logo Netzschleuder network catalog, repository, and centrifuge

History of hudong

The changes to the source code of this entry in the repository, newest first, each with the differences it made to the entry's files. They are also listed on GitLab.

[entries] New entry: hudong by Tiago de Paula Peixoto 54bb2d3
diff --git a/entries/hudong/__init__.py b/entries/hudong/__init__.py
new file mode 100644
index 0000000..48e63df
--- /dev/null
+++ b/entries/hudong/__init__.py
@@ -0,0 +1,60 @@
+#! /usr/bin/env python
+# -*- coding: utf-8 -*-
+#
+# Copyright (C) 2026 Tiago de Paula Peixoto <tiago@skewed.de>
+#
+# This program is free software: you can redistribute it and/or modify it under
+# the terms of the GNU Affero General Public License as published by the Free
+# Software Foundation, either version 3 of the License, or (at your option) any
+# later version.
+#
+# This program is distributed in the hope that it will be useful, but WITHOUT
+# ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS
+# FOR A PARTICULAR PURPOSE.  See the GNU Affero General Public License for more
+# details.
+#
+# You should have received a copy of the GNU Affero General Public License along
+# with this program.  If not, see <http://www.gnu.org/licenses/>.
+
+
+
+from .. import *
+
+
+title = 'Hudong encyclopedia links (2011)'
+description = """Directed networks of links between the articles of the Chinese online encyclopedia Hudong (互动百科, later Baike.com), from the Zhishi.me project of Chinese linked open data, as distributed by KONECT:
+
+- `internal_links`: hyperlinks; an edge from article A to article B means that A links to B;
+- `related_pages`: "related pages"; an edge from article A to article B means that A lists B as related.
+
+The data identify the articles only by indices (their titles are not included). Some articles link to themselves. The hyperlinks of the encyclopedia Baidu Baike, from the same project, are the entry `baidu`."""
+tags = ['Informational', 'Web graph', 'Unweighted']
+url = ['http://konect.cc/networks/zhishi-hudong-internallink', 'http://konect.cc/networks/zhishi-hudong-relatedpages']
+citation = [('X. Niu, X. Sun, H. Wang, S. Rong, G. Qi, Y. Yu, "Zhishi.me - Weaving Chinese Linking Open Data." The Semantic Web - ISWC 2011, Lecture Notes in Computer Science 7032, 205-220 (2011)', 'https://doi.org/10.1007/978-3-642-25093-4_14'),
+            ('J. Kunegis, "KONECT -- The Koblenz Network Collection." Proceedings of the 22nd International Conference on World Wide Web Companion, 1343-1350 (2013)', 'https://doi.org/10.1145/2487788.2488173')]
+icon_hash = None
+upstream_license = None
+upstream_prefix = 'http://konect.cc/files'
+files = [('download.tsv.zhishi-hudong-internallink.tar.bz2', 'internal_links', 'konect'),
+         ('download.tsv.zhishi-hudong-relatedpages.tar.bz2', 'related_pages', 'konect')]
+
+def postprocess(alt, g):
+    pass
+
+def fetch_upstream(force=False):
+    return fetch_upstream_files(__name__.split(".")[-1], upstream_prefix, files,
+                                force)
+
+@cache_network()
+@coerce_props()
+@annotate()
+def parse(alts=None):
+    global files
+    name = __name__.split(".")[-1]
+    for fname, alt, fmt in files:
+        if alts is not None and alt not in alts:
+            continue
+        with open_upstream_file(name, fname, "rb") as f:
+            g = parse_graph([f], fmt, directed=None)
+        postprocess(alt, g)
+        yield alt, g