result_list.append(sentence)
index = bi.current();
if __name__=='__main__':
# Получает задание
path_to_targets = 'spider-targets/'
target_file = path_to_targets+'_test_task.txt'
list_targets = read_utf_txt_file(target_file)
#map(printer, list_targets)
# Каждый файл отдельно
#
index_file = 0
for txt_fname in list_targets:
file_content_in_list = read_utf_txt_file(txt_fname)
meta = file_content_in_list[0]
content = file_content_in_list[1:]
# Пишем заголовок
result =[meta, '']
# Токенизируем контент
split_to_sentents(content, result)
# Записываем результаты
path_to_tmp_files = 'result_folder/'
write_result_file(result, path_to_tmp_files+'tmp'+str(index_file)+'.txt')
index_file += 1
print 'Done'
# App
from to_text.tika_wrapper import TextExtractorFromOdtDocPdf
from to_text.tika_wrapper import write_result_file
if __name__=='__main__':
fname = "d:/11832_.pdf"
fname = "d:/t.doc"
fname = "d:/letter.pdf"
ofile = 'u8_3_txt.txt'
fname = 'tests_data/t.pdf'
#class
path_to_node1 = 'D:/home/lugansky-igor/doc_pdf_odt/'
node_name = 'Test Node'
tmp_file_root = 'tmp_folder'
path = File(path_to_node1)
tasks_for_spider_purger = []#'['+node_name+']']
for fname in path.list():
full_name = path_to_node1+fname
extractor = TextExtractorFromOdtDocPdf()
tmp_fname, err_code, err_msg = extractor.process(full_name, tmp_file_root)
tasks_for_spider_purger.append(tmp_fname[0])
path_to_targets = 'spider-targets/'
write_result_file(tasks_for_spider_purger, path_to_targets+'_test_task.txt')
print
print 'Done'
