ENH: #2679 - DataFrame.to_html() urls_as_links parameter.

pandas/core/format.py

@@ -6,6 +6,7 @@
 
 from pandas.core.base import PandasObject
 from pandas.core.common import adjoin, notnull
+from pandas.io.common import _is_url
 from pandas.core.index import Index, MultiIndex, _ensure_index
 from pandas import compat
 from pandas.compat import(StringIO, lzip, range, map, zip, reduce, u,
@@ -307,7 +308,8 @@ def __init__(self, frame, buf=None, columns=None, col_space=None,
                  header=True, index=True, na_rep='NaN', formatters=None,
                  justify=None, float_format=None, sparsify=None,
                  index_names=True, line_width=None, max_rows=None,
-                 max_cols=None, show_dimensions=False, **kwds):
+                 max_cols=None, show_dimensions=False, urls_as_links=False,
+                 **kwds):
         self.frame = frame
         self.buf = buf if buf is not None else StringIO()
         self.show_index_names = index_names
@@ -329,6 +331,7 @@ def __init__(self, frame, buf=None, columns=None, col_space=None,
         self.max_rows_displayed = min(max_rows or len(self.frame),
                                       len(self.frame))
         self.show_dimensions = show_dimensions
+        self.urls_as_links = urls_as_links
 
         if justify is None:
             self.justify = get_option("display.colheader_justify")
@@ -821,6 +824,7 @@ def __init__(self, formatter, classes=None, max_rows=None, max_cols=None):
         self.max_rows = max_rows or len(self.fmt.frame)
         self.max_cols = max_cols or len(self.fmt.columns)
         self.show_dimensions = self.fmt.show_dimensions
+        self.urls_as_links = self.fmt.urls_as_links
         self.is_truncated = (self.max_rows < len(self.fmt.frame) or
                              self.max_cols < len(self.fmt.columns))
 
@@ -853,6 +857,11 @@ def _write_cell(self, s, kind='td', indent=0, tags=None):
         else:
             esc = {}
         rs = com.pprint_thing(s, escape_chars=esc).strip()
+        if self.urls_as_links and isinstance(s, compat.string_types):
+            s = s.strip()
+            if _is_url(s):
+                rs = '<a href="{url}">{escaped_url}</a>'.format(url=s,
+                                                                escaped_url=rs)
         self.write(
             '%s%s</%s>' % (start_tag, rs, kind), indent)
 

pandas/core/frame.py

@@ -1349,7 +1349,8 @@ def to_html(self, buf=None, columns=None, col_space=None, colSpace=None,
                 header=True, index=True, na_rep='NaN', formatters=None,
                 float_format=None, sparsify=None, index_names=True,
                 justify=None, bold_rows=True, classes=None, escape=True,
-                max_rows=None, max_cols=None, show_dimensions=False):
+                max_rows=None, max_cols=None, show_dimensions=False,
+                urls_as_links=False):
         """
         Render a DataFrame as an HTML table.
 
@@ -1367,6 +1368,8 @@ def to_html(self, buf=None, columns=None, col_space=None, colSpace=None,
         max_cols : int, optional
             Maximum number of columns to show before truncating. If None, show
             all.
+        urls_as_links : boolean, default False
+            Convert urls to HTML links.
 
         """
 
@@ -1387,7 +1390,8 @@ def to_html(self, buf=None, columns=None, col_space=None, colSpace=None,
                                            escape=escape,
                                            max_rows=max_rows,
                                            max_cols=max_cols,
-                                           show_dimensions=show_dimensions)
+                                           show_dimensions=show_dimensions,
+                                           urls_as_links=urls_as_links)
         formatter.to_html(classes=classes)
 
         if buf is None:

pandas/tests/test_format.py

@@ -731,6 +731,77 @@ def test_to_html_multiindex_sparsify_false_multi_sparse(self):
 </table>"""
             self.assertEqual(result, expected)
 
+    def test_to_html_with_hyperlinks(self):
+        data = [
+            {
+                'foo': 0,
+                'bar': 'http://pandas.pydata.org/',
+                None: 'pydata.org',
+            },
+            {
+                'foo': 0,
+                'bar': 'http://pandas.pydata.org/?q1=a&q2=b',
+                None: 'pydata.org',
+            },
+        ]
+        df = DataFrame(data, columns=['foo', 'bar', None],
+                       index=range(len(data)))
+
+        result_no_links = df.to_html()
+        result_with_links = df.to_html(urls_as_links=True)
+        expected_no_links = """\
+<table border="1" class="dataframe">
+  <thead>
+    <tr style="text-align: right;">
+      <th></th>
+      <th>foo</th>
+      <th>bar</th>
+      <th>None</th>
+    </tr>
+  </thead>
+  <tbody>
+    <tr>
+      <th>0</th>
+      <td>0</td>
+      <td>http://pandas.pydata.org/</td>
+      <td>pydata.org</td>
+    </tr>
+    <tr>
+      <th>1</th>
+      <td>0</td>
+      <td>http://pandas.pydata.org/?q1=a&amp;q2=b</td>
+      <td>pydata.org</td>
+    </tr>
+  </tbody>
+</table>"""
+        expected_with_links = """\
+<table border="1" class="dataframe">
+  <thead>
+    <tr style="text-align: right;">
+      <th></th>
+      <th>foo</th>
+      <th>bar</th>
+      <th>None</th>
+    </tr>
+  </thead>
+  <tbody>
+    <tr>
+      <th>0</th>
+      <td>0</td>
+      <td><a href="http://pandas.pydata.org/">http://pandas.pydata.org/</a></td>
+      <td>pydata.org</td>
+    </tr>
+    <tr>
+      <th>1</th>
+      <td>0</td>
+      <td><a href="http://pandas.pydata.org/?q1=a&q2=b">http://pandas.pydata.org/?q1=a&amp;q2=b</a></td>
+      <td>pydata.org</td>
+    </tr>
+  </tbody>
+</table>"""
+        self.assertEqual(result_with_links, expected_with_links)
+        self.assertEqual(result_no_links, expected_no_links)
+
     def test_to_html_multiindex_sparsify(self):
         index = MultiIndex.from_arrays([[0, 0, 1, 1], [0, 1, 0, 1]],
                                           names=['foo', None])