logo Netzschleuder network catalog, repository, and centrifuge

History of wikipedia_links_2013

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] wikipedia_links_2013: add the yearly English Wikipedia link graphs of 2015-2025 by Tiago de Paula Peixoto 35ce39e
The entry had only the link graphs of 2013 (five languages). The yearly
snapshots of the English Wikipedia distributed by LAW since 2015 are
added as the networks `en-2015` to `en-2025`; the existing networks are
unchanged.

Changed: upstream wikipedia_links_2013
diff --git a/entries/wikipedia_links_2013/__init__.py b/entries/wikipedia_links_2013/__init__.py
index 8986f57..783e614 100644
--- a/entries/wikipedia_links_2013/__init__.py
+++ b/entries/wikipedia_links_2013/__init__.py
@@ -18,10 +18,10 @@
 
 from .. import *
 
-title = "Wikipedia hyperlinks (2013)"
-description = """Directed networks of hyperlinks among the articles of five Wikipedia editions, English (`en`), German (`de`), French (`fr`), Italian (`it`) and Spanish (`es`), as of late February 2013, extracted and distributed by the Laboratory for Web Algorithmics (LAW). Nodes are articles, and a directed edge from one article to another indicates that the first contains a link to the second. Redirects were resolved when computing the links (a link to a redirect points to its target article), and redirect pages are not part of the graphs; namespaced pages (e.g. `Template:...` or `Category:...`) are not included either. Self-loops (articles linking to themselves) are present.
+title = "Wikipedia hyperlinks (2013-2025)"
+description = """Directed networks of hyperlinks among the articles of five Wikipedia editions, English (`en`), German (`de`), French (`fr`), Italian (`it`) and Spanish (`es`), as of late February 2013, and yearly snapshots of the English Wikipedia from 2015 to 2025 (`en-2015` to `en-2025`; as of mid-year, according to LAW, for 2015 to 2023, while the pages of 2024 and 2025 give no date), extracted and distributed by the Laboratory for Web Algorithmics (LAW). Nodes are articles, and a directed edge from one article to another indicates that the first contains a link to the second. Redirects were resolved when computing the links (a link to a redirect points to its target article), and redirect pages are not part of the graphs; namespaced pages (e.g. `Template:...` or `Category:...`) are not included either. Self-loops (articles linking to themselves) are present.
 
-Sizes (articles, links): `en` 4,206,785, 101,355,853; `de` 1,532,354, 36,722,696; `fr` 1,352,053, 34,378,431; `it` 1,016,867, 25,619,926; `es` 972,933, 23,041,488.
+Sizes (articles, links): `en` 4,206,785, 101,355,853; `de` 1,532,354, 36,722,696; `fr` 1,352,053, 34,378,431; `it` 1,016,867, 25,619,926; `es` 972,933, 23,041,488. The yearly snapshots of the English Wikipedia: `en-2015` 4,853,050, 106,314,263; `en-2016` 5,096,287, 113,095,771; `en-2017` 5,409,498, 122,008,994; `en-2018` 5,616,717, 128,835,798; `en-2019` 5,839,060, 135,700,782; `en-2020` 6,047,510, 142,691,609; `en-2021` 6,261,502, 150,124,927; `en-2022` 6,492,490, 159,047,205; `en-2023` 6,625,370, 165,206,104; `en-2024` 6,790,971, 172,762,484; `en-2025` 6,961,383, 181,022,291. The node order differs between the snapshots.
 
 A network of the links of the English Wikipedia from a slightly later dump (March/April 2013), extracted by DBpedia without resolving redirects, including pages in other namespaces and missing pages, and with link multiplicities, is in the entry `dbpedia_link`.
 
@@ -38,6 +38,9 @@ upstream_prefix = 'http://data.law.di.unimi.it/webdata'
 files = [((f'{la}wiki-2013/{la}wiki-2013.graph', f'{la}wiki-2013/{la}wiki-2013.properties',
            f'{la}wiki-2013/{la}wiki-2013.ids.gz'), la, None)
          for la in ["es", "it", "fr", "de", "en"]]
+files += [((f'enwiki-{y}/enwiki-{y}.graph', f'enwiki-{y}/enwiki-{y}.properties',
+            f'enwiki-{y}/enwiki-{y}.ids.gz'), f'en-{y}', None)
+          for y in range(2015, 2026)]
 
 def fetch_upstream(force=False):
     return fetch_upstream_files(__name__.split(".")[-1], upstream_prefix, files,
[entries] New entry: wikipedia_links_2013 by Tiago de Paula Peixoto 5416064
diff --git a/entries/wikipedia_links_2013/__init__.py b/entries/wikipedia_links_2013/__init__.py
new file mode 100644
index 0000000..8986f57
--- /dev/null
+++ b/entries/wikipedia_links_2013/__init__.py
@@ -0,0 +1,56 @@
+#! /usr/bin/env python
+# -*- coding: utf-8 -*-
+#
+# Copyright (C) 2020-2026 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 = "Wikipedia hyperlinks (2013)"
+description = """Directed networks of hyperlinks among the articles of five Wikipedia editions, English (`en`), German (`de`), French (`fr`), Italian (`it`) and Spanish (`es`), as of late February 2013, extracted and distributed by the Laboratory for Web Algorithmics (LAW). Nodes are articles, and a directed edge from one article to another indicates that the first contains a link to the second. Redirects were resolved when computing the links (a link to a redirect points to its target article), and redirect pages are not part of the graphs; namespaced pages (e.g. `Template:...` or `Category:...`) are not included either. Self-loops (articles linking to themselves) are present.
+
+Sizes (articles, links): `en` 4,206,785, 101,355,853; `de` 1,532,354, 36,722,696; `fr` 1,352,053, 34,378,431; `it` 1,016,867, 25,619,926; `es` 972,933, 23,041,488.
+
+A network of the links of the English Wikipedia from a slightly later dump (March/April 2013), extracted by DBpedia without resolving redirects, including pages in other namespaces and missing pages, and with link multiplicities, is in the entry `dbpedia_link`.
+
+The node order is the one of the distributed (LLP-permuted) graphs. Vertex property: `title`, the title of the article. The data were collected with support of the EU-FET grant NADINE (GA 288956)."""
+tags = ['Informational', 'Web graph', 'Unweighted']
+url = 'https://law.di.unimi.it/datasets.php'
+citation = [('P. Boldi and S. Vigna, "The WebGraph framework I: compression techniques." Proceedings of the 13th International Conference on World Wide Web (WWW 2004), 595-602 (2004).', 'https://doi.org/10.1145/988672.988752'),
+            ('P. Boldi, M. Rosa, M. Santini, and S. Vigna, "Layered label propagation: a multiresolution coordinate-free ordering for compressing social networks." Proceedings of the 20th International Conference on World Wide Web (WWW 2011), 587-596 (2011).', 'https://doi.org/10.1145/1963405.1963488')]
+icon_hash = '56a85c8e26855e083a2f793b'
+upstream_license = None
+# Too large to process on an ordinary machine (see --skip-huge)
+huge = True
+upstream_prefix = 'http://data.law.di.unimi.it/webdata'
+files = [((f'{la}wiki-2013/{la}wiki-2013.graph', f'{la}wiki-2013/{la}wiki-2013.properties',
+           f'{la}wiki-2013/{la}wiki-2013.ids.gz'), la, None)
+         for la in ["es", "it", "fr", "de", "en"]]
+
+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 fnames, alt, fmt in files:
+        if alts is not None and alt not in alts:
+            continue
+        g = law_graph(name, fnames, directed=True, label="title")
+        yield alt, g