BrowserSecurity
/
ExtensionCrawler
2
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

Fixed some bugs.

This commit is contained in:
Michael Herzberg 2019-02-28 13:06:15 +00:00
parent c827219a40
commit bff53c583e
1 changed files with 29 additions and 17 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

46
extgrep
View File

@ -84,6 +84,17 @@ def get_name_and_version(overview_contents):
return name, version
def first_match_in_locations(search_tag, pattern, locations):
for location_tag, lines in locations:
for line in lines:
m = re.search(pattern, line)
if m:
matched_string = m.group()
if search_tag is not "MINING_KEYS_REGEX" or is_likely_hash(matched_string):
return [[location_tag, search_tag, matched_string]]
return []
def handle_extid(conf, extid, csvwriter):
miner_strings = import_regexs(conf.REGEXP_FILE).MinerStrings()
@ -100,7 +111,7 @@ def handle_extid(conf, extid, csvwriter):
crx_etag = None
name = None
version = None
matches = []
date_matches = []
for tarentry, tarfile in tups:
tarentry_filename = tarentry.name.split("/")[-1]
@ -118,30 +129,31 @@ def handle_extid(conf, extid, csvwriter):
if tarentry_filename.endswith(".crx") and tarentry.size > 0:
with ZipFile(tarfile) as zf:
for zipentry in zf.infolist():
file_matches = []
if zipentry.filename.endswith(".js"):
with zf.open(zipentry) as f:
for block in mince_js(io.TextIOWrapper(f, encoding="utf-8", errors="surrogateescape")):
file_lines = []
file_lines += block.content.splitlines()
file_lines += "".join(map(lambda x: x[1], block.string_literals)).splitlines()
verbatim_lines = block.content.splitlines()
joined_string_lines = "".join(map(lambda x: x[1], block.string_literals)).splitlines()
for search_tag in miner_strings.strings.keys():
for search_string in miner_strings.strings[search_tag]:
for line in file_lines:
if search_string in line:
matches += [[zipentry.filename, search_tag, search_string]]
break
for match in first_match_in_locations(search_tag, re.escape(search_string),
[("verbatim", verbatim_lines),
("joined_string", joined_string_lines)]):
file_matches.append(match)
for search_tag in miner_strings.patterns.keys():
for search_pattern in miner_strings.patterns[search_tag]:
for line in file_lines:
m = re.search(search_pattern, line)
if m:
matched_string = m.group()
if search_tag is not "MINING_KEYS_REGEX" or is_likely_hash(matched_string):
matches += [[zipentry.filename, search_tag, matched_string]]
break
for match in matches:
for match in first_match_in_locations(search_tag, search_pattern,
[("verbatim", verbatim_lines),
("joined_string", joined_string_lines)]):
file_matches.append(match)
for match in file_matches:
date_matches.append([zipentry.filename] + match)
for match in date_matches:
results += [[date, crx_etag, name, version] + match]
for result in results:
@ -160,7 +172,7 @@ def main(conf):
with open(conf.EXTID_FILE) as f:
csvwriter = csv.writer(sys.stdout, csv.unix_dialect)
csvwriter.writerow(["extid", "still_in_store", "most_recent_crx_etag", "date", "crx_etag", "name", "version", "path", "tag", "match"])
csvwriter.writerow(["extid", "still_in_store", "most_recent_crx_etag", "date", "crx_etag", "name", "version", "path", "position", "tag", "match"])
for extid in [l.strip() for l in f.readlines()]:
handle_extid(conf, extid, csvwriter)