def classify_text_files(files_root_path, result_path):
count = 0
flist = os.listdir(files_root_path)
for f in flist:
print '%s:%s' % (count, f)
count += 1
ftext = codecs.open('%s/%s' % (files_root_path, f), 'r').read()
try:
json_obj = json.loads(ftext)
result = passage_first_level_classify(json_obj['post_content'])
except Exception, e: # 懒得差各种异常了，直接重复
print e
continue
try:
fout = codecs.open('%s/%s/%s' % (result_path, result, f), 'w')
except Exception, e:
print e
os.mkdir('%s/%s' % (result_path, result))
fout = codecs.open('%s/%s/%s' % (result_path, result, f), 'w')
def classify_rawtext_files(files_root_path, result_path, pass_num=-1):
count = 0
flist = os.listdir(files_root_path)
for f in flist:
print '%s:%s' % (count, f)
count += 1
if count < pass_num:
continue
ftext = codecs.open(os.path.join(files_root_path, f), 'r').read()
try:
# json_obj = json.loads(ftext)
result = passage_first_level_classify(ftext)
except Exception, e: # 懒得差各种异常了，直接重复
print e
continue
try:
fout = codecs.open(os.path.join(result_path, result, f), 'w')
except Exception, e:
print e
os.mkdir(os.path.join(result_path, result))
fout = codecs.open(os.path.join(result_path, result, f), 'w')
