def pdf_to_text(path_in, path_out):
if (conf.get_prop("use_pdf2txt") == '0'):
try:
from pdfminer.pdfdocument import PDFDocument
from pdfminer.pdfparser import PDFParser
from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter
from pdfminer.pdfdevice import PDFDevice, TagExtractor
from pdfminer.pdfpage import PDFPage
from pdfminer.converter import XMLConverter, HTMLConverter, TextConverter
from pdfminer.cmapdb import CMapDB
from pdfminer.layout import LAParams
from pdfminer.image import ImageWriter
except:
print ("system doesn't have PDFminer.six library installed. Try to use pdf2txt.")
conf.set_prop("use_pdf2txt", "1")
if (conf.get_prop("use_pdf2txt") == '0'):
rsrcmgr = PDFResourceManager(caching=True)
outfp = open(path_out, 'w')
codec = 'utf-8'
laparams = LAParams()
imagewriter = None
device = TextConverter(rsrcmgr, outfp, codec=codec, laparams=laparams, imagewriter=imagewriter)
fp = open(path_in, 'rb')
interpreter = PDFPageInterpreter(rsrcmgr, device)
for page in PDFPage.get_pages(fp, set(), caching=True, check_extractable=True):
interpreter.process_page(page)
fp.close()
device.close()
outfp.close()
def get_image_ids(swf_path):
# gets the output of swftools
swfextractOut = str(subprocess.check_output([conf.get_prop("swftools_path") +\
"swfextract", swf_path]))
# finds the string with the JPEG ids
beginpoint = swfextractOut.find("JPEG")
if (beginpoint is not -1):
ids = []
# finds start/end of the juicy bits
startpoint = swfextractOut.find(")", beginpoint) + 2
endpoint = swfextractOut.find('\\n', beginpoint)
idsStr = swfextractOut[startpoint:endpoint]
# prints debug info
print("starting point: " + str(startpoint))
print("ending point: " + str(endpoint))
print(swfextractOut[startpoint:endpoint])
if (idsStr.find(",") == -1): return [int(idsStr)]
else:
for idStr in idsStr.split(","):
ids.append(int(idStr))
return ids
return []
def extract_images(swf_path, out_dir):
# gets ids for images in SWF
imageIds = get_image_ids(swf_path)
# use swfextract to extract images based off id
for imageId in imageIds:
os.system(conf.get_prop("swftools_path") + "swfextract -j " + str(imageId) +\
" -o " + out_dir + "/" + str(imageId) + ".jpg " + swf_path)
def extract_audio(swf_path, out_path):
os.system(conf.get_prop("swftools_path") + "swfextract -m -o " + out_path + " " + swf_path)
if (len(sys.argv) == 1):
print("0 = gets_swf.fetch_all")
print("1 = gets_swf.extract_audio")
print("2 = gets_swf.extract_audio_all")
print("3 = gets_swf.convert_pdf")
print("4 = conf.set_prop")
print("5 = conf.get_prop")
print("6 = conf.check_prop_exists")
print("7 = gets_swf.gets_image_IDs")
print("8 = extract_images")
print("9 = extract_images_all")
print("10 = gets_swf.get_linked_text")
print("11 = gets_swf.get_linked_text_all")
else:
if (sys.argv[1] == "0"): gets_swf.fetch_all(sys.argv[2], sys.argv[3])
if (sys.argv[1] == "1"):
gets_swf.extract_audio(sys.argv[2], sys.argv[3])
if (sys.argv[1] == "2"): gets_swf.extract_audio_all(sys.argv[2])
if (sys.argv[1] == "3"): gets_swf.convert_pdf(sys.argv[2], sys.argv[3])
if (sys.argv[1] == "4"): conf.set_prop(sys.argv[2], sys.argv[3])
if (sys.argv[1] == "5"): print(conf.get_prop(sys.argv[2]))
if (sys.argv[1] == "6"): print(conf.check_prop_exist(sys.argv[2]))
if (sys.argv[1] == "7"): print(gets_swf.get_image_ids(sys.argv[2]))
if (sys.argv[1] == "8"):
gets_swf.extract_images(sys.argv[2], sys.argv[3])
if (sys.argv[1] == "9"): gets_swf.extract_images_all(sys.argv[2])
if (sys.argv[1] == "10"):
print(gets_swf.get_linked_text(sys.argv[2], sys.argv[3]))
if (sys.argv[1] == "11"): gets_swf.get_linked_text_all(sys.argv[2])
if (not os.path.exists(arguments[1])):
#print ("Could not find path " + arguments[1])
#sys.exit(0)
os.system("mkdir " + arguments[1])
# the code expects paths to end in '/'s so append them if needed
if (not arguments[0].endswith("/")): arguments[0] = arguments[0] + "/"
if (not arguments[1].endswith("/")): arguments[1] = arguments[1] + "/"
# set output_dir
conf.set_prop("output_dir", arguments[1])
kewUrl = arguments[0]
print("STEP 1: Acquiring KEW slides from server")
gets_swf.fetch_all(kewUrl, conf.get_prop("output_dir"))
print("STEP 2: Fetching linked text")
gets_swf.get_linked_text_all(conf.get_prop("output_dir"))
print("STEP 3: Extracting audio")
gets_swf.extract_audio_all(conf.get_prop("output_dir"))
print("STEP 4: Extracting images")
gets_swf.extract_images_all(conf.get_prop("output_dir"))
gets_swf.clean_up_all(conf.get_prop("output_dir"))
if (len(arguments) > 2):
if (arguments[2] == "-z"):
# remove '/' at end of string
zip_dir = conf.get_prop("output_dir")
if (zip_dir.endswith("/")): zip_dir = zip_dir[:-1]
# run zip on output_dir and delete the original directory