mirror of
https://github.com/bellingcat/auto-archiver.git
synced 2026-06-10 04:08:28 +03:00
Compare commits
3 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
31c07a02e1 | ||
|
|
bd231488ff | ||
|
|
fb197f1064 |
@@ -139,7 +139,7 @@ class Metadata:
|
||||
new_media = []
|
||||
for m in self.media:
|
||||
h = m.get("hash")
|
||||
if not h: h = calculate_hash_in_chunks(hashlib.sha256(), 1.6e7, m.filename)
|
||||
if not h: h = calculate_hash_in_chunks(hashlib.sha256(), int(1.6e7), m.filename)
|
||||
if len(h) and h in media_hashes: continue
|
||||
media_hashes.add(h)
|
||||
new_media.append(m)
|
||||
|
||||
@@ -23,7 +23,7 @@ class HashEnricher(Enricher):
|
||||
def configs() -> dict:
|
||||
return {
|
||||
"algorithm": {"default": "SHA-256", "help": "hash algorithm to use", "choices": ["SHA-256", "SHA3-512"]},
|
||||
"chunksize": {"default": 1.6e7, "help": "number of bytes to use when reading files in chunks (if this value is too large you will run out of RAM), default is 16MB"},
|
||||
"chunksize": {"default": int(1.6e7), "help": "number of bytes to use when reading files in chunks (if this value is too large you will run out of RAM), default is 16MB"},
|
||||
}
|
||||
|
||||
def enrich(self, to_enrich: Metadata) -> None:
|
||||
|
||||
@@ -49,6 +49,9 @@ class UrlUtil:
|
||||
# instagram recurring images
|
||||
if "https://static.cdninstagram.com/rsrc.php/" in url: return False
|
||||
|
||||
# telegram
|
||||
if "https://telegram.org/img/emoji/" in url: return False
|
||||
|
||||
return True
|
||||
|
||||
@staticmethod
|
||||
|
||||
@@ -3,7 +3,7 @@ _MAJOR = "0"
|
||||
_MINOR = "6"
|
||||
# On main and in a nightly release the patch should be one ahead of the last
|
||||
# released build.
|
||||
_PATCH = "1"
|
||||
_PATCH = "2"
|
||||
# This is mainly for nightly builds which have the suffix ".dev$DATE". See
|
||||
# https://semver.org/#is-v123-a-semantic-version for the semantics.
|
||||
_SUFFIX = ""
|
||||
|
||||
Reference in New Issue
Block a user