def downloadpdf(url):
try:
request = requests.get(url, verify=False)
if request.headers['Content-Type'] == 'text/html':
return None
except requests.exceptions.ConnectionError:
sys.exit(
"\nThere was an error when trying to connect to the domain. Please confirm if the domain is correctly written.\n"
)
try:
objbyte = BytesIO(request.content)
except Exception as e:
print(e)
return None
try:
s_stdout = sys.stdout
sys.stdout = BytesIO()
pdf = PdfFileReader(objbyte)
sys.stdout = s_stdout
except Exception as e:
print(e)
return None
if pdf.getIsEncrypted() is True:
try:
pdf.decrypt('')
except:
pdf = Scratcher.handlepdf(request.content)
return pdf
def add_watermark(pdf_file_in, pdf_file_mark, pdf_file_out):
"""添加水印
"""
pdf_output = PdfFileWriter()
input_stream = open(pdf_file_in, 'rb')
pdf_input = PdfFileReader(input_stream)
# PDF文件被加密了
if pdf_input.getIsEncrypted():
print('该PDF文件被加密了.')
# 尝试用空密码解密
try:
pdf_input.decrypt('')
except Exception as e:
print('尝试用空密码解密失败.')
return False
else:
print('用空密码解密成功.')
# 获取PDF文件的页数
page_num = pdf_input.getNumPages()
# 读入水印pdf文件
pdf_watermark_input_stream = open(pdf_file_mark, 'rb')
pdf_watermark = PdfFileReader(pdf_watermark_input_stream)
# 给每一页打水印
for i in range(page_num):
page = pdf_input.getPage(i)
page.mergePage(pdf_watermark.getPage(0))
page.compressContentStreams() # 压缩内容
pdf_output.addPage(page)
output_stream = open(pdf_file_out, "wb")
pdf_output.write(output_stream)
input_stream.close()
pdf_watermark_input_stream.close()
output_stream.close()
def add_watermark(pdf_file_mark, pdf_file_in, pdf_file_out):
with open(pdf_file_in, 'rb') as fp:
pdf_input = PdfFileReader(fp)
# PDF文件被加密了
if pdf_input.getIsEncrypted():
print('该PDF文件被加密了.')
# 尝试用空密码解密
try:
pdf_input.decrypt('')
except Exception:
print('尝试用空密码解密失败.')
return False
else:
print('用空密码解密成功.')
# 获取PDF文件的页数
pageNum = pdf_input.getNumPages()
with open(pdf_file_mark, 'rb') as mfp:
pdf_output = PdfFileWriter()
# 读入水印pdf文件
pdf_watermark = PdfFileReader(mfp)
# 给每一页打水印
for i in range(pageNum):
page = pdf_input.getPage(i)
page.mergePage(pdf_watermark.getPage(0))
page.compressContentStreams() # 压缩内容
pdf_output.addPage(page)
with open(pdf_file_out, 'wb') as wfp:
pdf_output.write(wfp)
def downloadpdf(url):
try:
request = requests.get(url, verify=False)
if 'Content-Type' in request.headers.keys():
if request.headers['Content-Type'] == 'text/html':
return None
except requests.exceptions.ConnectionError:
sys.exit(
"\nThere was an error when trying to connect to the domain. Please confirm if the domain is "
"correctly written.\n")
try:
objbyte = BytesIO(request.content)
except Exception as e:
Scratcher.log(url, e)
sys.exit(
"\nThere was an error when trying to convert the content of the response.Please verify the logs to"
" see the raised error.\n")
try:
pdf = PdfFileReader(objbyte)
except utils.PdfReadError as e:
Scratcher.log(url, e)
obje = BytesIO(request.content.strip(b'\x00'))
try:
pdf = PdfFileReader(obje)
except utils.PdfReadError:
return 2
if pdf.getIsEncrypted() is True:
try:
pdf.decrypt('')
except:
pdf = Scratcher.handlepdf(request.content)
return pdf
def add_watermark(pdf_file_in, pdf_file_mark, pdf_file_out):
"""添加水印
"""
pdf_output = PdfFileWriter()
input_stream = open(pdf_file_in, 'rb')
pdf_input = PdfFileReader(input_stream)
# PDF文件被加密了
if pdf_input.getIsEncrypted():
print('该PDF文件被加密了.')
# 尝试用空密码解密
try:
pdf_input.decrypt('')
except Exception as e:
print('尝试用空密码解密失败.')
return False
else:
print('用空密码解密成功.')
# 获取PDF文件的页数
page_num = pdf_input.getNumPages()
# 读入水印pdf文件
pdf_watermark_input_stream = open(pdf_file_mark, 'rb')
pdf_watermark = PdfFileReader(pdf_watermark_input_stream)
# 给每一页打水印
for i in range(page_num):
page = pdf_input.getPage(i)
page.mergePage(pdf_watermark.getPage(0))
page.compressContentStreams() # 压缩内容
pdf_output.addPage(page)
output_stream = open(pdf_file_out, "wb")
pdf_output.write(output_stream)
input_stream.close()
pdf_watermark_input_stream.close()
output_stream.close()
def _get_pdf_document_info(fp):
try:
pdf = PdfFileReader(fp)
if pdf.getIsEncrypted():
# Some PDFs are "encrypted" with an empty password: give that a
# shot...
if not pdf.decrypt(""):
return None
return pdf.getDocumentInfo()
except FileNotFoundError:
return None
def add_watermark(pdf_file_in, pdf_file_mark, pdf_file_out):
pdf_output = PdfFileWriter()
input_stream = file(pdf_file_in, 'rb')
pdf_input = PdfFileReader(input_stream, strict=False)
# PDF文件被加密了
if pdf_input.getIsEncrypted():
print '该PDF文件被加密了.'
# 尝试用空密码解密
try:
pdf_input.decrypt('')
except Exception, e:
return False
else:
print '用空密码解密成功.'
def add_watermark(pdf_file_in, pdf_file_mark, pdf_file_out):
pdf_output = PdfFileWriter()
input_stream = file(pdf_file_in, 'rb')
pdf_input = PdfFileReader(input_stream)
# PDF文件被加密了
if pdf_input.getIsEncrypted():
print '该PDF文件被加密了.'
# 尝试用空密码解密
try:
pdf_input.decrypt('')
except Exception, e:
print '尝试用空密码解密失败.'
return False
else:
print '用空密码解密成功.'
def __Get_info(file_path, plain_log, csv_log, analyzed_files, total_files):
"""
Get_info(file_path)
Opens the pdf file for reading.
Args:
- file_path: (string) Absolute file path.
- plain_log: (None | string) Log file in plain text.
- csv_log: (None | string) Log file in csv format.
"""
file_name = os.path.basename(file_path)
file_size = os.path.getsize(file_path)
encrypted = 'No'
try: # Try to open not password encrypted pdf files and pdf files
# encrypted with a blank password.
pdf_file = PdfFileReader(file(file_path, 'rb'))
if pdf_file.getIsEncrypted() is True:
dec_res = pdf_file.decrypt('')
if dec_res == 1:
encrypted = 'Yes'
#Get and parse metadata
doc_info = pdf_file.getDocumentInfo()
title, author, creator, subject, producer, c_date, m_date \
= __Parse_doc_info(doc_info)
num_pages = pdf_file.getNumPages()
#Group info
pdf_meta = pdf_metadata(file_name, title, author, creator, subject,
producer, c_date, m_date, encrypted, num_pages,
file_size)
__Print_metadata(pdf_meta)
if plain_log:
Log(file_name, pdf_meta, plain_log, 'txt')
if csv_log:
Log(file_name, pdf_meta, f_log_csv, 'csv')
analyzed_files = analyzed_files + 1
except Exception, e:
error = file_name + ' ' + str(e)
__Print_error(error)
def __Get_info(file_path, plain_log, csv_log, analyzed_files, total_files):
"""
Get_info(file_path)
Opens the pdf file for reading.
Args:
- file_path: (string) Absolute file path.
- plain_log: (None | string) Log file in plain text.
- csv_log: (None | string) Log file in csv format.
"""
file_name = os.path.basename(file_path)
file_size = os.path.getsize(file_path)
encrypted = 'No'
try: # Try to open not password encrypted pdf files and pdf files
# encrypted with a blank password.
pdf_file = PdfFileReader(file(file_path, 'rb'))
if pdf_file.getIsEncrypted() is True:
dec_res = pdf_file.decrypt('')
if dec_res == 1:
encrypted = 'Yes'
#Get and parse metadata
doc_info = pdf_file.getDocumentInfo()
title, author, creator, subject, producer, c_date, m_date \
= __Parse_doc_info(doc_info)
num_pages = pdf_file.getNumPages()
#Group info
pdf_meta = pdf_metadata(file_name, title, author, creator,
subject, producer, c_date, m_date,
encrypted, num_pages, file_size)
__Print_metadata(pdf_meta)
if plain_log:
Log(file_name, pdf_meta, plain_log, 'txt')
if csv_log:
Log(file_name, pdf_meta, f_log_csv, 'csv')
analyzed_files = analyzed_files + 1
except Exception, e:
error = file_name + ' ' + str(e)
__Print_error(error)
def merge_files(local_pdfs):
name = 'merge_{0}_output.pdf'.format(str(time.clock())[2:])
merged_export = PdfFileMerger()
for pdfile in local_pdfs:
filepath = getpath(pdfile, config().get(section='server', option='upload_folder'))
file_bin = PdfFileReader(file(filepath, 'rb'))
if file_bin.getIsEncrypted():
file_bin.decrypt('')
merged_export.append(fileobj=file_bin)
os.remove(filepath)
full_ouput = getpath(name, config().get(section='server', option='upload_folder'))
with open(full_ouput, 'wb') as output:
merged_export.write(output)
return full_ouput
def split_pdf(pdf_filename, temp_dir):
'''
Split the PDF into n PDFs ( one for each page ).
'''
filenames = []
inputpdf = PdfFileReader(open(pdf_filename, "rb"))
if inputpdf.getIsEncrypted():
inputpdf.decrypt('')
for i in range(inputpdf.numPages):
output = PdfFileWriter()
output.addPage(inputpdf.getPage(i))
filename = os.path.basename(pdf_filename)
filename = "{0}/{1}-p{2}.pdf".format(temp_dir, filename, i)
with open(filename, "wb") as outputStream:
output.write(outputStream)
filenames.append(filename)
return filenames
def split_pdf(pdf_filename):
filenames = []
inputpdf = PdfFileReader(open(pdf_filename, "rb"))
if inputpdf.getIsEncrypted():
inputpdf.decrypt('')
for i in range(inputpdf.numPages):
output = PdfFileWriter()
output.addPage(inputpdf.getPage(i))
directory = os.path.dirname(pdf_filename)
if directory == '':
directory = '.'
filename = os.path.basename(pdf_filename)
filename = "{0}/{1}-p{2}.pdf".format(directory,filename,i)
with open(filename, "wb") as outputStream:
output.write(outputStream)
filenames.append(filename)
return filenames
def extract_pdf_metadata(filepath: Path):
metadata = dict()
try:
metadata['pdf_file_size_bytes'] = filepath.stat().st_size
with filepath.open('rb') as handle:
pdf = PdfFileReader(handle)
metadata['pdf_is_encrypted'] = pdf.getIsEncrypted()
metadata['pdf_number_of_pages'] = pdf.getNumPages()
for key, val in pdf.getDocumentInfo().items():
metadata[key] = str(val)
except Exception as e:
error_msg = f'Failed to read metadata of {filepath}, error: {e}'
logger.error(error_msg)
return error_msg, None
return constants.RETURNCODE_OK, metadata
def main():
parser = OptionParser('usage %prog -F'+'<target_File>'+'-P <password_File>')
parser.add_option("-F", dest="targetFile", type='string',
help="target PDF File")
parser.add_option("-P", dest="PasswordFile", type='string',
help="Password File")
(options, args) = parser.parse_args()
if(options.targetFile == None)|(options.PasswordFile == None):
print parser.usage
exit(0)
else:
pdfFile = options.targetFile
PasswordFile = options.PasswordFile
pdfFileReader = PdfFileReader(file(pdfFile,'rb'))
if pdfFileReader.getIsEncrypted():
fp = open(PasswordFile,'r')
for line in fp.readlines():
passWord = line.strip('\r').strip('\n')
if(crackPdf(pdfFile, passWord, pdfFileReader)):
fp.close()
return True
fp.close()
else:
print '[*] PDF File '+pdfFile+' no encrypted!'
def print_pdf(file_full_path):
# Header with file path
cprint("[+] Metadata for file: %s " % (file_full_path),
"green",
attrs=['bold'])
# Open the file
pdf_file = PdfFileReader(file(file_full_path, 'rb'))
# Create a dictorionary with the info
pdf_info = pdf_file.getDocumentInfo()
# Print metadata
if pdf_info:
for metaItem in pdf_info:
try:
cprint('\t ' + metaItem[1:] + ': ', 'cyan', end="")
cprint(pdf_info[metaItem])
except TypeError:
cprint(
'\t ' + metaItem[1:] + ': ' + 'Error - Item not redeable',
'red')
else:
cprint('Not data found', 'red')
# Print other info
cprint("\t Number of pages: %s" % pdf_file.getNumPages(), 'cyan')
cprint("\t Is Encripted: %s" % pdf_file.getIsEncrypted(), 'cyan')
def process_file(self, curr_file):
"""Function to process the provided file. If the file is a PDF, the PyPDF2 library will be
used. Otherwise, the extract tool is used, so extract must be installed. This is the one
piece that requires Linux.
"""
global ED_FROM
author = '-'
date = '-'
generator = '-'
created = '-'
producer = '-'
modded = '-'
last_saved = '-'
if ".pdf" in curr_file:
try:
pdf_file = PdfFileReader(open(curr_file, 'rb'))
if pdf_file.getIsEncrypted():
pdf_file.decrypt('')
doc_info = pdf_file.getDocumentInfo()
if not doc_info:
return
last_saved = '-'
# Looks at the entire dictionary to parse for information
if "/CreationDate" in doc_info:
data = doc_info["/CreationDate"].strip("D:|'")
year = data[0:4]
date = data[4:6] + "/" + data[6:8]
created_time = data[8:10] + ":" + data[10:12]
created_time = time.strftime(
"%I:%M %p", time.strptime(created_time, "%H:%M"))
created = date + "/" + year + " " + created_time
if "/Author" in doc_info:
author = doc_info["/Author"] + " "
if len(author) <= 1:
author = "-"
if "/Producer" in doc_info:
producer = doc_info["/Producer"].strip("(Windows)")
producer = re.sub(r'[^\w]', ' ', producer)
if len(producer) == 0:
producer = "-"
while True:
if " " in producer:
producer = producer.replace(" ", " ")
else:
break
if "/ModDate" in doc_info:
data = doc_info["/ModDate"].strip("D:|'")
year = data[0:4]
date = data[4:6] + "/" + data[6:8]
modded_time = data[8:10] + ":" + data[10:12]
modded_time = time.strftime(
"%I:%M %p", time.strptime(modded_time, "%H:%M"))
modded = date + "/" + year + " " + modded_time
# Strips '/' off filename (if it includes directory name)
if "/" in curr_file:
curr_file = curr_file[curr_file.rfind("/") + 1:]
if "\\" in curr_file:
curr_file = curr_file.replace("\\", "")
if len(producer) > 30:
producer = producer[:20] + " [snipped] "
if len(author) > 20:
author = author[:20] + " [snipped] "
# Appends each piece of information
# Output will show ONLY if at least ONE file has data in a column
self.container.append(
[curr_file, created, author, producer, modded, last_saved])
except Exception:
return
else:
try:
curr_file = curr_file.replace(" ", "\ ").replace("(", "\(")\
.replace(")", "\)")
try:
extract_status = subprocess.getstatusoutput("extract")
except:
print(
yellow(
"[*] We found an Office document, but 'extract' is not installed \
on this system to get the metadata. It is downloaded for later analysis."))
if extract_status[0] == 0:
output = subprocess.check_output("extract -V " + curr_file, shell=True)\
.decode('utf-8').split('\n')
if "extract: not found" in output[0]:
print(
red("[!] PyFOCA requires the 'extract' command."))
print(
red("L.. Please install extract by typing 'apt-get install extract' \
in terminal."))
for i in output:
if "creator" in i:
author = i[i.find("-") + 2:]
rem_alphanumeric = re.compile(r'\W')
author = re.sub(rem_alphanumeric, ' ', author)
while True:
if " " in author:
author = author.replace(" ", " ")
elif author[0] == " ":
author = author[1:]
else:
break
elif "date" in i and "creation" not in i:
year = i[i.find('-') + 2:(i.find('-') + 2) + 4]
date = i[i.find(year) + 5:(i.find(year) + 5) +
5].replace("-", "/")
modded_time = i[i.find(":") - 2:i.rfind(":") - 1]
modded_time = time.strftime(
"%I:%M %p",
time.strptime(modded_time, "%H:%M"))
modded = date + "/" + year + " " + modded_time
elif "generator" in i:
producer = i[i.find('-') + 2:]
elif "creation" in i:
year = i[i.find('-') + 2:(i.find('-') + 2) + 4]
date = i[i.find(year) + 5:(i.find(year) + 5) +
5].replace("-", "/")
created_time = i[i.find(":") - 2:i.rfind(":") - 1]
created_time = time.strftime(
"%I:%M %p",
time.strptime(created_time, "%H:%M"))
created = date + "/" + year + " " + created_time
elif "last saved" in i:
last_saved = i[i.find('-') + 2:]
if "/" in curr_file:
curr_file = curr_file[curr_file.rfind("/") + 1:]
if "\\" in curr_file:
curr_file = curr_file.replace("\\", "")
if author != "-" or date != "-" or generator != "-" or created != "-" or \
producer != "-" or modded != "-" or last_saved != "-":
self.container.append([
" | " + curr_file, created, author, producer,
modded, last_saved
])
else:
print(
yellow(
"[*] We found an Office document, but 'extract' is not installed \
on this system to get the metadata. It is downloaded for later analysis."))
except Exception as error:
if "command not found" in str(error):
print(red("[!] PyFOCA requires the 'extract' command."))
print(
red("L.. Please install on Linux extract by typing 'apt-get install extract' \
in terminal."))
# exit()
return
def info(pdf):
data = {}
with open(pdf, 'rb') as fd:
try:
pdfreader = PdfFileReader(fd)
data['pages'] = pdfreader.numPages
if pdfreader.getIsEncrypted():
pdfreader.decrypt('')
info = pdfreader.getDocumentInfo()
if info:
for key in info:
if info[key]:
try:
value = info[key]
if len(value) == 1:
value = value[0]
if isinstance(value, bytes):
value = value.decode('utf-16')
data[key[1:].lower()] = value
except:
pass
xmp = pdfreader.getXmpMetadata()
if xmp:
for key in dir(xmp):
if key.startswith('dc_'):
value = getattr(xmp, key)
if isinstance(value, dict) and 'x-default' in value:
value = value['x-default']
elif isinstance(value, list):
value = [
v.strip() if isinstance(v, str) else v
for v in value if v
]
value = [
v.strftime('%Y-%m-%d') if isinstance(
v, datetime) else v for v in value
]
if len(value) == 1:
value = value[0]
_key = key[3:]
if value and _key not in data:
data[_key] = value
except:
logger.debug('FAILED TO PARSE %s', pdf, exc_info=1)
'''
cmd = ['pdfinfo', pdf]
p = subprocess.Popen(cmd, stdout=subprocess.PIPE, stderr=subprocess.PIPE, close_fds=True)
stdout, stderr = p.communicate()
for line in stdout.strip().split('\n'):
parts = line.split(':')
key = parts[0].lower().strip()
if key:
data[key] = ':'.join(parts[1:]).strip()
for key in data.keys():
if not data[key]:
del data[key]
'''
if 'identifier' in data:
value = normalize_isbn(data['identifier'])
if stdnum.isbn.is_valid(value):
data['isbn'] = [value]
del data['identifier']
for key, value in data.items():
if isinstance(value, dict):
value = ' '.join(list(value.values()))
data[key] = value.strip()
for key in list(data):
if data[key] in ('Unknown', ):
del data[key]
if key == 'language':
data[key] = get_language(data[key])
text = extract_text(pdf)
data['textsize'] = len(text)
if settings.server['extract_text']:
if not 'isbn' in data:
isbn = extract_isbn(text)
if isbn:
data['isbn'] = [isbn]
if 'isbn' in data and isinstance(data['isbn'], str):
data['isbn'] = [data['isbn']]
if 'date' in data and len(data['date']) == 8 and data['date'].isdigit():
d = data['date']
data['date'] = '%s-%s-%s' % (d[:4], d[4:6], d[6:])
if 'author' in data and isinstance(data['author'], str):
data['author'] = data['author'].split(', ')
return data
def process_file(self,curr_file):
"""Process the provided file. If the file is a PDF, the PyPDF2 library will be used.
Otherwise, the extract tool is used, so extract must be installed. This is the one
piece that requires Linux.
Parameters:
curr_file The filepath of the file to be processed
"""
date = "None"
modded = "None"
author = "None"
created = "None"
producer = "None"
last_saved = "None"
# Process the current file as a PDF
if ".pdf" in curr_file:
try:
pdf_file = PdfFileReader(open(curr_file,"rb"))
if pdf_file.getIsEncrypted():
pdf_file.decrypt('')
# getDocumentInfo() returns something like:
# {'/Author': 'Chris Maddalena',
# '/CreationDate': "D:20131014182824-04'00'",
# '/Creator': 'Microsoft® Excel® 2013',1
# '/ModDate': "D:20131015141200-04'00'",
# '/Producer': 'Microsoft® Excel® 2013'}
doc_info = pdf_file.getDocumentInfo()
# If there is no info, just return
if not doc_info:
return
# Parse the document into
if "/CreationDate" in doc_info:
data = doc_info["/CreationDate"].strip("D:|'")
year = data[0:4]
date = data[4:6] + "/" + data[6:8]
created_time = data[8:10] + ":" + data[10:12]
created_time = time.strftime("%I:%M %p",time.strptime(created_time,"%H:%M"))
created = date + "/" + year + " " + created_time
if "/Author" in doc_info:
author = doc_info["/Author"]
if "/Producer" in doc_info:
producer = doc_info["/Producer"].strip("(Windows)")
producer = re.sub(r'[^\w]',' ',producer)
while True:
if " " in producer:
producer = producer.replace(" "," ")
else:
break
if "/ModDate" in doc_info:
data = doc_info["/ModDate"].strip("D:|'")
year = data[0:4]
date = data[4:6] + "/" + data[6:8]
modded_time = data[8:10] + ":" + data[10:12]
modded_time = time.strftime("%I:%M %p",time.strptime(modded_time,"%H:%M"))
modded = date + "/" + year + " " + modded_time
# Strips '/' off filename (if it includes directory name)
if "/" in curr_file:
curr_file = curr_file[curr_file.rfind("/")+1:]
if "\\" in curr_file:
curr_file = curr_file.replace("\\","")
# Add the document info to the container
self.container.append([curr_file,created,author,producer,modded,last_saved])
except Exception:
return
# Not a PDF, so treat the current file as an Office doc
else:
curr_file = curr_file.replace(" ","\ ").replace("(","\(").replace(")","\)")
try:
# Unzip the contents of the document to get the contents of core.xml and app.xml files
unzipped = zipfile.ZipFile(curr_file)
doc_xml = lxml.etree.fromstring(unzipped.read("docProps/core.xml"))
app_xml = lxml.etree.fromstring(unzipped.read("docProps/app.xml"))
# Namespaces for doc.xml
dc_ns = {"dc":"http://purl.org/dc/elements/1.1/"}
cp_ns = {"cp":"http://schemas.openxmlformats.org/package/2006/metadata/core-properties"}
dcterms_ns = {"dcterms":"http://purl.org/dc/terms/"}
# Namespaces for app.xml:
# app_ns = {"http://schemas.openxmlformats.org/officeDocument/2006/extended-properties"}
# vt_ns = {"vt": "http://schemas.openxmlformats.org/officeDocument/2006/docPropsVTypes"}
# tags = doc_xml.xpath('//cp:keywords', namespaces=cp_ns)[0].text
# description = doc_xml.xpath('//dc:description', namespaces=dc_ns)[0].text
author = doc_xml.xpath('//dc:creator',namespaces=dc_ns)[0].text
modded = doc_xml.xpath('//cp:lastModifiedBy',namespaces=cp_ns)[0].text
created = doc_xml.xpath('//dcterms:created',namespaces=dcterms_ns)[0].text
last_saved = doc_xml.xpath('//dcterms:modified',namespaces=dcterms_ns)[0].text
# Convert the created time to a prettier format
created_date = created.split("T")[0]
created_time = created.split("T")[1].strip("Z")
modded_time = time.strftime("%I:%M %p",time.strptime(created_time,"%H:%M:%S"))
created = created_date + " " + modded_time
# Determine the Office application and version that created this document
for child in app_xml:
if 'AppVersion' in child.tag:
office_version = child.text
if "16." in office_version:
version = "2016"
elif "15." in office_version:
version = "2013"
elif "14." in office_version:
version = "2010"
elif "12." in office_version:
version = "2007"
if ".xls" in curr_file:
producer = "Microsoft Excel " + version
elif ".doc" in curr_file:
producer = "Microsoft Word " + version
elif ".ppt" in curr_file:
producer = "Microsoft PowerPoint " + version
# Remove any slashes in the filename
if "/" in curr_file:
curr_file = curr_file[curr_file.rfind("/")+1:]
if "\\" in curr_file:
curr_file = curr_file.replace("\\","")
# Add the results to the container
self.container.append([curr_file,created,author,producer,modded,last_saved])
except Exception as error:
click.secho("[!] Failed to extract metadata from {}!".format(curr_file),fg="red")
click.secho("L.. Details: {}".format(error),fg="red")
pass
def processFile(self, curr_file):
global extractedFrom
author = '-'
date = '-'
generator = '-'
created = '-'
producer = '-'
modded = '-'
last_saved = '-'
if ".pdf" in curr_file:
try:
pdfFile = PdfFileReader(file(curr_file, 'rb'))
if pdfFile.getIsEncrypted():
pdfFile.decrypt('')
docInfo = pdfFile.getDocumentInfo()
if not docInfo:
return
last_saved = '-'
#looks at the entire dictionary to parse for information
if "/CreationDate" in docInfo:
data = docInfo["/CreationDate"].strip("D:|'")
year = data[0:4]
date = data[4:6] + "/" + data[6:8]
created_time = data[8:10] + ":" + data[10:12]
created_time = time.strftime(
"%I:%M %p", time.strptime(created_time, "%H:%M"))
created = date + "/" + year + " " + created_time
if "/Author" in docInfo:
author = docInfo["/Author"] + " "
if len(author) <= 1:
author = "-"
if "/Producer" in docInfo:
producer = docInfo["/Producer"].strip("(Windows)")
producer = re.sub(r'[^\w]', ' ', producer)
if len(producer) == 0:
producer = "-"
while True:
if " " in producer:
producer = producer.replace(" ", " ")
else:
break
if "/ModDate" in docInfo:
data = docInfo["/ModDate"].strip("D:|'")
year = data[0:4]
date = data[4:6] + "/" + data[6:8]
modded_time = data[8:10] + ":" + data[10:12]
modded_time = time.strftime(
"%I:%M %p", time.strptime(modded_time, "%H:%M"))
modded = date + "/" + year + " " + modded_time
#strips '/' off file name (if it includes directory name)
if "/" in curr_file:
curr_file = curr_file[curr_file.rfind("/") + 1:]
if "\\" in curr_file:
curr_file = curr_file.replace("\\", "")
#trim information if it's too long
if len(curr_file) > 15: # trims file name
curr_file = curr_file[:15] + "..." + curr_file[-13:]
if len(producer) > 30:
producer = producer[:20] + " [snipped] "
if len(author) > 20:
author = author[:20] + " [snipped] "
#appends each piece of information. output will show ONLY if at least ONE file has data in a column
self.container.append([
" | " + curr_file, created, author, producer, modded,
last_saved
])
except Exception, err:
return
def process_file(self, curr_file):
"""Process the provided file. If the file is a PDF, the PyPDF2 library will be used.
Otherwise, the extract tool is used, so extract must be installed. This is the one
piece that requires Linux.
Parameters:
curr_file The filepath of the file to be processed
"""
date = "None"
modded = "None"
author = "None"
created = "None"
producer = "None"
last_saved = "None"
# Process the current file as a PDF
if ".pdf" in curr_file:
try:
pdf_file = PdfFileReader(open(curr_file, "rb"))
if pdf_file.getIsEncrypted():
pdf_file.decrypt('')
# getDocumentInfo() returns something like:
# {'/Author': 'Chris Maddalena',
# '/CreationDate': "D:20131014182824-04'00'",
# '/Creator': 'Microsoft® Excel® 2013',1
# '/ModDate': "D:20131015141200-04'00'",
# '/Producer': 'Microsoft® Excel® 2013'}
doc_info = pdf_file.getDocumentInfo()
# If there is no info, just return
if not doc_info:
return
# Parse the document into
if "/CreationDate" in doc_info:
data = doc_info["/CreationDate"].strip("D:|'")
year = data[0:4]
date = data[4:6] + "/" + data[6:8]
created_time = data[8:10] + ":" + data[10:12]
created_time = time.strftime(
"%I:%M %p", time.strptime(created_time, "%H:%M"))
created = date + "/" + year + " " + created_time
if "/Author" in doc_info:
author = doc_info["/Author"]
if "/Producer" in doc_info:
producer = doc_info["/Producer"].strip("(Windows)")
producer = re.sub(r'[^\w]', ' ', producer)
while True:
if " " in producer:
producer = producer.replace(" ", " ")
else:
break
if "/ModDate" in doc_info:
data = doc_info["/ModDate"].strip("D:|'")
year = data[0:4]
date = data[4:6] + "/" + data[6:8]
modded_time = data[8:10] + ":" + data[10:12]
modded_time = time.strftime(
"%I:%M %p", time.strptime(modded_time, "%H:%M"))
modded = date + "/" + year + " " + modded_time
# Strips '/' off filename (if it includes directory name)
if "/" in curr_file:
curr_file = curr_file[curr_file.rfind("/") + 1:]
if "\\" in curr_file:
curr_file = curr_file.replace("\\", "")
# Add the document info to the container
self.container.append(
[curr_file, created, author, producer, modded, last_saved])
except Exception:
return
# Not a PDF, so treat the current file as an Office doc
else:
curr_file = curr_file.replace(" ", "\ ").replace("(",
"\(").replace(
")", "\)")
try:
# Unzip the contents of the document to get the contents of core.xml and app.xml files
unzipped = zipfile.ZipFile(curr_file)
doc_xml = lxml.etree.fromstring(
unzipped.read("docProps/core.xml"))
app_xml = lxml.etree.fromstring(
unzipped.read("docProps/app.xml"))
# Namespaces for doc.xml
dc_ns = {"dc": "http://purl.org/dc/elements/1.1/"}
cp_ns = {
"cp":
"http://schemas.openxmlformats.org/package/2006/metadata/core-properties"
}
dcterms_ns = {"dcterms": "http://purl.org/dc/terms/"}
# Namespaces for app.xml:
# app_ns = {"http://schemas.openxmlformats.org/officeDocument/2006/extended-properties"}
# vt_ns = {"vt": "http://schemas.openxmlformats.org/officeDocument/2006/docPropsVTypes"}
# tags = doc_xml.xpath('//cp:keywords', namespaces=cp_ns)[0].text
# description = doc_xml.xpath('//dc:description', namespaces=dc_ns)[0].text
author = doc_xml.xpath('//dc:creator',
namespaces=dc_ns)[0].text
modded = doc_xml.xpath('//cp:lastModifiedBy',
namespaces=cp_ns)[0].text
created = doc_xml.xpath('//dcterms:created',
namespaces=dcterms_ns)[0].text
last_saved = doc_xml.xpath('//dcterms:modified',
namespaces=dcterms_ns)[0].text
# Convert the created time to a prettier format
created_date = created.split("T")[0]
created_time = created.split("T")[1].strip("Z")
modded_time = time.strftime(
"%I:%M %p", time.strptime(created_time, "%H:%M:%S"))
created = created_date + " " + modded_time
# Determine the Office application and version that created this document
for child in app_xml:
if 'AppVersion' in child.tag:
office_version = child.text
if "16." in office_version:
version = "2016"
elif "15." in office_version:
version = "2013"
elif "14." in office_version:
version = "2010"
elif "12." in office_version:
version = "2007"
if ".xls" in curr_file:
producer = "Microsoft Excel " + version
elif ".doc" in curr_file:
producer = "Microsoft Word " + version
elif ".ppt" in curr_file:
producer = "Microsoft PowerPoint " + version
# Remove any slashes in the filename
if "/" in curr_file:
curr_file = curr_file[curr_file.rfind("/") + 1:]
if "\\" in curr_file:
curr_file = curr_file.replace("\\", "")
# Add the results to the container
self.container.append(
[curr_file, created, author, producer, modded, last_saved])
except Exception as error:
click.secho("[!] Failed to extract metadata from {}!".format(
curr_file),
fg="red")
click.secho("L.. Details: {}".format(error), fg="red")
pass
output.close()
print("Your hot 'n' ready PDF awaits.")
print(
"You'll find it this directory with '-reordered' appended to the filename."
)
if __name__ == "__main__":
pdf_path = input(
'Enter the path to your PDF (e.g. "path/to/your/pdf.pdf"): ').strip()
if pdf_path[-1] == '/':
pdf_path = pdf_path[0:-1]
regex = r"(?P<filename>[\w\-\_]+)(\.|$)"
title = re.search(regex, pdf_path).groupdict()['filename']
reader = PdfFileReader(pdf_path)
if reader.getIsEncrypted():
try:
reader.decrypt('')
except:
print(
"This file was detected as encrypted. Attempted to decrypt with empty password, but failed."
)
print(
"If this file is not encrypted with a password, you can try decrypting with QPDF."
)
print(
"Please make sure you have installed QPDF before saying yes to the following prompt..."
)
tryWithQPDF = input(
"Would you like to try decrypting with QPDF?: ")
if re.match(r"(y|Y|Yes|yes)", tryWithQPDF):
#!/usr/bin/python
from PyPDF2 import PdfFileReader
pdf_document = "file.pdf"
with open(pdf_document, "rb") as filehandle:
pdf = PdfFileReader(filehandle)
info = pdf.getDocumentInfo()
pages = pdf.getNumPages()
print('file information: ', info)
print("number of pages: %i" % pages)
page1 = pdf.getPage(0)
print(pdf.getIsEncrypted())
print(pdf.pageMode)
print(pdf.getFields())
print(pdf.stream)
print(pdf.flattenedPages)
print(page1)
print(page1.extractText())
def export_to_file(self, file_out, only_selected=False):
"""Export to file"""
selection = self.iconview.get_selected_items()
pdf_output = PdfFileWriter()
pdf_input = []
for pdfdoc in self.pdfqueue:
pdfdoc_inp = PdfFileReader(open(pdfdoc.copyname, 'rb'))
if pdfdoc_inp.getIsEncrypted():
try: # Workaround for lp:#355479
stat = pdfdoc_inp.decrypt('')
except:
stat = 0
if stat != 1:
errmsg = _(
'File %s is encrypted.\n'
'Support for encrypted files has not been implemented yet.\n'
'File export failed.') % pdfdoc.filename
raise Exception(errmsg)
#FIXME
#else
# ask for password and decrypt file
pdf_input.append(pdfdoc_inp)
for row in self.model:
if only_selected and row.path not in selection:
continue
# add pages from input to output document
nfile = row[2]
npage = row[3]
current_page = copy(pdf_input[nfile - 1].getPage(npage - 1))
angle = row[6]
angle0 = current_page.get("/Rotate", 0)
crop = [row[7], row[8], row[9], row[10]]
if angle != 0:
current_page.rotateClockwise(angle)
if crop != [0., 0., 0., 0.]:
rotate_times = int(round(((angle + angle0) % 360) / 90) % 4)
crop_init = crop
if rotate_times != 0:
perm = [0, 2, 1, 3]
for it in range(rotate_times):
perm.append(perm.pop(0))
perm.insert(1, perm.pop(2))
crop = [crop_init[perm[side]] for side in range(4)]
#(x1, y1) = current_page.cropBox.lowerLeft
#(x2, y2) = current_page.cropBox.upperRight
(x1,
y1) = [float(xy) for xy in current_page.mediaBox.lowerLeft]
(x2,
y2) = [float(xy) for xy in current_page.mediaBox.upperRight]
x1_new = int(x1 + (x2 - x1) * crop[0])
x2_new = int(x2 - (x2 - x1) * crop[1])
y1_new = int(y1 + (y2 - y1) * crop[3])
y2_new = int(y2 - (y2 - y1) * crop[2])
#current_page.cropBox.lowerLeft = (x1_new, y1_new)
#current_page.cropBox.upperRight = (x2_new, y2_new)
current_page.mediaBox.lowerLeft = (x1_new, y1_new)
current_page.mediaBox.upperRight = (x2_new, y2_new)
pdf_output.addPage(current_page)
# finally, write "output" to document-output.pdf
pdf_output.write(open(file_out, 'wb'))
def info(pdf):
data = {}
with open(pdf, 'rb') as fd:
try:
pdfreader = PdfFileReader(fd)
data['pages'] = pdfreader.numPages
if pdfreader.getIsEncrypted():
pdfreader.decrypt('')
info = pdfreader.getDocumentInfo()
if info:
for key in info:
if info[key]:
try:
value = info[key]
if len(value) == 1:
value = value[0]
if isinstance(value, bytes):
value = value.decode('utf-16')
data[key[1:].lower()] = value
except:
pass
xmp = pdfreader.getXmpMetadata()
if xmp:
for key in dir(xmp):
if key.startswith('dc_'):
value = getattr(xmp, key)
if isinstance(value, dict) and 'x-default' in value:
value = value['x-default']
elif isinstance(value, list):
value = [v.strip() if isinstance(v, str) else v for v in value if v]
value = [v.strftime('%Y-%m-%d') if isinstance(v, datetime) else v for v in value]
if len(value) == 1:
value = value[0]
_key = key[3:]
if value and _key not in data:
data[_key] = value
except:
logger.debug('FAILED TO PARSE %s', pdf, exc_info=1)
'''
cmd = ['pdfinfo', pdf]
p = subprocess.Popen(cmd, stdout=subprocess.PIPE, stderr=subprocess.PIPE, close_fds=True)
stdout, stderr = p.communicate()
for line in stdout.strip().split('\n'):
parts = line.split(':')
key = parts[0].lower().strip()
if key:
data[key] = ':'.join(parts[1:]).strip()
for key in data.keys():
if not data[key]:
del data[key]
'''
if 'identifier' in data:
value = normalize_isbn(data['identifier'])
if stdnum.isbn.is_valid(value):
data['isbn'] = [value]
del data['identifier']
for key, value in data.items():
if isinstance(value, dict):
value = ' '.join(list(value.values()))
data[key] = value.strip()
for key in list(data):
if data[key] in ('Unknown',):
del data[key]
if key == 'language':
data[key] = get_language(data[key])
text = extract_text(pdf)
data['textsize'] = len(text)
if settings.server['extract_text']:
if not 'isbn' in data:
isbn = extract_isbn(text)
if isbn:
data['isbn'] = [isbn]
if 'isbn' in data and isinstance(data['isbn'], str):
data['isbn'] = [data['isbn']]
if 'date' in data and len(data['date']) == 8 and data['date'].isdigit():
d = data['date']
data['date'] = '%s-%s-%s' % (d[:4], d[4:6], d[6:])
if 'author' in data and isinstance(data['author'], str):
data['author'] = data['author'].split(', ')
return data
