def main(self):
self.get_user_input()
# get all of .wiz
self.get_all_of_wiz()
# unzip all of wiz files.
self.unzip_wiz()
# remove blank dir.
Path.remove_blank_dir(self._dst)
def get_face_image():
fid = None
sid = None
args = Base.get_user_input('hf:s:')
if '-h' in args:
Base.print_help(help_menu)
if '-f' in args:
fid = Path.get_abs_path(args['-f'])
if '-s' in args:
sid = Path.get_abs_path(args['-s'])
return fid, sid
def get_input(self, args=None):
if not args:
args = Base.get_user_input('hu:n:p:x:m:R:t:UvDd')
if '-h' in args:
Base.print_help(self.HELP_MENU)
if '-U' in args:
self._run_ui = True
if '-u' in args:
if os.path.isfile(args['-u']):
self._url_file = Path.get_abs_path(args['-u'])
else:
self._url = re.sub('/$', '', args['-u'])
if '-x' in args:
self._xval = args['-x']
if '-d' in args:
self._pr.set_pr_level(self._pr.get_pr_level() | Print.PR_LVL_DBG)
# get url_base from xval
if self._xval:
if self._xval in URL_BASE:
self._url_base = list(URL_BASE[self._xval])[0]
self._class = URL_BASE[self._xval][self._url_base]
else:
Base.print_exit('[WebImageCrawler] Error, invalid -x val!')
# get class from url
if self._url:
base, num = self.get_url_base_and_num(self._url)
if base:
self._url_base = base
# get class from url_base
if all((not self._class, self._url_base)):
for dict_url_base in URL_BASE.values():
if self._url_base == list(dict_url_base)[0]:
self._class = dict_url_base[self._url_base]
break
return args
def get_url_content(cls, url, retry_times=3, view=True, path=None):
if cls.url_is_https(url):
content = cls.get_html(url=url,
context=cls.CONTEXT_UNVERIFIED,
retry_times=retry_times,
view=view)
else:
content = cls.get_html(url=url, retry_times=retry_times, view=view)
# save content to path.
if all((content, path)):
Path.make_path(path)
f = '%s/%s' % (path, cls.convert_url_to_title(url))
if File.get_exname(f) != '.html':
f = f + '.html'
with open(f, 'w') as fd:
fd.write(content)
return content
def get_user_input(self):
args = Base.get_user_input('hs:t:')
if '-h' in args:
Base.print_help(self.HELP_MENU)
if '-s' in args:
self._src = re.sub('/$', '', args['-s'])
if '-t' in args:
self._tgt = Path.get_abs_path(args['-t'])
return args
def unzip_wiz(self):
for f in self._fs:
path = os.path.join(
os.path.dirname(f).replace(self._src, self._dst),
File.get_fname(f))
path = os.path.splitext(path)[0]
Path.make_path(path)
self.unzip_file(f, path)
# remove small image.
Image.remove_small_image(path)
# move image.
if os.path.exists('%s/index_files' % path):
for ff in os.listdir('%s/index_files' % path):
if Image.image_file('%s/index_files/%s' % (path, ff)):
shutil.copyfile('%s/index_files/%s' % (path, ff),
'%s/%s' % (path, ff))
# remove invalid files and dirs.
shutil.rmtree('%s/index_files' % path)
if os.path.exists('%s/index.html' % path):
os.remove('%s/index.html' % path)
def get_user_input(self):
args = Base.get_user_input('hs:t:v')
# help
if '-h' in args:
Base.print_help(self.help_menu)
# src path
if '-s' in args:
self._src = Path.get_abs_path(args['-s'])
# dst path
if '-t' in args:
self._dst = Path.get_abs_path(args['-t'])
# show
if '-v' in args:
self._show = True
# start to check args.
# start id is must be set, otherwise return..
if self._src == None:
return False
# next to start if _end is not set.
if self._dst == None:
self._dst = Path.get_current_path()
print('warnning: no found -t, output to: %s' % self._dst)
return True
' view info of webcontent.',
)
path = None
url = None
df = None
view = False
wc = WebContent()
pr = Print(wc.__class__.__name__)
args = Base.get_user_input('hp:u:d:v')
if '-h' in args:
Base.print_help(HELP_MENU)
if '-p' in args:
path = Path.get_abs_path(args['-p'])
if '-u' in args:
url = args['-u']
if '-v' in args:
view = True
wc.pr.set_pr_level(0x07)
if '-d' in args:
df_funcs = {
'wget': wc.wget_url_file,
'rtrv': wc.retrieve_url_file,
'rget': wc.requests_get_url_file,
'uget': wc.urlopen_get_url_file,
'html': wc.get_url_content,
}
if all((args['-d'] in df_funcs.keys(), url)):
df = df_funcs[args['-d']]
if File.get_exname(f) == '.pyc':
os.remove(f)
if show:
print('remove: %s' % f)
if dr:
for d in dr:
if d == '__pycache__':
os.remove(d)
if __name__ == '__main__':
args = Base.get_user_input('hp:vc')
# help
if '-h' in args:
Base.print_help(help_menu)
# check path.
if '-p' in args:
if re.match('\.', args['-p']):
path = re.sub('.', Path.get_current_path(), args['-p'])
else:
path = args['-p']
else:
path = Path.get_current_path()
# check show.
if '-v' in args:
show = True
else:
show = False
# clean .pyc now.
clean_pyc(path, show)
' -o path,rename,nz: rename image to order',
' path: path of images',
' rename: the format of image to be rename',
' nz: True is set %0d, False is set %d',
' -i img: show detail info of image file',
' img: the path of image file',
)
Img = Image()
pr = Print(Img.__class__.__name__)
xval = None
args = Base.get_user_input('hc:r:R:x:o:i:')
if '-h' in args:
Base.print_help(HELP_MENU)
if '-c' in args:
result = Img.image_file(Path.get_abs_path(args['-c']))
pr.pr_info(result)
if '-r' in args:
data = args['-r'].split(',')
path = data[0]
if len(data) >=2:
w = data[1]
h = data[2]
Img.remove_small_image(path, int(w), int(h))
else:
Img.remove_small_image(path)
if '-R' in args:
path = args['-R']
if Img.image_file(path):
Img.reclaim_image(path)
else:
def download_image(self, url, path):
if self._dl_image:
Path.make_path(path)
self._dl_image(url, path, self.__dbg)