0x2620/openmedialibrary
1
0
Fork 0
Code Issues 131 Pull requests Releases Wiki Activity

cleanup pdf

Browse source
This commit is contained in:
j 2015-12-25 13:33:32 +05:30
parent 935f8d7f2b
commit c5afc46af1
1 changed files with 8 additions and 9 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

15
oml/media/pdf.py
View file

@ -115,9 +115,6 @@ def info(pdf):
value = value[0] value = value[0]
if isinstance(value, bytes): if isinstance(value, bytes):
value = value.decode('utf-16') value = value.decode('utf-16')
if value in ('Unknown',):
value = None
if value:
data[key[1:].lower()] = value data[key[1:].lower()] = value
except: except:
pass pass
@ -134,15 +131,12 @@ def info(pdf):
value = [v.strftime('%Y-%m-%d') if isinstance(v, datetime) else v for v in value] value = [v.strftime('%Y-%m-%d') if isinstance(v, datetime) else v for v in value]
if len(value) == 1: if len(value) == 1:
value = value[0] value = value[0]
if value in ('Unknown',):
value = None
_key = key[3:] _key = key[3:]
if value and _key not in data: if value and _key not in data:
if _key == 'language':
value = ox.iso.codeToLang(value)
data[_key] = value data[_key] = value
except: except:
logger.debug('FAILED TO PARSE %s', pdf, exc_info=1) logger.debug('FAILED TO PARSE %s', pdf, exc_info=1)
''' '''
cmd = ['pdfinfo', pdf] cmd = ['pdfinfo', pdf]
p = subprocess.Popen(cmd, stdout=subprocess.PIPE, stderr=subprocess.PIPE, close_fds=True) p = subprocess.Popen(cmd, stdout=subprocess.PIPE, stderr=subprocess.PIPE, close_fds=True)
@ -164,7 +158,12 @@ def info(pdf):
for key, value in data.items(): for key, value in data.items():
if isinstance(value, dict): if isinstance(value, dict):
value = ' '.join(list(value.values())) value = ' '.join(list(value.values()))
data[key] = value data[key] = value.strip()
for key in list(data):
if data[key] in ('Unknown',):
del data[key]
if key == 'language':
data[key] = ox.iso.codeToLang(data[key])
text = extract_text(pdf) text = extract_text(pdf)
data['textsize'] = len(text) data['textsize'] = len(text)
if settings.server['extract_text']: if settings.server['extract_text']: