use lxml instead of bs4

Author: 0x0L

pandas_datareader/data.py

@@ -595,15 +595,18 @@ def get_datasets_famafrench():
     -------
     A list of valid inputs for get_data_famafrench.
     """
-    from bs4 import BeautifulSoup
+    try:
+        from lxml.html import parse
+    except ImportError:
+        raise ImportError("Please install lxml if you want to use the "
+                          "get_datasets_famafrench function")
 
-    with urlopen(_FAMAFRENCH_URL + 'data_library.html') as socket:
-        root = BeautifulSoup(socket.read(), 'html.parser')
+    root = parse(_FAMAFRENCH_URL + 'data_library.html')
 
     l = filter(lambda x: x.startswith(_FF_PREFIX) and x.endswith(_FF_SUFFIX),
-               [e.attrs['href'] for e in root.findAll('a') if 'href' in e.attrs])
+               [e.attrib['href'] for e in root.findall('.//a') if 'href' in e.attrib])
 
-    return list(map(lambda x: x[len(_FF_PREFIX):-len(_FF_SUFFIX)], l))
+    return lmap(lambda x: x[len(_FF_PREFIX):-len(_FF_SUFFIX)], l)
 
 
 def _download_data_famafrench(name):
@@ -621,7 +624,6 @@ def _download_data_famafrench(name):
 
 
 def _parse_date_famafrench(x):
-    # what's the correct python way to do that ??
     x = x.strip()
     try: return dt.datetime.strptime(x, '%Y')
     except: pass

pandas_datareader/tests/test_famafrench.py

@@ -3,12 +3,6 @@
 
 import pandas_datareader.data as web
 
-def _skip_if_no_bs4():
-    try:
-        import bs4
-    except ImportError:
-        raise nose.SkipTest('no bs4')
-
 
 class TestFamaFrench(tm.TestCase):
     def test_read_famafrench(self):
@@ -23,7 +17,7 @@ def test_read_famafrench(self):
             assert len(ff) > 1
 
     def test_get_datasets(self):
-        _skip_if_no_bs4()
+        # _skip_if_no_lxml()
         l = web.get_datasets_famafrench()
         assert len(l) > 100