handles cases where multiple nodes are returned by the XPath (such as…

… <article>)

trafilatura/core.py

@@ -14,7 +14,7 @@
 from copy import deepcopy
 
 from lxml.etree import Element, SubElement, strip_elements, strip_tags
-from lxml.html import tostring
+from lxml.html import tostring, Element as HtmlElement
 
 # own
 from .external import (SANITIZED_XPATH, justext_rescue, sanitize_tree,
@@ -545,7 +545,16 @@ def extract_content(tree, options):
     for expr in BODY_XPATH:
         # select tree if the expression has been found
         try:
-            subtree = tree.xpath(expr)[0]
+            subtrees = tree.xpath(expr)
+            if len(subtrees) > 1 and options.recall is True:
+                new_subtree = HtmlElement(subtrees[0].tag)
+                for _subtree in subtrees:
+                    for child in _subtree:
+                        # if len(' '.join(child.itertext()).strip()) > MIN_EXTRACTED_SIZE ?
+                        new_subtree.append(child)
+                subtree = new_subtree
+            else:
+                subtree = subtrees[0]
         except IndexError:
             continue
         # prune the subtree

trafilatura/xpaths.py

@@ -25,7 +25,7 @@
     contains(@id, "body-text") or contains(@class, "body-text") or
     contains(@class, "article__container") or contains(@id, "art-content") or contains(@class, "art-content")][1]''',
     # (…)[1] = first occurrence
-    '(.//article)[1]',
+    '(.//article)',
     """(.//*[(self::article or self::div or self::main or self::section)][
     contains(@class, 'post-bodycopy') or
     contains(@class, 'storycontent') or contains(@class, 'story-content') or