read_fwf with urlopen test GH#26376 (#52233)

Signed-off-by: Liang Yan <ckgppl_yan@sina.cn>

Author: liang3zy22

pandas/_testing/_io.py

@@ -271,7 +271,10 @@ def can_connect(url, error_classes=None) -> bool:
     try:
         with urlopen(url, timeout=20) as response:
             # Timeout just in case rate-limiting is applied
-            if response.status != 200:
+            if (
+                response.info().get("Content-type") == "text/html"
+                and response.status != 200
+            ):
                 return False
     except error_classes:
         return False

pandas/tests/io/parser/test_read_fwf.py

@@ -28,6 +28,7 @@
 )
 from pandas.tests.io.test_compression import _compression_to_extension
 
+from pandas.io.common import urlopen
 from pandas.io.parsers import (
     read_csv,
     read_fwf,
@@ -1010,3 +1011,50 @@ def test_invalid_dtype_backend():
     )
     with pytest.raises(ValueError, match=msg):
         read_fwf("test", dtype_backend="numpy")
+
+
+@pytest.mark.network
+@tm.network(
+    url="ftp://ftp.ncdc.noaa.gov/pub/data/igra/igra2-station-list.txt",
+    check_before_test=True,
+)
+def test_url_urlopen():
+    expected = pd.Index(
+        [
+            "CC",
+            "Network",
+            "Code",
+            "StationId",
+            "Latitude",
+            "Longitude",
+            "Elev",
+            "dummy",
+            "StationName",
+            "From",
+            "To",
+            "Nrec",
+        ],
+        dtype="object",
+    )
+    url = "ftp://ftp.ncdc.noaa.gov/pub/data/igra/igra2-station-list.txt"
+    with urlopen(url) as f:
+        result = read_fwf(
+            f,
+            widths=(2, 1, 3, 5, 9, 10, 7, 4, 30, 5, 5, 7),
+            names=(
+                "CC",
+                "Network",
+                "Code",
+                "StationId",
+                "Latitude",
+                "Longitude",
+                "Elev",
+                "dummy",
+                "StationName",
+                "From",
+                "To",
+                "Nrec",
+            ),
+        ).columns
+
+    tm.assert_index_equal(result, expected)