with open(
target_file.split("\\")[-1].replace(".pdf", "") +
"_py_pdf.txt", "a+"
) as file: # insert the seperate line and datetime everytime run the program
file.write(70 * '=' + "\n")
file.write(
str(datetime.datetime.now()) + "( {0} )\n".format(
calendar.day_name[datetime.datetime.today().weekday()]))
# Process the page one by one
for file_text in file_texts:
i += 1
ac = AcoraBuilder(keywords)
ac = ac.build()
result_list = [
list(element) for element in ac.findall(file_text)
] # turn tuple in the list into List object -- Bug: cannot turn int into list
result_dict = {}
result_dict = combine_column_to_dict(result_list)
if result_dict: # only found result, it will write a line
with open(
target_file.split("\\")[-1].replace(".pdf", "") +
"_py_pdf.txt",
"a+") as file: # insert the search result
file.write("Page {0} : ".format(i) + "\n")
for key, values in result_dict.items():
file.write(
str(key) + ": " + str(values) +
" [Total: {0}".format(len(values.split(","))) +
"]\n")
