CIRCL
/
lookyloo
mirror of https://github.com/CIRCL/lookyloo
2
0
Fork 0
Code Issues Releases Wiki Activity

chg: Use cache instead of pickle for meta info

pull/559/head
Raphaël Vinot 2022-12-08 10:49:26 +01:00
parent 2c6d6b2556
commit 1ae76ddea7
1 changed files with 7 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
lookyloo/lookyloo.py
View File

@ -203,14 +203,18 @@ class Lookyloo():
def get_meta(self, capture_uuid: str, /) -> Dict[str, str]: def get_meta(self, capture_uuid: str, /) -> Dict[str, str]:
'''Get the meta informations from a capture (mostly, details about the User Agent used.)''' '''Get the meta informations from a capture (mostly, details about the User Agent used.)'''
metafile = self._captures_index[capture_uuid].capture_dir / 'meta' cache = self.capture_cache(capture_uuid)
if not cache:
return {}
metafile = cache.capture_dir / 'meta'
if metafile.exists(): if metafile.exists():
with metafile.open('r') as f: with metafile.open('r') as f:
return json.load(f) return json.load(f)
if not cache.user_agent:
return {}
meta = {} meta = {}
ct = self.get_crawled_tree(capture_uuid) ua = ParsedUserAgent(cache.user_agent)
ua = ParsedUserAgent(ct.root_hartree.user_agent)
meta['user_agent'] = ua.string meta['user_agent'] = ua.string
if ua.platform: if ua.platform:
meta['os'] = ua.platform meta['os'] = ua.platform