Create broken-linkcheck.yml

.github/workflows/broken-linkcheck.yml

@@ -0,0 +1,37 @@
+name: Linkcheck
+on:
+    schedule:
+    # Run monthly on the 1st day of the month
+        - cron: '0 0 1 * *'
+    pull_request:
+      paths:
+        - ".github/workflows/broken-linkcheck.yml"
+        - "doc/make.py"
+jobs:
+    linkcheck:
+        runs-on: ubuntu-latest
+        defaults:
+          run:
+            shell: bash -el {0}
+
+        steps:
+        - name: Checkout
+          uses: actions/checkout@v4
+          with:
+            fetch-depth: 0
+
+        - name: Set up Conda
+          uses: ./.github/actions/setup-conda
+
+        - name: Build Pandas
+          uses: ./.github/actions/build_pandas
+        - name: Run linkcheck script
+          working-directory: ./doc
+          run: |
+            set -o pipefail
+            python make.py linkcheck | tee linkcheck.txt
+
+        - name: Display broken links
+          if: failure()
+          working-directory: ./doc
+          run: grep broken linkcheck.txt

doc/source/conf.py

@@ -14,6 +14,7 @@
 import inspect
 import logging
 import os
+import re
 import sys
 import warnings
 
@@ -798,3 +799,52 @@ def setup(app):
     app.add_autodocumenter(AccessorMethodDocumenter)
     app.add_autodocumenter(AccessorCallableDocumenter)
     app.add_directive("autosummary", PandasAutosummary)
+
+
+# Ignore list for broken links,found in CI run checks for broken-linkcheck.yml
+
+links = [
+    "^http://$",
+    "^https://$",
+    "http://scatterci.github.io/pydata/pandas",
+    "http://specs.frictionlessdata.io/json-table-schema/",
+    "https://cloud.google.com/bigquery/docs/access-control#roles",
+    "https://cloud.google.com/bigquery/docs/reference/rest/v2/jobs#configuration.query",
+    "https://crates.io/crates/calamine",
+    "https://devguide.python.org/setup/#macos",
+    "https://en.wikipedia.org/wiki/Imputation_statistics",
+    "https://en.wikipedia.org/wiki/Imputation_(statistics",
+    "https://github.com/noatamir/pandas-dev",
+    "https://github.com/pandas-dev/pandas/blob/main/pandas/plotting/__init__.py#L1",
+    "https://github.com/pandas-dev/pandas/blob/v0.20.2/pandas/core/generic.py#L568",
+    "https://github.com/pandas-dev/pandas/blob/v0.20.2/pandas/core/frame.py#L1495",
+    "https://github.com/pandas-dev/pandas/issues/174151",
+    "https://gitpod.io/#https://github.com/USERNAME/pandas",
+    "https://manishamde.github.io/blog/2013/03/07/pandas-and-python-top-10/",
+    "https://matplotlib.org/api/axes_api.html#matplotlib.axes.Axes.table",
+    "https://nipunbatra.github.io/blog/visualisation/2013/05/01/aggregation-timeseries.html",
+    "https://nbviewer.ipython.org/gist/metakermit/5720498",
+    "https://numpy.org/doc/stable/user/basics.byteswapping.html",
+    "https://pandas-gbq.readthedocs.io/en/latest/changelog.html#changelog-0-8-0",
+    "https://pandas.pydata.org/pandas-docs/stable/io.html#io-chunking",
+    "https://pandas.pydata.org/pandas-docs/stable/ecosystem.html",
+    "https://sqlalchemy.readthedocs.io/en/latest/dialects/index.html",
+    "https://support.sas.com/documentation/cdl/en/lrdict/64316/HTML/default/viewer.htm#a000245912.htm",
+    "https://support.sas.com/documentation/cdl/en/lrdict/64316/HTML/default/viewer.htm#a000214639.htm",
+    "https://support.sas.com/documentation/cdl/en/lrdict/64316/HTML/default/viewer.htm#a002283942.htm",
+    "https://support.sas.com/documentation/cdl/en/lrdict/64316/HTML/default/viewer.htm#a000245965.htm",
+    "https://support.sas.com/documentation/cdl/en/imlug/66845/HTML/default/viewer.htm#imlug_langref_sect455.htm",
+    "https://support.sas.com/documentation/cdl/en/lrdict/64316/HTML/default/viewer.htm#a002284668.htm",
+    "https://support.sas.com/documentation/cdl/en/lrdict/64316/HTML/default/viewer.htm#a002978282.htm",
+    "https://wesmckinney.com/blog/update-on-upcoming-pandas-v0-10-new-file-parser-other-performance-wins/",
+    "pandas.zip",
+]
+
+# Exclude specific links from the links list
+
+excluded_links = ["^http://$", "^https://$"]
+filtered_links = [link for link in links if link not in excluded_links]
+
+# Apply re.escape() to the filtered links
+
+linkcheck_ignore = [re.escape(link) for link in filtered_links]