davosian · July 19, 2021 14:57 · Feb 14, 2021 · Feb 14, 2021
diff --git a/groceries → groceries_wiktionary b/groceries → groceries_wiktionary
diff --git a/groceries b/groceries
@@ -0,0 +1,53 @@
+#! /usr/bin/python3
+try:
+    # For Python 3.0 and later
+    from urllib.request import urlopen
+    from urllib.parse import quote
+except ImportError:
+    # Fall back to Python 2's urllib2
+    from urllib2 import urlopen
+    from urllib2 import quote
+
+import json
+
+
+def get_jsonparsed_data(url):
+    """
+    Receive the content of ``url``, parse it as JSON and return the object.
+
+    Parameters
+    ----------
+    url : str
+
+    Returns
+    -------
+    dict
+    """
+    response = urlopen(url)
+    data = response.read().decode("utf-8")
+    return json.loads(data)
+
+appendices = [
+              "Verzeichnis:Deutsch/Essen_und_Trinken/Lebensmittel",
+              "Verzeichnis:Deutsch/Essen_und_Trinken/Obst_und_Gem%C3%BCse",
+              "Verzeichnis:Deutsch/Essen_und_Trinken/Speisen",
+              "Verzeichnis:Deutsch/Essen_und_Trinken/Getr%C3%A4nke"
+]
+base_url = "https://de.wiktionary.org/w/api.php?format=json&action=query&titles={}&prop=links&formatversion=2&pllimit=500"
+plcont = "&plcontinue={}"
+
+words = []
+for appendix in appendices:
+    # print(appendix)
+    url = base_url.format(appendix)
+    url2 = url
+    while True:
+        # print(url2)
+        res = get_jsonparsed_data(url2)
+        # print(res)
+        words += [d["title"] for d in res["query"]["pages"][0]["links"] if ":" not in d["title"]]
+        if not "continue" in res:
+            break;
+        url2 = url + plcont.format(quote(res["continue"]["plcontinue"]))
+
+print("\n".join(words))