def extract_to_text(i):
# The pdfReader variable is a readable object that will be parsed
path = get_path()
pdf_file_path = get_path(i, ".pdf")
txt_file_path = get_path(i, ".txt")
if not os.path.exists(path):
os.makedirs(path)
if not os.path.exists(txt_file_path):
mock_test_file = get_past_paper(i)
with open(pdf_file_path, "wb") as f:
f.write(mock_test_file)
s = 'pdf2txt -o%s %s' % (txt_file_path, pdf_file_path)
pdf2txt.main(s.split(' ')[1:])
os.remove(pdf_file_path)
with open(txt_file_path, "r+", encoding="utf-8") as f:
tmp_text = f.read()
clean_mock_paper_text = filter_mock_paper_text(tmp_text)
with open(txt_file_path, "wb") as f:
f.write(str.encode(clean_mock_paper_text))
return clean_mock_paper_text
def run(datapath, filename, options=None):
i = path + datapath + filename + '.pdf'
o = path + filename + '.txt'
if options:
s = 'pdf2txt -o%s %s %s' % (o, options, i)
else:
s = 'pdf2txt -o%s %s' % (o, i)
pdf2txt.main(s.split(' ')[1:])
def run(datapath,filename,options=None):
i=path+datapath+filename+'.pdf'
o=path+filename+'.txt'
if options:
s='pdf2txt -o%s %s %s'%(o,options,i)
else:
s='pdf2txt -o%s %s'%(o,i)
pdf2txt.main(s.split(' ')[1:])
def run(sample_path, options=None):
absolute_path = absolute_sample_path(sample_path)
with NamedTemporaryFile() as output_file:
if options:
s = 'pdf2txt -o{} {} {}' \
.format(output_file.name, options, absolute_path)
else:
s = 'pdf2txt -o{} {}'.format(output_file.name, absolute_path)
pdf2txt.main(s.split(' ')[1:])
def extract_images(self, input_file):
output_dir = mkdtemp()
with NamedTemporaryFile() as output_file:
commands = [
'-o', output_file.name, '--output-dir', output_dir, input_file
]
pdf2txt.main(commands)
image_files = os.listdir(output_dir)
rmtree(output_dir)
return image_files
)
mock_test_response = session.get(pdf_mock_test_url) # stream=True
mock_test_response.raise_for_status()
mock_test_file = io.BytesIO(mock_test_response.content)
# The pdfReader variable is a readable object that will be parsed
path = os.path.dirname(os.path.abspath(__file__)) + '/tmp/'
file_name = "tmp_{}".format(i)
pdf_file_path = path + file_name+".pdf"
txt_file_path = path + file_name+".txt"
if not os.path.exists(path):
os.makedirs(path)
with open(pdf_file_path, "wb") as f:
f.write(mock_test_response.content)
s = 'pdf2txt -o%s %s' % (txt_file_path, pdf_file_path)
pdf2txt.main(s.split(' ')[1:])
os.remove(pdf_file_path)
with open(txt_file_path, "r+", encoding="utf-8") as f:
tmp_text = f.read()
clean_mock_paper_text = filter_mock_paper_text(tmp_text)
f.write(clean_mock_paper_text)
mock_test_pattern = r"(.*)(Answers\s?:)(.*)"
mock_test_regex = re.compile(mock_test_pattern)
g = mock_test_regex.findall(clean_mock_paper_text)
questions_str = next(g.__iter__())[0]
answers_str = next(g.__iter__())[2]
# question_pattern = r"(\d+\.)(^(\d+\.))*"
# questions_regex = re.compile(question_pattern)
i + 1)
mock_test_response = session.get(pdf_mock_test_url) # stream=True
mock_test_response.raise_for_status()
mock_test_file = io.BytesIO(mock_test_response.content)
# The pdfReader variable is a readable object that will be parsed
path = os.path.dirname(os.path.abspath(__file__)) + '/tmp/'
file_name = "tmp_{}".format(i)
pdf_file_path = path + file_name + ".pdf"
txt_file_path = path + file_name + ".txt"
if not os.path.exists(path):
os.makedirs(path)
with open(pdf_file_path, "wb") as f:
f.write(mock_test_response.content)
s = 'pdf2txt -o%s %s' % (txt_file_path, pdf_file_path)
pdf2txt.main(s.split(' ')[1:])
os.remove(pdf_file_path)
with open(txt_file_path, "r+", encoding="utf-8") as f:
tmp_text = f.read()
clean_mock_paper_text = filter_mock_paper_text(tmp_text)
f.write(clean_mock_paper_text)
mock_test_pattern = r"(.*)(Answers\s?:)(.*)"
mock_test_regex = re.compile(mock_test_pattern)
g = mock_test_regex.findall(clean_mock_paper_text)
questions_str = next(g.__iter__())[0]
answers_str = next(g.__iter__())[2]
# question_pattern = r"(\d+\.)(^(\d+\.))*"
# questions_regex = re.compile(question_pattern)
