dash/pdfgrab
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

bugfixes for bad ssl handshakes and decrypted files

Browse Source
This commit is contained in:
dash
2019-09-26 17:01:08 +02:00
parent d56ca14cb0
commit d74205eddb
1 changed files with 29 additions and 11 deletions
Download Patch File Download Diff File Expand all files Collapse all files

40
pdfgrab.py
View File

@@ -10,6 +10,10 @@
# TODO # TODO
# * json output # * json output
# * txt output # * txt output
# * catch ssl exceptions
# * catch conn refused connections
# * set option for certificate verification, default is false
# * add decryption routine
import os import os
import sys import sys
@@ -40,7 +44,7 @@ def find_name(pdf):
name = pdf.split("/") name = pdf.split("/")
a = len(name) a = len(name)
name = name[a-1] name = name[a-1]
print(name) #print(name)
return name return name
@@ -49,14 +53,23 @@ def make_directory(outdir):
try: try:
os.mkdir(outdir) os.mkdir(outdir)
except: except:
print("[W] mkdir, some error, directory probably exists") #print("[W] mkdir, some error, directory probably exists")
pass
def download_pdf(url, header_data): def download_pdf(url, header_data):
''' downloading the pdfile for later analysis ''' ''' downloading the pdfile for later analysis '''
req = requests.get(url,headers=header_data) try:
data = req.content req = requests.get(url,headers=header_data,verify=True)
#data = req.text #req = requests.get(url,headers=header_data,verify=False)
print(len(data)) data = req.content
except requests.exceptions.SSLError as e:
print('Error: %s' % e)
return -1
except:
print('Error: Probably something wrong with remote server')
return -1
#print(len(data))
return data return data
def store_pdf(url,data,outdir): def store_pdf(url,data,outdir):
@@ -83,7 +96,11 @@ def _parse_pdf(filename):
print('[-] Error: %s' % (e)) print('[-] Error: %s' % (e))
return return
extract = h.documentInfo try:
extract = h.documentInfo
except pdf.utils.PdfReadError as e:
print('Error: %s' % e)
return -1
print('-'*80) print('-'*80)
print('File: %s' % filename) print('File: %s' % filename)
@@ -102,8 +119,9 @@ def grab_url(url, outdir):
just one pdf and analysing it just one pdf and analysing it
''' '''
data = download_pdf(url,None) data = download_pdf(url,None)
savepath = store_pdf(url, data, outdir) if data != -1:
_parse_pdf(savepath) savepath = store_pdf(url, data, outdir)
_parse_pdf(savepath)
return return
@@ -123,7 +141,7 @@ def search_pdf(search, sargs):
query='%s filetype:pdf' % search query='%s filetype:pdf' % search
#print(query) #print(query)
urls = [] urls = []
for url in gs.search(query,stop=10): for url in gs.search(query,stop=sargs):
print(url) print(url)
urls.append(url) urls.append(url)
@@ -150,7 +168,7 @@ def run(args):
elif args.search: elif args.search:
search = args.search search = args.search
print(args) #print(args)
print('[+] Seek and de...erm...analysing %s' % (search)) print('[+] Seek and de...erm...analysing %s' % (search))
sargs=10 sargs=10
seek_and_analyse(search,sargs,outdir) seek_and_analyse(search,sargs,outdir)