domains/example">More information...</a></p>\n</div>
+    \n</body>\n</div></body></html>'
+
+    >>> doc.summary_with_score()
    (u'<html><body><div><body id="readabilityBody">\n<div>\n    <h1>Example Domain</h1>\n
    <p>This domain is established to be used for illustrative examples in documents. You may
    use this\n    domain in examples without prior coordination or asking for permission.</p>
    \n    <p><a href="http://www.iana.org/domains/example">More information...</a></p>\n</div>
-    \n</body>\n</div></body></html>', 31.43)
+    \n</body>\n</div></body></html>', 24.293830845771144)

 Change Log
 ----------
--- a/readability/readability.py
+++ b/readability/readability.py
@ -180,6 +180,19 @@ class Document:
        :param html_partial: return only the div of the document, don't wrap
        in html and body tags.

+        Warning: It mutates internal DOM representation of the HTML document,
+        so it is better to call other API methods before this one.
+        """
+        article, _ = self.summary_with_score(html_partial)
+        return article
+
+    def summary_with_score(self, html_partial=False):
+        """
+        Given a HTML file, extracts the text of the article with score.
+
+        :param html_partial: return only the div of the document, don't wrap
+        in html and body tags.
+
        Warning: It mutates internal DOM representation of the HTML document,
        so it is better to call other API methods before this one.
        """