Mirrors
/
APT_CyberCriminal_Campagin_Collections
mirror of https://github.com/CyberMonitor/APT_CyberCriminal_Campagin_Collections
6
0
Fork 0
Code Issues Projects Releases Wiki Activity

Fixes for PYPDF2

This commit is contained in:
Robert Haist 2022-12-27 17:57:51 +01:00
parent 72b0d84034
commit e4cb9cc9aa
2 changed files with 1541 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1533
index.csv
View File

File diff suppressed because it is too large Load Diff

15
index/generate_index.py
View File

@ -33,18 +33,19 @@ def index_report(path: str):
# Get the published date from the path name if possible
published_raw = DATE_REGEX.match(os.path.basename(os.path.dirname(path)))
pypdf = PyPDF2.PdfFileReader(open(path, "rb"), strict=False)
pypdf = PyPDF2.PdfReader(open(path, "rb"), strict=False)
if published_raw == None or (".00" in published_raw.group(0)):
logging.debug(f"no published date for report: {path}")
if pypdf.isEncrypted:
if pypdf.is_encrypted:
pypdf.decrypt("")
try:
cdate_raw = pypdf.documentInfo["/CreationDate"]
cdate_clean = cdate_raw.replace("'", "").replace("D:", "")[:8]
cadate_parsed = datetime.strptime(cdate_clean, "%Y%m%d")
published = cadate_parsed.date()
cdate = pypdf.metadata.creation_date
if cdate != None:
published = pypdf.metadata.creation_date.date()
else:
published = datetime.min.date()
except (KeyError, ValueError, PdfReadError) as derr:
logging.error(f"no date for report: {path} | {derr}")
return
@ -67,7 +68,7 @@ def process_reports(path: str):
if not filepath.endswith(".pdf"):
continue
try:
PyPDF2.PdfFileReader(open(full_path, "rb"))
PyPDF2.PdfReader(open(full_path, "rb"))
rel_dir = os.path.relpath(path, os.getcwd())
rel_file = os.path.join(rel_dir, filepath)
report_list.append(rel_file)