Migrate Scraper to GitHub .md Files

backend/apps/github/management/commands/github_update_owasp_organization.py

@@ -76,24 +76,28 @@ def handle(self, *_args, **options) -> None:
                 print(f"{prefix:<12} {repository_url}")
 
                 try:
-                    owasp_organization, repository = sync_repository(
+                    owasp_organization, synced_repository = sync_repository(
                         gh_repository,
                         organization=owasp_organization,
                         user=owasp_user,
                     )
 
                     # OWASP chapters.
                     if entity_key.startswith("www-chapter-"):
-                        chapters.append(Chapter.update_data(gh_repository, repository, save=False))
+                        chapters.append(
+                            Chapter.update_data(gh_repository, synced_repository, gh, save=False)
+                        )
 
                     # OWASP projects.
                     elif entity_key.startswith("www-project-"):
-                        projects.append(Project.update_data(gh_repository, repository, save=False))
+                        projects.append(
+                            Project.update_data(gh_repository, synced_repository, gh, save=False)
+                        )
 
                     # OWASP committees.
                     elif entity_key.startswith("www-committee-"):
                         committees.append(
-                            Committee.update_data(gh_repository, repository, save=False)
+                            Committee.update_data(gh_repository, synced_repository, gh, save=False)
                         )
                 except Exception:
                     logger.exception("Error syncing repository %s", repository_url)

backend/apps/owasp/models/chapter.py

@@ -87,11 +87,12 @@ def active_chapters_count():
         """Return active chapters count."""
         return IndexBase.get_total_count("chapters", search_filters="idx_is_active:true")
 
-    def from_github(self, repository) -> None:
+    def from_github(self, repository, gh) -> None:
         """Update instance based on GitHub repository data.
 
         Args:
             repository (github.Repository): The GitHub repository instance.
+            gh (Github): The authenticated Github client instance.
 
         """
         self.owasp_repository = repository
@@ -108,6 +109,7 @@ def from_github(self, repository) -> None:
                 "region": "region",
                 "tags": "tags",
             },
+            gh,
         )
 
         self.created_at = repository.created_at
@@ -192,12 +194,13 @@ def bulk_save(  # type: ignore[override]
         BulkSaveModel.bulk_save(Chapter, chapters, fields=fields)
 
     @staticmethod
-    def update_data(gh_repository, repository, *, save: bool = True) -> Chapter:
+    def update_data(gh_repository, repository, gh, *, save: bool = True) -> Chapter:
         """Update chapter data from GitHub repository.
 
         Args:
             gh_repository (github.Repository): The GitHub repository instance.
             repository (github.Repository): The repository data to update from.
+            gh (Github): The authenticated Github client instance.
             save (bool, optional): Whether to save the instance.
 
         Returns:
@@ -210,7 +213,7 @@ def update_data(gh_repository, repository, *, save: bool = True) -> Chapter:
         except Chapter.DoesNotExist:
             chapter = Chapter(key=key)
 
-        chapter.from_github(repository)
+        chapter.from_github(repository, gh)
         if save:
             chapter.save()
 

backend/apps/owasp/models/committee.py

@@ -35,7 +35,7 @@ def __str__(self) -> str:
         """Committee human readable representation."""
         return f"{self.name}"
 
-    def from_github(self, repository) -> None:
+    def from_github(self, repository, gh) -> None:
         """Update instance based on GitHub repository data."""
         self.owasp_repository = repository
 
@@ -46,6 +46,7 @@ def from_github(self, repository) -> None:
                 "name": "title",
                 "tags": "tags",
             },
+            gh,
         )
 
         self.created_at = repository.created_at
@@ -75,15 +76,15 @@ def bulk_save(committees, fields=None) -> None:  # type: ignore[override]
         BulkSaveModel.bulk_save(Committee, committees, fields=fields)
 
     @staticmethod
-    def update_data(gh_repository, repository, *, save: bool = True) -> "Committee":
+    def update_data(gh_repository, repository, gh, *, save: bool = True) -> "Committee":
         """Update committee data."""
         key = gh_repository.name.lower()
         try:
             committee = Committee.objects.get(key=key)
         except Committee.DoesNotExist:
             committee = Committee(key=key)
 
-        committee.from_github(repository)
+        committee.from_github(repository, gh)
         if save:
             committee.save()