feat: Multiple organization scan and fixed broken py2neo (#83)

* Scan multipule organization in one command.

* Fixed py2neo dependency fail.

* Fixed test file.

Author: elad-pticha

README.md

@@ -154,7 +154,7 @@ options:
 
 Retrieve all workflows and actions associated with the organization.
 ``` bash
-raven download org --token $GITHUB_TOKEN --org-name microsoft --debug
+raven download org --token $GITHUB_TOKEN --org-name microsoft --org-name google --debug
 ```
 
 Scrape all publicly accessible GitHub repositories.

requirements.txt

@@ -8,7 +8,6 @@ monotonic==1.6
 packaging==23.1
 pansi==2020.7.3
 pluggy==1.3.0
-py2neo==2021.2.3
 Pygments==2.16.1
 pytest==7.4.2
 pytz==2023.3.post1
@@ -19,4 +18,6 @@ six==1.16.0
 slack-sdk==3.22.0
 tabulate==0.9.0
 tqdm==4.66.1
-urllib3==2.0.5
+urllib3==2.0.5
+
+py2neo @ git+https://github.com/elad-pticha/py2neo.git@d684901abeeb1484e5b396d4b6cef491c4bd8271#egg=py2neo

src/cmdline.py

@@ -151,6 +151,8 @@ def raven() -> None:
     org_download_parser.add_argument(
         "--org-name",
         required=True,
+        action="append",
+        type=str,
         help="Organization name to download the workflows",
     )
 

src/config/config.py

@@ -96,7 +96,7 @@ class Config:
     github_token: str = None
     min_stars: int = None
     max_stars: int = None
-    org_name: str = None
+    org_name: list[str] = []
 
     # Indexer Configs
     clean_neo4j: bool = None

src/downloader/download.py

@@ -34,14 +34,17 @@ def download_org_workflows_and_actions() -> None:
     We are trying to cache the downloads as much as we can to reduce redundant download attempts.
     """
     log.debug("[+] Starting organization repository iterator")
-    generator = get_organization_repository_generator(Config.org_name)
 
-    # Clean redis
-    if Config.clean_redis:
-        clean_redis_db()
+    for organization in Config.org_name:
+        log.debug(f"[+] Scanning {organization}")
+        generator = get_organization_repository_generator(organization)
 
-    for repo in generator:
-        download_workflows_and_actions(repo)
+        # Clean redis
+        if Config.clean_redis:
+            clean_redis_db()
+
+        for repo in generator:
+            download_workflows_and_actions(repo)
 
 
 def download_all_workflows_and_actions() -> None:

tests/test_raven.py

@@ -15,7 +15,7 @@
 
 def load_integration_tests_config() -> None:
     load_downloader_config(
-        {"debug": False, "token": getenv("GITHUB_TOKEN"), "org_name": "RavenDemo"}
+        {"debug": False, "token": getenv("GITHUB_TOKEN"), "org_name": ["RavenDemo"]}
     )
 
     load_indexer_config(