diff options
| author | W. Kosior <koszko@koszko.org> | 2024-12-17 17:34:11 +0100 |
|---|---|---|
| committer | W. Kosior <koszko@koszko.org> | 2024-12-17 17:34:11 +0100 |
| commit | b94e315bc34bd5ce93d69d68b2837dc968a4a39a (patch) | |
| tree | f56d6b7e73772c4b24aaf4c9db489fcbf27713fe | |
| parent | b6418bfbfad8fb3f0d9f206163496a10b36a1877 (diff) | |
| download | AGH-threat-intel-course-b94e315bc34bd5ce93d69d68b2837dc968a4a39a.tar.gz AGH-threat-intel-course-b94e315bc34bd5ce93d69d68b2837dc968a4a39a.zip | |
Attach scraped data to that from profiles.yaml and output together.
| -rw-r--r-- | Makefile | 9 | ||||
| -rw-r--r-- | scrape_groups_info.py | 28 |
2 files changed, 19 insertions, 18 deletions
@@ -8,7 +8,7 @@ PYTHON=python3 PANDOC=pandoc -all: tables.pdf scraped_info.yaml +all: tables.pdf profiles_with_scraped_info.yaml .PHONY: all .SUFFIXES: .pdf .md @@ -25,18 +25,19 @@ all: tables.pdf scraped_info.yaml tables.md: threats_by_sector_table.py profiles.yaml $(PYTHON) $^ > $@ -scraped_info.yaml: scrape_groups_info.py profiles.yaml +profiles_with_scraped_info.yaml: scrape_groups_info.py profiles.yaml $(PYTHON) $^ > $@ th-proj-archive.tar.gz: Makefile profiles.yaml scrape_groups_info.py \ - scraped_info.yaml tables.md tables.pdf \ + profiles_with_scraped_info.yaml tables.md tables.pdf \ threats_by_sector_table.py tar --transform='s|^|th-proj-archive/|' \ --mtime=1970-01-01T00:00:00-00:00 --group=0 --owner=0 \ -czf $@ $^ clean: - rm -rf scraped_info.yaml tables.pdf tables.md th-proj-archive.tar.gz + rm -rf profiles_with_scraped_info.yaml tables.pdf tables.md \ + th-proj-archive.tar.gz .PHONY: clean magisterclean: clean diff --git a/scrape_groups_info.py b/scrape_groups_info.py index 92219db..ac6956b 100644 --- a/scrape_groups_info.py +++ b/scrape_groups_info.py @@ -109,28 +109,28 @@ def get_groups_and_techniques(relevant_names): return groups, all_techniques -def get_group_names(profiles_path): - def group_names(inp): - return {group["name"] for group in yaml.safe_load(inp)["groups"]} - +def get_profiles_data(profiles_path): if profiles_path: with open(profiles_path) as inp: - return group_names(inp) + return yaml.safe_load(inp) - return group_names(sys.stdin) + return yaml.safe_load(sys.stdin) if __name__ == "__main__": - group_names = get_group_names(None if len(sys.argv) < 2 else sys.argv[1]) - groups, techniques = get_groups_and_techniques(group_names) - missing_names = group_names.difference(groups) + profiles_data = get_profiles_data(None if len(sys.argv) < 2 + else sys.argv[1]) + group_profiles = dict((g["name"],g) for g in profiles_data["groups"]) + groups, techniques = get_groups_and_techniques(group_profiles) + missing_names = set(group_profiles).difference(groups) if missing_names: print(f"No data found for group(s): {', '.join(sorted(missing_names))}", file=sys.stderr) - out_obj = { - "groups": [g.__dict__ for g in groups.values()], - "techniques": [t.__dict__ for t in techniques.values()] - } + for name, group in groups.items(): + group_profiles[name].update(group.__dict__) + + profiles_data["groups"] = list(group_profiles.values()) + profiles_data["techniques"] = [t.__dict__ for t in techniques.values()] - yaml.safe_dump(out_obj, sys.stdout) + yaml.safe_dump(profiles_data, sys.stdout) |