Update

ncc_core/nc_import/bots/get_langs.py

@@ -4,6 +4,7 @@
 
 """
 import re
+import wikitextparser as wtp
 from newapi.ncc_page import MainPage as ncc_MainPage
 from newapi import printe
 
@@ -26,9 +27,30 @@ def get_langs_codes():
     """
     text = get_text()
     langs = []
-    fi = re.findall(r"\* (.*)\n", text)
-    for i in fi:
-        langs.append(i.strip())
+    # * {{User:Mr. Ibrahem/import bot/line|ar}}
+    # ---
+    tmp = "User:Mr. Ibrahem/import bot/line"
+    # ---
+    prased = wtp.parse(text)
+    temps = prased.templates
+    for temp in temps:
+        # ---
+        name = str(temp.normal_name()).strip().lower().replace("_", " ")
+        # ---
+        printe.output(f"{temp.name=}, {name=}")
+        # ---
+        if name == tmp.lower():
+            # ---
+            # get first argument
+            # ---
+            va = temp.get_arg("1")
+            if va and va.value:
+                langs.append(va.value.strip())
     # ---
     printe.output(f"langs: {langs}")
+    # ---
     return langs
+
+if __name__ == "__main__":
+    # python3 core8/pwb.py nc_import/bots/get_langs
+    get_langs_codes()

ncc_core/nc_import/bots/import_files.py

@@ -3,6 +3,7 @@
 bot for importing files from nccommons to wikipedia
 
 """
+import re
 import sys
 from newapi.ncc_page import MainPage as ncc_MainPage, NEW_API as ncc_NEW_API
 from newapi import printe
@@ -22,6 +23,16 @@ def get_file_text(title):
 
     return text
 
+def categories_work(text):
+    """
+    remove all categories from the text
+    """
+    # ---
+    text = re.sub(r"\[\[Category:(.*?)\]\]", "", text, flags=re.DOTALL)
+    # ---
+    text += "\n[[Category:Files imported from NC Commons]]"
+    # ---
+    return text
 
 def import_file(title, code):
     """
@@ -31,6 +42,8 @@ def import_file(title, code):
     # ---
     file_text = get_file_text(title)
     # ---
+    file_text = categories_work(file_text)
+    # ---
     api_new = ncc_NEW_API("www", family="nccommons")
     # api_new.Login_to_wiki()
     img_url = api_new.Get_image_url(title)

ncc_core/nc_import/bots/wrk_pages.py

@@ -28,6 +28,12 @@ def start(self):
         # ---
         self.get_temps()
         self.work_on_temps()
+        # ---
+        if self.new_text == self.text:
+            printe.output("no changes")
+            return
+        # ---
+        self.add_category()
         self.save()
 
     def get_temps(self):
@@ -79,9 +85,14 @@ def work_on_temps(self):
             if temp_new_text != string:
                 self.new_text = self.new_text.replace(string, temp_new_text)
 
+    def add_category(self):
+        cat = "Category:Contains images from NC Commons"
+        # ---
+        if self.new_text.find(cat) == -1:
+            self.new_text += "\n[[Category:Contains images from NC Commons]]"
+
     def save(self):
-        if self.new_text != self.text:
-            self.page.save(newtext=self.new_text, summary="bot: fix NC")
+        self.page.save(newtext=self.new_text, summary="bot: fix NC")
 
 
 def work_on_pages(code, pages):

ncc_core/nc_import/views.py

@@ -0,0 +1,52 @@
+"""
+
+python3 core8/pwb.py nc_import/views
+fetch("https://pageviews.wmcloud.org/pageviews/api.php?pages=Kat%7CHond&project=af.wikipedia.org&start=2015-07-01&end=2024-03-27&totals=true", {
+  "headers": {
+    "accept": "*/*",
+    "accept-language": "ar-EG,ar;q=0.9,en-US;q=0.8,en;q=0.7,sk;q=0.6,zh-CN;q=0.5,zh-TW;q=0.4,zh;q=0.3",
+    "sec-ch-ua": "\"Google Chrome\";v=\"123\", \"Not:A-Brand\";v=\"8\", \"Chromium\";v=\"123\"",
+    "sec-ch-ua-mobile": "?0",
+    "sec-ch-ua-platform": "\"Windows\"",
+    "sec-fetch-dest": "empty",
+    "sec-fetch-mode": "cors",
+    "sec-fetch-site": "same-origin",
+    "x-requested-with": "XMLHttpRequest"
+  },
+  "referrer": "https://pageviews.wmcloud.org/pageviews/?project=af.wikipedia.org&platform=all-access&agent=user&redirects=0&range=all-time&pages=Kat|Hond",
+  "referrerPolicy": "strict-origin-when-cross-origin",
+  "body": null,
+  "method": "GET",
+  "mode": "cors",
+  "credentials": "omit"
+});
+"""
+from nc_import.bots.get_langs import get_langs_codes
+
+def get_views(code):
+    endpoint = "https://pageviews.wmcloud.org/massviews/api.php"
+    category = "Category:Files_imported_from_NC_Commons"
+    # ---
+    # https://pageviews.wmcloud.org/massviews/api.php?project=af.wikipedia.org&category=Files_imported_from_NC_Commons&limit=20000
+    # ---
+    params = {
+        "project": f"{code}.wikipedia.org",
+        "category": category
+    }
+    # ---
+    # result example: [{"title":"Chondrosarcoma_of_the_nasal_septum_(Radiopaedia_165701-135935_Sagittal_2).jpeg","ns":6}]
+    # ---
+
+
+def start():
+    """
+    A function that starts the process by iterating over languages, getting pages for each language, and then working on those pages.
+    """
+    langs = get_langs_codes()
+    # ---
+    for code in langs:
+        pages = get_views(code)
+
+
+if __name__ == "__main__":
+    start()