Thanks to visit codestin.com
Credit goes to github.com

Skip to content

Commit e3a5a92

Browse files
PeterDingPeterDing
committed
rewrite highlight; fix; update
1 parent d0423ca commit e3a5a92

2 files changed

Lines changed: 102 additions & 42 deletions

File tree

‎README.md‎

Lines changed: 12 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -183,7 +183,9 @@
183183

184184
下载默认为非递归，递归下载加 -R
185185

186-
搜索时，默认在 /。
186+
搜索时，默认在 /
187+
188+
搜索支持高亮
187189

188190
上传模式默认是 c (续传)。
189191

@@ -284,6 +286,10 @@
284286
l -H head -T tail -E "^re(gul.*) ex(p|g)ress$" path1 path2 ..
285287
# 显示文件size, md5
286288
l path1 path2 .. -v
289+
# 空文件夹
290+
l path1 path2 -t e,d
291+
# 非空文件夹
292+
l path1 path2 -t ne,d
287293

288294
# 查看文件占用空间
289295
du path1 path2 .. 文件夹下所有*文件(不包含下层文件夹)*总大小
@@ -317,12 +323,15 @@
317323
-s SECRET, --secret SECRET 提取密码
318324
-f number, --from_ number 从第几个开始(用于download, play)，eg: p /video -f 42
319325
-t ext, --type_ ext 类型参数.
320-
eg: l -t f (文件); l -t d (文件夹)
326+
eg:
327+
l -t f # 文件
328+
l -t d # 文件夹
329+
l -t du # 查看文件占用空间
330+
l -t e,d # 空文件夹
321331
a -t m,d,p,a
322332
u -t r # 只进行 rapidupload
323333
u -t e # 如果云端已经存在则不上传(不比对md5)
324334
u -t r,e
325-
l -t du # 查看文件占用空间
326335
-l amount, --limit amount 下载速度限制，eg: -l 100k
327336
-m {o,c}, --uploadmode {o,c} 上传模式: o # 重新上传. c # 连续上传.
328337
-R, --recursive 递归, 用于download, play, ls, find, rmre, rnre, rmre, cpre

‎pan.baidu.com.py‎

Lines changed: 90 additions & 39 deletions
Original file line numberDiff line numberDiff line change
@@ -105,6 +105,10 @@ class panbaiducom_HOME(object):
105105
def __init__(self):
106106
self._download_do = self._play_do if args.play else self._download_do
107107
self.ondup = 'overwrite'
108+
self.highlights = {}
109+
if args.tail: self.highlights['tail'] = {'text': args.tail.decode('utf8', 'ignore'), 'is_regex': 0}
110+
if args.head: self.highlights['head'] = {'text': args.head.decode('utf8', 'ignore'), 'is_regex': 0}
111+
if args.include: self.highlights['include'] = {'text': args.include.decode('utf8', 'ignore'), 'is_regex': 1}
108112

109113
def init(self):
110114
if os.path.exists(cookie_file):
@@ -248,7 +252,7 @@ def sort(reverse, arg, fileslist=fileslist):
248252
reverse = False
249253
fileslist = sort(reverse, 'size')
250254

251-
# for size
255+
# for time
252256
if arguments.get('time'):
253257
reverse = None
254258
if arguments['time'] == 'reverse':
@@ -291,14 +295,26 @@ def sort(reverse, arg, fileslist=fileslist):
291295
fileslist = [fileslist[i] for i in indexs]
292296

293297
dirs = [i for i in fileslist if i['isdir']]
298+
t, tt = [], []
299+
args.type_ = args.type_ if args.type_ else ''
300+
if 'e' in args.type_:
301+
for i in dirs:
302+
d = i['path'].encode('utf8')
303+
j = self._get_file_list('name', None, d, 1, all=False)
304+
if not j['list']:
305+
t.append(i)
306+
else:
307+
tt.append(i)
308+
if 'e' in args.type_.split(','): dirs = t
309+
if 'ne' in args.type_.split(','): dirs = tt
294310
files = [i for i in fileslist if not i['isdir']]
295311
if arguments.get('desc') == 1:
296312
dirs.reverse()
297313
files.reverse()
298314

299-
if args.type_ == 'f':
315+
if 'f' in args.type_:
300316
fileslist = files
301-
elif args.type_ == 'd':
317+
elif 'd' in args.type_:
302318
fileslist = dirs
303319
else:
304320
fileslist = dirs + files
@@ -315,7 +331,7 @@ def _get_path(self, url):
315331
t = urllib.unquote_plus(t)
316332
return t
317333

318-
def _get_file_list(self, order, desc, dir_):
334+
def _get_file_list(self, order, desc, dir_, num, all=True):
319335
t = {'Referer':'http://pan.baidu.com/disk/home'}
320336
theaders = headers
321337
theaders.update(t)
@@ -324,14 +340,15 @@ def _get_file_list(self, order, desc, dir_):
324340
"channel": "chunlei",
325341
"clienttype": 0,
326342
"web": 1,
327-
"num": 10000, ## max amount of listed file at one page
343+
"showempty": 1,
344+
"num": num, ## max amount is 10000
328345
"t": int(time.time()*1000),
329346
"dir": dir_,
330347
"page": 1,
331348
"desc": 1, ## reversely
332349
"order": order, ## sort by name, or size, time
333-
"_": int(time.time()*1000)
334-
#"bdstoken": token
350+
"_": int(time.time()*1000),
351+
#"bdstoken": self._get_bdstoken(),
335352
}
336353
if not desc: del p['desc']
337354
url = 'http://pan.baidu.com/api/list'
@@ -346,7 +363,9 @@ def _get_file_list(self, order, desc, dir_):
346363
else:
347364
infos += j['list']
348365

349-
if len(infos) == 10000:
366+
if not all: return j
367+
368+
if len(infos) == num:
350369
p['page'] += 1
351370
else:
352371
j['list'] = infos
@@ -471,7 +490,7 @@ def download(self, paths):
471490
if meta['info'][0]['isdir']:
472491
dir_loop = [path]
473492
for d in dir_loop:
474-
j = self._get_file_list('name', None, d)
493+
j = self._get_file_list('name', None, d, 10000)
475494
if j['list']:
476495
if args.recursive:
477496
for i in j['list']:
@@ -869,7 +888,7 @@ def _upload_file(self, lpath, rpath):
869888
self.upload_datas[lpath]['is_over'] = True
870889
self.upload_datas[lpath]['remotepaths'].update([rpath])
871890
#self.save_upload_datas()
872-
print s % (1, 92, ' |-- success.\n')
891+
print s % (1, 92, '\n |-- success.\n')
873892
break
874893
else:
875894
print s % (1, 91, ' !! Error: _upload_one_file is fall, retry.')
@@ -1216,6 +1235,33 @@ def _search(self, keyword, directory):
12161235
print s % (1, 91, ' !! Error at _search'), j
12171236
sys.exit(1)
12181237

1238+
def _highlight_filename_zones(self, info):
1239+
filename = info['server_filename']
1240+
target = ['.' for i in xrange(len(filename))]
1241+
for hl in self.highlights.values():
1242+
re_tp = hl['text'] if hl['is_regex'] else re.escape(hl['text'])
1243+
for m in re.finditer(re_tp, filename, re.I):
1244+
for i in xrange(m.start(), m.end()):
1245+
target[i] = ' '
1246+
1247+
highlight_zones = []
1248+
for m in re.finditer('\s+', ''.join(target)):
1249+
highlight_zones.append(m.start())
1250+
highlight_zones.append(m.end())
1251+
1252+
filename_zones = []
1253+
for i in xrange(len(highlight_zones)):
1254+
if i == 0:
1255+
filename_zones.append(filename[:highlight_zones[i]])
1256+
filename_zones.append(filename[highlight_zones[i]:highlight_zones[i+1]])
1257+
else:
1258+
try:
1259+
filename_zones.append(filename[highlight_zones[i]:highlight_zones[i+1]])
1260+
except:
1261+
filename_zones.append(filename[highlight_zones[i]:])
1262+
1263+
return filename_zones if filename_zones else [filename]
1264+
12191265
def _find_display(self, info):
12201266
if args.type_ == 'f':
12211267
if info['isdir']:
@@ -1229,26 +1275,24 @@ def _find_display(self, info):
12291275
if args.ls_color == 'on':
12301276
isdir = s % (1, 93, 'd') if info['isdir'] else s % (1, 97, '-')
12311277
size = s % (1, 91, sizeof_fmt(info['size']).rjust(8))
1232-
base_dir, filename = os.path.split(info['path'])
1278+
base_dir = os.path.split(info['path'])[0]
12331279
base_dir = s % (2, 95, base_dir.encode('utf8')) if base_dir != '/' else '/'
12341280

1235-
highligh_text = info.get('highligh_text')
1236-
ii = filename.lower().find(highligh_text.lower()) if highligh_text else -1
1237-
if ii != -1: highligh_text = filename[ii:ii+len(highligh_text)]
1238-
t1 = filename[:ii] if ii != -1 else filename
1239-
t2 = filename[ii+len(highligh_text):] if ii != -1 else u''
1240-
if info['isdir']:
1241-
t1 = s % (2, 94, t1.encode('utf8'))
1242-
t2 = s % (2, 94, t2.encode('utf8')) if t2 else ''
1243-
highligh_text = s % (2, 93, highligh_text.encode('utf8')) \
1244-
if ii != -1 else ''
1245-
filename = t1 + highligh_text + t2
1246-
else:
1247-
t1 = t1.encode('utf8')
1248-
t2 = t2.encode('utf8') if t2 else ''
1249-
highligh_text = s % (2, 93, highligh_text.encode('utf8')) \
1250-
if ii != -1 else ''
1251-
filename = t1 + highligh_text + t2
1281+
filename_zones = self._highlight_filename_zones(info)
1282+
t = ''
1283+
for i in xrange(0, len(filename_zones), 2):
1284+
if info['isdir']:
1285+
try:
1286+
t += s % (2, 94, filename_zones[i].encode('utf8')) + s % (2, 93, filename_zones[i+1].encode('utf8'))
1287+
except:
1288+
t += s % (2, 94, filename_zones[i].encode('utf8'))
1289+
else:
1290+
try:
1291+
t += filename_zones[i].encode('utf8') + s % (2, 93, filename_zones[i+1].encode('utf8'))
1292+
except:
1293+
t += filename_zones[i].encode('utf8')
1294+
filename = t
1295+
12521296
path = os.path.join(base_dir, filename)
12531297

12541298
elif args.ls_color == 'off':
@@ -1267,9 +1311,9 @@ def _find_display(self, info):
12671311
def find(self, keywords, **arguments):
12681312
infos = []
12691313
for keyword in keywords:
1270-
t = self._search(keyword, arguments.get('directory'))
1271-
for i in xrange(len(t)): t[i]['highligh_text'] = keyword.decode('utf8', 'ignore')
1272-
infos += t
1314+
infos += self._search(keyword, arguments.get('directory'))
1315+
kw = keyword.decode('utf8', 'ignore')
1316+
self.highlights['find'] = {'text': kw, 'is_regex': 0}
12731317
infos = {i['fs_id']: i for i in infos}.values()
12741318
infos = self._sift(infos, name=arguments.get('name'), \
12751319
size=arguments.get('size'), time=arguments.get('time'), \
@@ -1342,9 +1386,9 @@ def _ls_directory(self, order, desc, path):
13421386
y = 1
13431387
sum_size = 0
13441388
for dir_ in directorys:
1345-
infos = self._get_file_list(order, desc, dir_.encode('utf8'))['list']
1389+
infos = self._get_file_list(order, desc, dir_.encode('utf8'), 10000)['list']
13461390
tinfos = infos
1347-
if args.head or args.tail or args.include or args.exclude:
1391+
if args.head or args.tail or args.include or args.exclude or args.type_:
13481392
tinfos = self._sift(infos)
13491393
if args.type_ != 'du':
13501394
self._ls_display(tinfos, dir_)
@@ -1531,7 +1575,7 @@ def rnre(self, foo, bar, dirs):
15311575
directorys = [path.decode('utf8', 'ignore')]
15321576
y = 1
15331577
for dir_ in directorys:
1534-
infos = self._get_file_list('name', None, dir_.encode('utf8'))['list']
1578+
infos = self._get_file_list('name', None, dir_.encode('utf8'), 10000)['list']
15351579
t = infos
15361580
if args.type_ == 'f' or args.type_ == 'd':
15371581
t = self._sift(infos)
@@ -1551,7 +1595,7 @@ def rnre(self, foo, bar, dirs):
15511595
self._rnre_do(foo, bar, tinfos)
15521596

15531597
def _rmre_do(self, infos):
1554-
if args.recursive and args.type_ == 'f':
1598+
if args.recursive and 'f' in args.type_:
15551599
paths = [i['path'].encode('utf8') for i in infos if not i['isdir']]
15561600
else:
15571601
paths = [i['path'].encode('utf8') for i in infos]
@@ -1576,7 +1620,7 @@ def rmre(self, dirs):
15761620
directorys = [path.decode('utf8', 'ignore')]
15771621
y = 1
15781622
for dir_ in directorys:
1579-
infos = self._get_file_list('name', None, dir_.encode('utf8'))['list']
1623+
infos = self._get_file_list('name', None, dir_.encode('utf8'), 10000)['list']
15801624
tinfos += infos
15811625
if args.recursive:
15821626
subdirs = [i['path'] for i in infos if i['isdir']]
@@ -1622,7 +1666,7 @@ def cmre(self, type, dirs, todir):
16221666
directorys = [path.decode('utf8', 'ignore')]
16231667
y = 1
16241668
for dir_ in directorys:
1625-
infos = self._get_file_list('name', None, dir_.encode('utf8'))['list']
1669+
infos = self._get_file_list('name', None, dir_.encode('utf8'), 10000)['list']
16261670
tinfos += infos
16271671
if args.recursive:
16281672
subdirs = [i['path'] for i in infos if i['isdir']]
@@ -2205,6 +2249,10 @@ def main(argv):
22052249
sl -H head -T tail -E "^re(gul.*) ex(p|g)ress$" path1 path2 ..
22062250
# 显示文件size, md5
22072251
sl path1 path2 .. -v
2252+
# 空文件夹
2253+
l path1 path2 -t e,d
2254+
# 非空文件夹
2255+
l path1 path2 -t ne,d
22082256
22092257
# 查看文件占用空间
22102258
du path1 path2 .. 文件夹下所有*文件(不包含下层文件夹)*总大小
@@ -2250,12 +2298,15 @@ def main(argv):
22502298
-s SECRET, --secret SECRET 提取密码
22512299
-f number, --from_ number 从第几个开始下载，eg: -f 42
22522300
-t ext, --type_ ext 类型参数.
2253-
eg: l -t f (文件); l -t d (文件夹)
2301+
eg:
2302+
l -t f # 文件
2303+
l -t d # 文件夹
2304+
l -t du # 查看文件占用空间
2305+
l -t e,d # 空文件夹
22542306
a -t m,d,p,a
22552307
u -t r # 只进行 rapidupload
22562308
u -t e # 如果云端已经存在则不上传(不比对md5)
22572309
u -t r,e
2258-
l -t du # 查看文件占用空间
22592310
-l amount, --limit amount 下载速度限制，eg: -l 100k
22602311
-m {o,c}, --uploadmode {o,c} 上传模式: o --> 重新上传. c --> 连续上传.
22612312
-R, --recursive 递归, 用于download, play, ls, find, rmre, rnre, rmre, cpre

0 commit comments

Comments
 (0)