事實證明,這是pytesseract無法找到臨時的輸出文件是他們在被存儲比.txt或.box的其他擴展的原因(他們.hocr文件) 。從源代碼中,這些是pytesseract支持的唯一類型的tesseract輸出文件(或者更像是pytesseract的「查找」)。從源頭上相關的片段低於:
input_file_name = '%s.bmp' % tempnam() output_file_name_base = tempnam() if not boxes: output_file_name = '%s.txt' % output_file_name_base else: 123 output_file_name = '%s.box' % output_file_name_base
if status: errors = get_errors(error_string) raise TesseractError(status, errors) 135 f = open(output_file_name, 'rb')
在pytesseract的github上pulls來看,這似乎是對其它輸出類型,計劃但尚未實施的支持(我使用的源代碼以顯示爲什麼.hocr文件似乎未被發現是從pytesseract master分支複製/粘貼)。
在此之前,我對pytesseract腳本進行了一些篡改,以支持多種文件類型。
此版本沒有爲輸出文件設置擴展名(因爲tesseract會自動執行此擴展)並查看pytesseract將其臨時輸出文件存儲到的目錄,並查找以輸出文件名開頭的文件(最多「」通過pytesseract分配的第一個字符)(無需關心擴展名):
def tempnam():
''' returns a temporary file-name and directory '''
tmpfile = tempfile.NamedTemporaryFile(prefix="tess_")
return tmpfile.name, tempfile.tempdir
def image_to_string(image, lang=None, boxes=False, config=None, nice=0):
if len(image.split()) == 4:
# In case we have 4 channels, lets discard the Alpha.
# Kind of a hack, should fix in the future some time.
r, g, b, a = image.split()
image = Image.merge("RGB", (r, g, b))
(input_file_name, _) = tempnam() #'%s.bmp' % tempnam()
input_file_name += '.bmp'
(output_file_name_base, output_filename_base_dir) = tempnam()
if not boxes:
# Don’t put an extension on the output file name because Tesseract will do it automatically
output_file_name = '%s' % output_file_name_base
else:
output_file_name = '%s.box' % output_file_name_base
try:
########## DEBUGGING
#print('input file name: %s' % input_file_name)
#print('temp output name: %s' % output_file_name)
#print('temp output dir: %s' % output_filename_base_dir)
##########
image.save(input_file_name)
status, error_string = run_tesseract(input_file_name,
output_file_name_base,
lang=lang,
boxes=boxes,
config=config,
nice=nice)
if status:
errors = get_errors(error_string)
raise TesseractError(status, errors)
# find the temp output file in temp dir under whatever extension tesseract has assigned
output_file_name += '.'
output_file_name_leaf = os.path.basename(output_file_name)
print('**output file starts with %s, type: %s' % (output_file_name, type(output_file_name)))
l=os.listdir(output_filename_base_dir)
for f in l:
if f.startswith(output_file_name_leaf):
output_file_name_leaf = f
break
output_file_name_abs = os.path.join(output_filename_base_dir, output_file_name_leaf)
f = open(output_file_name_abs, 'rb')
try:
return f.read().decode('utf-8').strip()
finally:
f.close()
finally:
cleanup(input_file_name)
# if successfully created and opened temp output file
if 'output_file_name_abs' in locals():
output_file_name = output_file_name_abs
print('**temp output file %s successfully created and deleted' % output_file_name)
cleanup(output_file_name)
希望這有助於他人。